CN115733980A - Video transmission method, system, electronic device, storage medium and chip system - Google Patents

Abstract

This application is applicable to the field of video technology, and provides a video transmission method, system, electronic equipment, storage medium and chip system. The method includes: determining two groups of video frames according to the video data of the target video, each group of video frames The resolutions of the video frames are the same, and the resolution of one group of video frames is greater than that of the other group of video frames, and any video frame in one group of video frames has the same frame number as any video frame in another group Differently, each group of video frames includes a plurality of video frames with intermittent frame numbers; each group of video frames is encoded separately to obtain the encoded data corresponding to each group of video frames; and each of the encoded data is sent. By encoding and transmitting each encoded data with different resolutions, the compression rate can be increased by 30%-40%, so that the compression rate of the video data of the target video can be effectively improved, the network bandwidth resources occupied by the transmission of video data can be reduced, and network bandwidth resources can be avoided. The waste of bandwidth resources reduces the cost of transmitting video data.

Description

Video transmission method, system, electronic device, storage medium and chip system

technical field

The present application relates to the field of video technology, and in particular to a video transmission method, system, electronic equipment, storage medium and chip system.

Background technique

With the continuous development of data streaming media, the storage space occupied by video data continues to increase. Correspondingly, the transmission of video data through the Internet has also caused increasingly tight network bandwidth resources. Therefore, it is necessary to compress the video data.

In order to alleviate the situation of video data transmission occupying network bandwidth, currently, in the process of sending video data from the sending device to the receiving device, the sending device can first compress the video data to be transmitted according to the video coding rules, and then send the video data to the receiving device. The end device sends the compressed video data. However, the compressed video data still occupies more network bandwidth resources during transmission.

Contents of the invention

The present application provides a video transmission method, system, electronic equipment, storage medium and chip system, which solves the problem in the prior art that more network bandwidth resources are still occupied in the process of transmitting video data.

In order to achieve the above object, the application adopts the following technical solutions:

In the first aspect, a video transmission method is provided, the method is applied to a video transmission system composed of a sending end device and a receiving end device, and the method includes:

The sending end device determines two groups of video frames according to the video data of the target video, the resolution of each video frame in each group of video frames is the same, and the resolution of one group of video frames is greater than the resolution of the other group of video frames, one group of video frames The frame number of any video frame in the group of video frames is different from the frame number of any video frame in another group of video frames, and each group of video frames includes a plurality of video frames with intermittent frame numbers;

The sending end device encodes each group of video frames respectively, to obtain encoded data corresponding to each group of video frames;

The sending end device sends first coded data and second coded data respectively corresponding to the two groups of video frames, the resolution corresponding to the first coded data is greater than the resolution corresponding to the second coded data;

The receiver device receives the first coded data and the second coded data;

Decoding the first encoded data and the second encoded data by the receiving end device respectively, to obtain first decoded data corresponding to the first encoded data and second decoded data corresponding to the second encoded data, The resolution of the first decoded data is greater than the resolution of the second decoded data.

The sending end device determines two groups of video frames according to the video data of the target video, and encodes and compresses each group of video frames to obtain the encoded data corresponding to each group of video frames, and then sends each encoded data to the receiving end device, and transmits different resolutions through encoding. Each coded data with high rate can increase the compression rate by 30%-40%, thereby effectively improving the compression rate of the video data of the target video, reducing the network bandwidth resources occupied when transmitting video data, and avoiding the waste of network bandwidth resources. Reduce the cost of transmitting video data.

The receiving end device decodes the first encoded data and the second encoded data to obtain the first decoded data and the second decoded data, and then synthesizes the first decoded data and the second decoded data to obtain the synthesized video data, and the receiving end The device only stores the first coded data and the second coded data that occupy less storage space, and can realize the video data of the target video, without storing the video data of the high-resolution target video, which can reduce the occupied storage space and improve the storage capacity. Space utilization.

In a first possible implementation manner of the first aspect, the video data of the target video includes: first video data and second video data;

The sending end device determines two groups of video frames according to the video data of the target video, including:

The sending end device down-samples the first video data to obtain the second video data, and the resolution of each video frame in the first video data is higher than that of each video frame in the second video data resolution;

The sending device selects a plurality of video frames from the first video data and the second video data to obtain the two groups of video frames.

In a second possible implementation manner of the first aspect, the resolutions of the video frames in the video data of the target video are the same;

The sending end device determines two groups of video frames according to the video data of the target video, including:

The sending end device selects a part of video frames from the video data of the target video to obtain a set of video frames;

The sending end device down-samples another part of video frames in the video data of the target video to obtain another group of video frames.

The sending end device obtains the video data of the target video in different ways, and encodes the video data of the target video in a way corresponding to the acquisition method, which can improve the flexibility of obtaining video data, and can also improve the video data of the target video. Coding flexibility.

Based on the above-mentioned first or second possible implementation of the first aspect, in the third possible implementation of the first aspect, in a group of video frames with a larger resolution of the two groups of video frames , the difference between the frame numbers of every two adjacent video frames is m, where m is a positive integer greater than 1.

By arranging the video frames with discontinuous frame numbers in a group of video frames with relatively large resolution, the storage space occupied by the group of video frames can be reduced, and the compression rate of encoding the group of video frames can be improved.

Based on any one of the above-mentioned first to third possible implementation manners of the first aspect, in the fourth possible implementation manner of the first aspect, in the one with the smaller resolution of the two groups of video frames A group of video frames includes multiple groups of video frames with consecutive frame numbers, and the number of video frames included in each group of video frames with consecutive frame numbers is n, where n is a positive integer greater than or equal to 1.

By arranging video frames with continuous frame numbers or discontinuous frame numbers in a group of video frames with a smaller resolution, the storage space occupied by the group of video frames can be reduced, and the encoding of the group of video frames can be improved. the compression rate.

Based on any one of the above possible implementation manners of the first aspect, in a fifth possible implementation manner of the first aspect, the frame numbers of the video frames obtained after combining the two groups of video frames are continuous.

The frame numbers of the video frames included in the two groups of video frames are consecutive, which means that the two groups of video frames are complementary, which can improve the accuracy of the recovered video frames, thereby improving the playback effect of the synthesized video data.

Based on any of the above possible implementations of the first aspect, in a sixth possible implementation of the first aspect, before the sending device determines two groups of video frames according to the video data of the target video, the method Also includes:

The sending end device obtains the video data of the target video from the storage space;

Alternatively, the sending end device collects video data of the target video in real time.

By adopting different ways to acquire video data, the flexibility of acquiring video data can be improved, and the acquired video data can also be encoded by using an encoding mode corresponding to the acquisition mode.

Based on any of the above possible implementations of the first aspect, in a seventh possible implementation of the first aspect, the sending end device sends the first coded data and the second coded data respectively corresponding to the two groups of video frames. Encoded data, including:

The sending end device sends the first encoded data and the second encoded data respectively corresponding to the two groups of video frames to the receiving end device;

Alternatively, the sending end device sends the first encoded data and the second encoded data respectively corresponding to the two groups of video frames to the server, and the server is used to forward the two groups of video frames to the receiving end device The frames respectively correspond to the first encoded data and the second encoded data.

By sending encoded data in different ways, the flexibility of sending encoded data can be improved.

In an eighth possible implementation manner of the first aspect, the receiver device processes the second decoded data according to the first decoded data to obtain a resolution that is the same as that of the first decoded data. Restoration frames, including:

The receiver device processes the video frames of the second decoded data according to the video frames of the first decoded data through a preset artificial intelligence AI super-resolution model to obtain the restored frames.

The receiver device uses the AI super-resolution model to process the low-resolution video frames according to the high-resolution video frames adjacent to the frame number, and utilizes the high-frequency spatial information of the high-resolution video frames, which can reduce the complexity of the super-resolution network In this way, the operating conditions of the AI super-resolution model can be reduced, and the AI super-resolution model can be run through a portable terminal, which improves the versatility of the AI super-resolution model.

Based on the above-mentioned eighth possible implementation of the first aspect, in the ninth possible implementation of the first aspect, the receiver device uses a preset artificial intelligence AI super-resolution model, according to the first decoding The video frame of the data is processed to the video frame of the second decoded data to obtain the restored frame, including:

The receiving end device inputs the first video frame of the second decoded data and at least one video frame whose frame number is continuous with the first video frame into the AI super-resolution model to obtain the first video frame The frame corresponding to the restored frame.

In the process of processing video frames through the AI super-resolution model, the receiver device can obtain information about missing frames based on low-resolution video frames. While saving network bandwidth resources, it also reduces the complexity of processing video frames and improves restoration. frame accuracy.

In a second aspect, a video transmission method is provided, the method comprising:

Determine two groups of video frames according to the video data of the target video, the resolution of each video frame in each group of video frames is the same, and the resolution of one group of video frames is greater than the resolution of the other group of video frames, and the resolution of each group of video frames in a group of video frames Any video frame has a different frame number from any video frame in another group of video frames, and each group of video frames includes multiple video frames with intermittent frame numbers;

Encoding each group of video frames respectively to obtain encoded data corresponding to each group of video frames;

Each of said coded data is transmitted.

Wherein, the discontinuous frame number is used to indicate that the frame numbers of two video frames are discontinuous. Correspondingly, each group of video frames includes adjacent video frames whose frame number difference is a positive integer greater than 1.

In a first possible implementation manner of the second aspect, the video data of the target video includes: first video data and second video data;

The said determination of two groups of video frames according to the video data of the target video includes:

Downsampling the first video data to obtain the second video data, the resolution of each video frame in the first video data is higher than the resolution of each video frame in the second video data;

Selecting a plurality of video frames from the first video data and the second video data to obtain the two groups of video frames.

In a second possible implementation manner of the second aspect, the resolutions of the video frames in the video data of the target video are the same;

The said determination of two groups of video frames according to the video data of the target video includes:

Selecting a part of video frames from the video data of the target video to obtain a set of video frames;

Downsampling is performed on another part of video frames in the video data of the target video to obtain another group of video frames.

Based on the above-mentioned first or second possible implementation of the second aspect, in the third possible implementation of the second aspect, in a group of video frames with a larger resolution of the two groups of video frames , the difference between the frame numbers of every two adjacent video frames is m, where m is a positive integer greater than 1.

Based on any one of the above-mentioned first to third possible implementation manners of the second aspect, in the fourth possible implementation manner of the second aspect, in the one with the smaller resolution of the two groups of video frames A group of video frames includes multiple groups of video frames with consecutive frame numbers, and the number of video frames included in each group of video frames with consecutive frame numbers is n, where n is a positive integer greater than or equal to 1.

Based on any one of the above possible implementation manners of the second aspect, in a fifth possible implementation manner of the second aspect, the frame numbers of the video frames obtained after combining the two groups of video frames are continuous.

Based on any of the above possible implementations of the second aspect, in a sixth possible implementation of the second aspect, before determining two groups of video frames according to the video data of the target video, the method further includes:

Acquiring the video data of the target video from the storage space;

Alternatively, video data of the target video is collected in real time.

Based on any of the above possible implementation manners of the second aspect, in a seventh possible implementation manner of the second aspect, the sending each of the encoded data includes:

Send each of the encoded data to the receiving end device;

Alternatively, each of the encoded data is sent to a server, and the server is configured to forward each of the encoded data to the receiving end device.

In a third aspect, a video transmission method is provided, the method comprising:

receiving first encoded data and second encoded data of the target video, where the resolutions corresponding to the first encoded data and the second encoded data are different;

Decoding the first encoded data and the second encoded data respectively to obtain first decoded data corresponding to the first encoded data and second decoded data corresponding to the second encoded data, the first decoded The resolution of the data is greater than the resolution of the second decoded data;

Process the second decoded data according to the first decoded data to obtain a restored frame with the same resolution as the first decoded data;

Combining the first decoded data and the restored frame to obtain video data of the target video.

In a first possible implementation manner of the third aspect, according to the first decoded data, the second decoded data is processed to obtain restored frames with the same resolution as the first decoded data, include:

The restored frame is obtained by processing the video frame of the second decoded data according to the video frame of the first decoded data through a preset AI super-resolution model.

Based on the above-mentioned first possible implementation of the third aspect, in the second possible implementation of the third aspect, the preset AI super-resolution model, according to the video frame of the first decoded data, Processing the video frame of the second decoded data to obtain the restored frame includes:

Inputting the first video frame of the second decoded data and at least one video frame whose frame number is continuous with the first video frame into the AI super-resolution model to obtain a restored frame corresponding to the first video frame .

In a fourth aspect, a video transmission device is provided, the device comprising:

The encoding module is used to determine two groups of video frames according to the video data of the target video, the resolution of each video frame in each group of video frames is the same, and the resolution of one group of video frames is greater than the resolution of another group of video frames, one group of video frames The frame number of any video frame in the group of video frames is different from the frame number of any video frame in another group of video frames, and each group of video frames includes a plurality of video frames with intermittent frame numbers;

The encoding module is also used to encode each group of video frames respectively to obtain the corresponding encoded data of each group of video frames;

A sending module, configured to send each of the coded data.

In a first possible implementation manner of the fourth aspect, the video data of the target video includes: first video data and second video data;

The encoding module is specifically configured to down-sample the first video data to obtain the second video data, and the resolution of each video frame in the first video data is higher than that of each video frame in the second video data. The resolution of the video frame; respectively selecting a plurality of video frames from the first video data and the second video data to obtain the two groups of video frames.

In a second possible implementation manner of the fourth aspect, the resolutions of the video frames in the video data of the target video are the same;

The coding module is specifically used to select a part of video frames from the video data of the target video to obtain a set of video frames; down-sample another part of the video frames in the video data of the target video to obtain another set of video frames video frame.

Based on the above-mentioned first or second possible implementation of the fourth aspect, in the third possible implementation of the fourth aspect, in the group of video frames with a larger resolution of the two groups of video frames , the difference between the frame numbers of every two adjacent video frames is m, where m is a positive integer greater than 1.

Based on any one of the above-mentioned first to third possible implementations of the fourth aspect, in the fourth possible implementation of the fourth aspect, in the one with the smaller resolution of the two groups of video frames A group of video frames includes multiple groups of video frames with consecutive frame numbers, and the number of video frames included in each group of video frames with consecutive frame numbers is n, where n is a positive integer greater than or equal to 1.

Based on any one of the above possible implementation manners of the fourth aspect, in a fifth possible implementation manner of the fourth aspect, the frame numbers of the video frames obtained after combining the two groups of video frames are continuous.

Based on any of the above possible implementation manners of the fourth aspect, in a sixth possible implementation manner of the fourth aspect, the device further includes:

An acquisition module, configured to acquire video data of the target video from a storage space;

Or, an acquisition module, configured to acquire video data of the target video in real time.

Based on any one of the above possible implementation manners of the fourth aspect, in a seventh possible implementation manner of the fourth aspect, the sending module is specifically configured to send each of the encoded data to the receiving end device;

Alternatively, the sending module is specifically configured to send each of the encoded data to a server, and the server is configured to forward each of the encoded data to a receiving end device.

In a fifth aspect, a video transmission device is provided, the device comprising:

A receiving module, configured to receive first encoded data and second encoded data of the target video, where the resolutions corresponding to the first encoded data and the second encoded data are different;

a decoding module, configured to respectively decode the first encoded data and the second encoded data to obtain first decoded data corresponding to the first encoded data and second decoded data corresponding to the second encoded data, The resolution of the first decoded data is greater than the resolution of the second decoded data;

A processing module, configured to process the second decoded data according to the first decoded data, to obtain restored frames with the same resolution as the first decoded data;

The processing module is further configured to combine the first decoded data and the restored frame to obtain video data of the target video.

In a first possible implementation manner of the fifth aspect, the processing module is specifically configured to, according to the video frame of the first decoded data, process the The video frame is processed to obtain the restored frame.

Based on the foregoing first possible implementation of the fifth aspect, in a second possible implementation of the fifth aspect, the processing module is specifically configured to convert the first video frame of the second decoded data, and At least one video frame whose frame number is continuous with the first video frame is input to the AI super-resolution model to obtain a restored frame corresponding to the first video frame.

In a sixth aspect, a video transmission system is provided, and the video transmission system includes: a sending end device and a receiving end device;

The sending end device is configured to execute the video transmission method according to any one of the second aspect;

The receiver device is configured to execute the video transmission method according to any one of the third aspect.

In a seventh aspect, an electronic device is provided, including: a processor, the processor is configured to run a computer program stored in a memory, so as to implement the video transmission method according to any one of the second aspect or the third aspect.

In an eighth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the second aspect or the third aspect is implemented. The video transmission method described in the item.

According to the ninth aspect, there is provided a chip system, the chip system includes a memory and a processor, and the processor executes the computer program stored in the memory, so as to implement any one of the second aspect or the third aspect. video transmission method.

It can be understood that, the beneficial effects of the above-mentioned second aspect to the ninth aspect can refer to the related description of the above-mentioned first aspect, which will not be repeated here.

Description of drawings

FIG. 1 is a system architecture diagram of a system framework of a video transmission system provided in an embodiment of the present application;

FIG. 2 is a structural block diagram of transmitting video data between a sending end device and a receiving end device provided by an embodiment of the present application;

FIG. 3 is a schematic flowchart of a video transmission method provided by an embodiment of the present application;

FIG. 4A is a schematic diagram of selecting a video frame for encoding according to video data provided by an embodiment of the present application;

FIG. 4B is another schematic diagram of selecting video frames for encoding according to video data provided by the embodiment of the present application;

FIG. 4C is another schematic diagram of selecting video frames for encoding according to video data provided by the embodiment of the present application;

FIG. 5A is a schematic diagram of grouping video frames in video data according to an embodiment of the present application;

FIG. 5B is another schematic diagram of grouping video frames in video data provided by the embodiment of the present application;

FIG. 5C is another schematic diagram of grouping video frames in video data provided by the embodiment of the present application;

FIG. 6 is a schematic diagram of decoding encoded data provided by an embodiment of the present application;

FIG. 7 is a schematic flow chart of generating a restored frame through an AI super-resolution model provided by an embodiment of the present application;

FIG. 8 is a framework diagram of an AI super-resolution model provided by an embodiment of the present application;

FIG. 9 is a schematic flowchart of another video transmission method provided by an embodiment of the present application;

FIG. 10 is another schematic diagram of grouping video frames in video data provided by the embodiment of the present application;

FIG. 11 is a structural frame of a video transmission device provided in an embodiment of the present application;

FIG. 12 is a structural frame of another video transmission device provided by the embodiment of the present application;

FIG. 13 is a structural frame of another video transmission device provided by the embodiment of the present application;

FIG. 14 is a schematic structural diagram of a terminal device provided in an embodiment of the present application.

Detailed ways

In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known video compression methods, video compression standards, video transmission methods, and electronic devices are omitted so as not to obscure the description of the present application with unnecessary detail.

The terms used in the following examples are for the purpose of describing particular examples only, and are not intended to limit the application. As used in the specification and appended claims of this application, the singular expressions "a", "the", "above" and "the" are intended to also include such terms as "one or more". expressions, unless the context clearly indicates otherwise.

First, the system framework of the video transmission system involved in the embodiment of the present application is introduced. Referring to FIG. 1 , the system framework of the video transmission system shown in FIG. 1 includes: a sending end device 110 , a receiving end device 120 and a server 130 .

Wherein, the server 130 may respectively establish a communication connection with the sending end device 110 and the receiving end device 120 , and the sending end device 110 may also establish a communication connection with the receiving end device 120 . Correspondingly, in the process of transmitting video data, the sending end device 110 may send video data to the receiving end device 120, or may send video data to the server 130, and then forward the video data to the receiving end device 120 through the server 130. This application The embodiment does not limit the manner in which the sending end device 110 sends video data.

The process of transmitting the video data of the target video will be introduced below by taking the transmission of the video data of the target video by the sending end device 110 to the receiving end device 120 as an example.

Referring to FIG. 2 , FIG. 2 shows a structural block diagram of video data transmission between a sender device and a receiver device. As shown in FIG. 2 , the sender device 110 may include: a data collection module 1101 and an encoding module 1102 .

Wherein, the data collection module 1101 is connected with the encoding module 1102 . The data collection module 1101 may be a camera of the sending end device 110, and the encoding module 1102 may include: an encoder.

Before transmitting the video data of the target video, the sending end device 110 can first collect the first video data of the target video through the data acquisition module 1101, and then down-sample the first video data to obtain the second video data, wherein the first video The resolution of the data is higher than that of the second video data. Afterwards, the encoder in the encoding module 1102 can encode part of the video frames in the first video data and part of the video frames in the second video data in parallel in a dual-threaded manner, to obtain the second video frame corresponding to the first video data. Encoded data, and second encoded data corresponding to the second video data, so that the first encoded data and the second encoded data can be sent to the receiving end device 120 or the server 130 .

The above is to encode and compress the video data of the target video obtained in real-time shooting, and the video data of the pre-stored target video can also be included in the sending end device 110, and the video data of the pre-stored target video can also be compressed by the sending end device 110 first. Compression is performed, and then the first encoded data and the second encoded data are sent to the receiving end device 120 or the server 130 .

Correspondingly, referring to FIG. 2 , the sending end device 110 may further include: a storage module 1103 , and the storage module 1103 may include pre-stored video data of the target video.

In the process of encoding the pre-stored video data of the target video by the sending-end device 110, the sending-end device 110 may first process the video data of the target video stored in the storage module 1103 to obtain multiple high-resolution continuous video frames, and then group multiple consecutive video frames according to preset rules to obtain two groups of video frames. Then one group of video frames can be down-sampled to obtain low-resolution video frames, so that a group of high-resolution video frames and a group of low-resolution video frames can be obtained, and then through the encoder of the encoding module 1102, respectively Two sets of video frames with different resolutions are encoded to obtain the first encoded data and the second encoded data, so that the first encoded data and the second encoded data can be sent to the receiving end device 120 or the server 130 .

Referring to FIG. 2 , the receiver device 120 may include: a decoding module 1201 , a combining module 1202 , a playing module 1203 and a storage module 1204 .

Wherein, the decoding module 1201 is connected to the synthesis module 1202 and the storage module 1204 respectively, and the synthesis module 1202 is also connected to the playback module 1203 . Moreover, the decoding module 1201 may include: a decoder.

After receiving the first encoded data and the second encoded data corresponding to different resolutions, the receiving end device 120 may use the decoder of the decoding module 1201 to decode the first encoded data and the second encoded data in parallel in a dual-threaded manner, The first decoded data and the second decoded data are obtained, that is, two groups of video frames. The synthesis module 1202 can restore a group of low-resolution video frames according to a pre-set artificial intelligence (AI) super-resolution model based on a group of high-resolution video frames to obtain restored frames. Afterwards, the synthesis module 1202 can combine a group of high-resolution video frames and each restored frame to obtain synthesized video data. Finally, the playing module 1203 can play the synthesized video data.

After the decoding module 1201 decodes and obtains two groups of video frames, the storage module 1204 may store the first decoded data and the second decoded data respectively composed of the two groups of video frames. Further, the receiver device 120 may respectively play the first decoded data and the second decoded data.

It should be noted that FIG. 2 shows a process in which the sending end device 110 may send the first encoded data and the second encoded data to the receiving end device 120 in a point-to-point transmission manner. However, in practical applications, the sending end device 110 may first send the first coded data and the second coded data to the server 130 . Afterwards, the server 130 may forward the received first encoded data and second encoded data to the receiving end device 120 , and the embodiment of the present application does not limit the manner of sending the first encoded data and the second encoded data to the receiving end device 120 .

Further, in the video transmission system provided in the embodiment of the present application, the sending device 110 can transmit the currently collected video data in real time. For example, the video transmission system may be applied in a video call scenario, a teleconference scenario, or a network live broadcast scenario.

Of course, in the video transmission system provided by the embodiment of the present application, the sending end device 110 can also transmit pre-stored video data, and the embodiment of the present application does not limit the application timing and application scenarios of the video transmission system.

In addition, the above description is based on the video data of the target video including two video data with different resolutions as an example. In practical applications, the sending device 110 can obtain video data corresponding to multiple resolutions of the target video. The embodiment of the application does not limit the number of video data corresponding to the target video.

Moreover, the sending end device 110 may also down-sample the video data of the target video to obtain multiple sets of video frames corresponding to multiple resolutions. The embodiment of the present application does not limit the multiple resolutions obtained by down-sampling the sending end device 110. There is also no limitation on the number of groups of video frames obtained through encoding and compression.

For the sake of simplicity, the coded data corresponding to two resolutions obtained by encoding and compressing by the sending device 110 is used as an example for illustration, that is, the coded data sent by the sending device 110 to the receiving device 120 includes the first coded data and the second coded data. coded data as an example.

Fig. 3 is a schematic flowchart of a video transmission method provided by an embodiment of the present application. As an example but not a limitation, the method can be applied to the above-mentioned sending end device and receiving end device. See Fig. 3 , the method includes:

Step 301, the sending end device acquires video data of a target video.

The sending end device can obtain video data in various ways. Specifically, the sending end device can obtain the video data of the target video through real-time collection, or obtain the pre-stored video data of the target video from the preset storage space. The embodiment of the present application does not limit the manner of acquiring the video data of the target video.

The sending device can use any of the following methods to obtain the video data of the target video, see the following method 1 and method 2:

Method 1: The sending end device collects video data of the target video.

During the video call, remote conference or live video broadcast between the sending device and the receiving device, the sending device can collect the video data of the target video in real time through the preset camera. Moreover, in order to facilitate encoding and compression of video data in subsequent steps, the sending end device may obtain video data of multiple resolutions for the target video at the same time according to the adjusted application programming interface (application programming interface, API).

For example, during a video call, the sending device can collect images captured by the camera in real time, and simultaneously output video data of two resolutions, such as the first video data corresponding to high resolution, and the second video data corresponding to low resolution. video data. Wherein, the second video data is obtained after down-sampling the first video data.

It should be noted that the camera used to collect the video data of the target video may be a self-contained camera of the sending device, or an external camera connected to the sending device, which is not limited in this embodiment of the present application. For example, the camera can be a built-in camera of the mobile phone, or an external camera connected to the computer.

Method 2: The sending end device acquires the video data of the target video stored in advance.

The sending end device can not only send the video data of the target video collected in real time to the receiving end device, but also send the pre-stored video data of the target video to the receiving end device. If the sending device needs to send the pre-stored video data of the target video to the receiving device, the sending device may obtain the video data of the target video from the preset storage space.

For example, the sending end device can detect the operation triggered by the user, determine the storage path of the video data of the target video used for transmission according to the operation triggered by the user, and then obtain the video of the target video from the corresponding storage space according to the storage path data.

It should be noted that, in practical applications, the storage space for the sending device to obtain video data may be the storage space of the sending device itself, or an external storage device connected to the sending device, or an external storage device connected to the sending device. The server connected to the sending end device is the cloud storage space, and the embodiment of the present application does not limit the storage space.

Step 302: The sending end device encodes and compresses the acquired video data of the target video to obtain first encoded data and second encoded data.

Wherein, the first encoded data is encoded and compressed high-resolution video data, and the second encoded data is encoded and compressed low-resolution video data.

In step 301, the sending end device can acquire the video data of the target video in different ways. encoding and compressing to obtain the first encoded data and the second encoded data.

Similar to step 301, the sending device can also use any of the following methods to compress the acquired video data of the target video, see the following method 1 and method 2, wherein the method 1 of step 302 and the method 1 of step 301 Correspondingly, the second manner of step 302 corresponds to the second manner of step 301 .

Mode 1: The sending end device encodes some video frames in the first video data and the second video data according to preset rules to obtain the first encoded data and the second encoded data.

After the sending end device acquires the first video data and the second video data of the target video through the camera, it can respectively encode part of the video frames in the first video data and the second video data through the preset encoder, so that First encoded data generated from the first video data and second encoded data generated from the second video data are obtained.

In the process of encoding some video frames in the first video data and the second video data, the sending end device can select according to preset rules according to the frame numbers of the video frames used to indicate the order of each video frame in the first video data. Part of the video frames of the first video data is obtained to obtain a group of video frames, and then the selected group of video frames is encoded by an encoder to obtain the first encoded data.

The sending end device can select some video frames in the second video data to obtain another set of video frames, and then the encoder can also encode another set of video frames in a manner similar to the above encoding process to obtain the second encoding data.

For example, referring to Fig. 4A, Fig. 4B and Fig. 4C, Fig. 4A, Fig. 4B and Fig. 4C all show video frames of the first video data and the second video data, the first video data and the second video data all include 10 frames of video frames, and the resolution of the video frames of the first video data is higher than that of the video frames of the second video data. In the process of the sending end device selecting video frames through the encoder, referring to FIG. 4A, the sending end device can select the first frame, the third frame, the fifth frame, the seventh frame and the ninth frame in the first video data, and Select the 2nd frame, the 4th frame, the 6th frame, the 8th frame and the 10th frame in the second video data; or, referring to FIG. frame, the 7th frame and the 10th frame, and select the 2nd frame, the 3rd frame, the 5th frame, the 6th frame, the 8th frame and the 9th frame in the second video data; or, referring to Fig. 4C, the sending end The device may select the first frame, the fifth frame and the ninth frame in the first video data, and select the second frame, the third frame, the fourth frame, the sixth frame, the seventh frame, and the second frame in the second video data. Frame 8 and Frame 10. Afterwards, the sending end device can encode the video frames selected from the first video data through the encoder to obtain the first encoded data, and simultaneously use the encoder to encode the video frames selected from the second video data respectively to obtain the first encoded data. Two encoded data.

It should be noted that the sending end device may also select video frames in other ways according to preset rules, and this embodiment of the present application does not limit the way of selecting video frames.

Method 2: The sending end device down-samples some video frames in the video data of the acquired target video according to preset rules to obtain two sets of video frames with different resolutions, and then encodes the two sets of video frames respectively to obtain the second set of video frames. A coded data and a second coded data.

After the sending end device obtains the video data of the pre-stored target video from the storage space, it can down-sample some video frames in the video data of the pre-stored target video to obtain two sets of video frames with different resolutions , so that the two groups of video frames can be compressed by a preset encoder to obtain the first encoded data and the second encoded data.

Specifically, the sending end device may first group each video frame according to a preset rule in combination with the video frame number of each video frame in the pre-stored video data, so as to obtain two groups of video frames with the same resolution. Afterwards, the sending device can down-sample one of the video frames according to the preset rules to obtain a group of low-resolution video frames. Combined with a group of non-down-sampled video frames, two groups of videos with different resolutions can be obtained. frame.

Afterwards, the sending end device may encode and compress the two groups of video frames through an encoder in a manner similar to the first manner, to obtain the first encoded data and the second encoded data.

It should be noted that, among the two groups of video frames acquired in method 1 and method 2, the resolution of each video frame in each group of video frames is the same, and the resolution of one group of video frames is greater than the resolution of the other group of video frames . However, the frame number of any video frame in one group of video frames is different from the frame number of any video frame in another group of encoded data. Moreover, each group of video frames may include a plurality of video frames with intermittent frame numbers.

Moreover, the frame numbers of each video frame in a group of high-resolution video frames are discontinuous, and the frame numbers of each video frame in a group of low-resolution video frames may be continuous or discontinuous. In order to improve the compression rate of video data and reduce the storage space and network bandwidth resources occupied by compressed data, in a group of high-resolution video frames, the difference between the frame numbers of every two adjacent video frames is m, Among them, m is a positive integer greater than 1. A group of low-resolution video frames may include multiple groups of video frames with continuous frame numbers. The number of video frames included in each group of video frames with continuous frame numbers is n, where n is a positive integer greater than or equal to 1. For example, n may be greater than or equal to 1 and less than or equal to 3. Wherein, two adjacent video frames in each group of video frames means that no other video frames are included between the two video frames in the group of video frames. For example, if a group of video frames includes video frames with frame numbers 1, 3 and 5, then the two video frames with frame number 1 and frame number 3 are adjacent, and the two video frames with frame number 3 and frame number 5 are adjacent to each other. The video frames are adjacent.

In addition, each video frame corresponding to the first encoded data is complementary to each video frame corresponding to the second encoded data. That is, after combining each video frame corresponding to the first coded data and each video frame corresponding to the second coded data, each video frame with consecutive video frame frame numbers can be obtained by combining, and each consecutive video frame frame number One-to-one correspondence with the video frame number of the target video.

For example, referring to FIG. 5A, FIG. 5B and FIG. 5C, FIG. 5A, FIG. 5B and FIG. 5C show video frames of pre-stored video data, and the pre-stored video data includes 10 frames of video frames. The sending end device can group the 10 video frames according to preset rules, see Figure 5A, for example, the first frame, the third frame, the fifth frame, the seventh frame and the ninth frame can be used as the first group of video frames, And the 2nd frame, the 4th frame, the 6th frame, the 8th frame and the 10th frame are used as the second group of video frames; or, referring to Fig. 5B, the sending end device can use the 1st frame, the 4th frame, the 7th frame and the 10th frame as the first group of video frames, and the 2nd frame, the 3rd frame, the 5th frame, the 6th frame, the 8th frame and the 9th frame as the second group of video frames; or, referring to Fig. 5C, sending The end device can regard the 1st, 5th and 9th frames as the first group of video frames, and the 2nd, 3rd, 4th, 6th, 7th, 8th and 10th frames frame as the second set of video frames. Afterwards, the sending end device may perform down-sampling on the second group of video frames to obtain a group of low-resolution video frames. Finally, the sending end device may encode the first group of video frames through the encoder to obtain the first encoded data, and use the encoder to encode the down-sampled second group of video frames to obtain the second encoded data.

It should be noted that in practical applications, the sending device in the first method of step 301 can also only collect high-resolution video data, and then encode and compress it through the second method of step 302. The way of encoding and compressing video data is not limited, nor is the way of encoding and compressing video data.

Step 303, the sending end device sends the first encoded data and the second encoded data to the receiving end device.

After obtaining the first coded data and the second coded data, the sending device can send the first coded data and the second coded data to the receiving device in a dual-channel manner while occupying relatively low network bandwidth resources.

Step 304, the receiver device receives the first coded data and the second coded data.

Step 305, the receiving end device decodes the first encoded data and the second encoded data respectively to obtain the first decoded data and the second decoded data.

After receiving the first coded data and the second coded data, the receiver device can decode the first coded data through a preset decoder to obtain the first decoded data corresponding to the first coded data, and use the decoder to decode the first coded data The second encoded data is decoded to obtain second decoded data corresponding to the second encoded data, that is, to obtain video frames respectively corresponding to the first encoded data and the second encoded data.

At the same time, the receiving end device can store the first decoded data and the second decoded data, so that the storage space of the receiving end device can be saved. Correspondingly, if the receiving-end device needs to play the high-resolution video data corresponding to the first decoded data and the second decoded data, the receiving-end device can perform steps 306 and 307 to play the video data according to the first decoded data and the second decoded data .

It should be noted that, during the process of receiving encoded data, the receiving end device may decode the received encoded data in real time to obtain decoded video frames, and then compose decoded data according to multiple decoded video frames. For example, referring to FIG. 6, after receiving part of the first coded data and part of the second coded data, the receiving device can decode the received coded data, so that the first frame and the first frame can be obtained according to the decoding of part of the first coded data. 3 frames, and decode according to part of the second encoded data to obtain the second frame and the fourth frame, and at the same time, the receiving end device can continue to receive the remaining first encoded data and second encoded data sent by the sending end device.

Step 306, the receiving end device synthesizes according to the first decoded data and the second decoded data, to obtain synthesized video data.

After the receiver device decodes the first decoded data and the second decoded data respectively corresponding to the first encoded data and the second encoded data, it can use the preset AI super resolution according to the high-resolution video frame included in the first decoded data. The model restores the video frame included in the second decoded data to obtain a restored frame with high resolution. Afterwards, the receiver device can combine the high-resolution video frames included in the first decoded data and the high-resolution restoration frames to obtain video data of the target video synthesized from multiple high-resolution continuous video frames.

Specifically, referring to FIG. 7 , FIG. 7 shows a schematic flowchart of generating a high-resolution restored frame by the receiving device through the AI super-resolution model, and the AI super-resolution model includes multiple neural network convolution layers. If the receiving end device needs to recover the first video frame included in the second decoded data, the receiving end device can, according to the frame number of the video frame of the first video frame, select from the multiple high-resolution video frames included in the first decoded data , combining the video frame frame numbers of each high-resolution video frame, selecting high-resolution video frames that are continuous with the frame number of the first video frame. Afterwards, the receiver device can input the selected first video frame and the corresponding high-resolution video frame into the pre-set AI super-resolution model, and combine the corresponding high-resolution video frame with the AI super-resolution model to process the first video frame. Restoring to obtain a restored frame with high resolution corresponding to the first video frame.

Wherein, the first video frame may be any video frame in the second decoded data. The high-resolution video frame whose frame number is continuous with the video frame of the first video frame can be a video frame with a continuous frame number before the low-resolution video frame, or a frame number after the low-resolution video frame Consecutive video frames. For example, if the video frame number of the first video frame is 2, then the video frame number of consecutive video frames may be 1 or 3, which is not limited in this embodiment of the present application.

After recovering each low-resolution video frame corresponding to the second decoded data, the receiver device can use the video frame number of each high-resolution video frame corresponding to the first decoded data, and the low-resolution video frame corresponding to each restored frame The video frame number of the high-resolution video frame is sorted and combined for each high-resolution video frame and each restored frame to obtain high-resolution synthesized video data.

Further, referring to Fig. 8, Fig. 8 shows the framework diagram of the AI super-resolution model, the AI super-resolution model can obtain a high-resolution parameter of 1*540*960*6 through the first input terminal (input_1) Video frame, where 1 represents the number of video frames, 540*960 represents the resolution of the video frame, and 6 represents the number of channels for the AI super-resolution model to obtain the video frame. The meaning of the parameters of each video frame in the following is the same as that of the high-resolution video The meanings of the parameters of the frame are similar, and will not be repeated here. Similarly, the AI super-resolution model can obtain a low-resolution video frame with a parameter of 1*270*480*6 through the second input terminal (input_2), and the AI super-resolution model can first perform spatial transformation on the high-resolution video frame Depth operation (SpaceToDepth), convert the video frame whose parameters are 1*270*480*24, and then perform the association operation (Concatenation) on the converted high-resolution video frame and low-resolution video frame, and convert the converted high-resolution video frame The high-resolution video frame and the low-resolution video frame are spliced, and the dimensions are superimposed to obtain a video frame with associated parameters of 1*270*480*30.

After that, the AI super-resolution model performs multiple convolutions (Conv2D) on the associated video frames and corrects them through the activation function (Relu), then superimposes (Add) the convolved video frames and the associated video frames, and then Perform a depth-to-space operation (DepthToSpace) on the superimposed video frame, and finally output (Identity) to obtain a restored video frame with a parameter of 1*540*960*6.

Wherein, when each video frame is convoluted by the convolution layer, the parameters of the convolution kernel in each convolution layer are different. Referring to Figure 8, when performing the first convolution on a video frame with a parameter of 1*270*480*30, the parameter of the convolution kernel (filter) is 6*3*3*30, and the parameter of the error (bias) is 6 , to obtain a video frame with a parameter of 1*270*480*6; after that, the video frame with a parameter of 1*270*480*6 can be convolved again, and the parameter of the convolution kernel is 12*3*3*6 , the error parameter is 12, and the video frame with the parameter of 1*270*480*12 is obtained; finally, the video frame with the parameter of 1*270*480*12 is convolved again, and the parameter of the convolution kernel is 24* 1*1*12, the error parameter is 24, and the video frame with the parameter of 1*270*480*24 is obtained.

In addition, the AI super-resolution model can also convolute the video frame with a parameter of 1*270*480*30 (that is, the associated video frame) in another way. The parameter of the convolution kernel is 24*1* 1*30, the error parameter is 24, and another video frame with a parameter of 1*270*480*24 is obtained, so that two video frames with a parameter of 1*270*480*24 can be superimposed to obtain the superimposed video frame.

Moreover, the above-mentioned AI super-resolution model can include 4 convolutional layers, and the number of channels of the convolution kernel is very small, and the amount of calculation required is very low. When the receiving end device is used as a mobile phone, tablet or other portable mobile device, it can satisfy The AI super-resolution model restores the conditions of the video frame, which can be restored to obtain the restored frame.

It should be noted that each pixel in the above video frame is expressed in YUV format. Correspondingly, before inputting video frames to the AI super-resolution model, the data in YUV format of each video frame can be converted first to obtain data in 6-channel YUV format. Wherein, the first 4 channels may be Y data representing brightness, and the latter 2 channels may be U data and V data representing color and saturation respectively.

In addition, the above is only an example of restoring a low-resolution video frame from a high-resolution video frame. In practical applications, the receiving device can input multiple high-resolution video frames to the AI super-resolution model to restore a Low resolution video frame. For example, if the video frame number of the low-resolution video frame to be restored is 2, then the video frame number of the high-resolution video frame input to the AI super-resolution model can be 1 and 3, which is not limited in the embodiment of the present application .

In addition, if the video frames of the second decoded data include video frames with continuous frame numbers, in the process of restoring the video frames with continuous frame numbers, the receiver device can use the video frames included in the first decoded data to The adjacent video frames of the video frame can be restored, and the remaining video frames in the continuous video frames can also be restored through the adjacent restored frames. The process of restoring continuous video frames is similar to the above-mentioned process of restoring low-resolution video frames, and will not be repeated here.

For example, the first decoded data includes a video frame whose frame number is 1, and the second decoded data includes 3 consecutive video frames whose frame numbers are 2, 3, and 4. Each video frame of 4 is input into the AI super-resolution model, and the AI super-resolution model can process the video frames with frame numbers 2, 3 and 4, and obtain the restoration frames corresponding to the video frames with frame numbers 2, 3 and 4 respectively .

Alternatively, the receiver device can input the video frames with frame number 1 and 2 into the AI super-resolution model, and the AI super-resolution model can process the video frame with frame number 2 according to the video frame with frame number 1 to obtain the frame The restoration frame corresponding to the video frame with the frame number 2, and then input the video frame with the frame number 3, and process the video frame with the frame number 3 through the restoration frame corresponding to the video frame with the frame number 2 to obtain the frame number It is the restoration frame corresponding to the video frame of 3. The receiving end device may continue to restore the video frame with the frame number 4 in a manner similar to processing the video frame with the frame number 3, so as to complete the restoration process for the video frames with consecutive frame numbers.

Step 307, the receiver device plays the synthesized video data.

After the receiving end device obtains the synthesized video data according to the first decoded data and the second decoded data, it can play the synthesized video data, so that high-resolution images can be obtained by occupying less network bandwidth and less storage space. rate video data.

In practical applications, the receiver device can not only play the video data synthesized from the first decoded data and the second decoded data, but also play the stored first decoded data and the second decoded data separately. There is no limit to this.

In addition, referring to FIG. 9 , the sending end device may also send the first encoded data and the second encoded data to the server, and the server forwards the first encoded data and the second encoded data to the receiving end device.

Further, the sending end device may not encode and compress the video data of the target video, but send the video data of the high-resolution target video to the server, and then encode and compress the video data of the target video through the server to obtain the first coded data and the second coded data, the server then sends the coded first coded data and second coded data to the receiving end device. The embodiment of the present application does not limit the format of the video data sent by the sending end device to the server.

It should be noted that, in the above-mentioned embodiment, the sending end device only sends compressed data corresponding to two different resolutions to the receiving end device, but in practical applications, the sending end device can also obtain three or more sets of Video frames with different resolutions are compressed for each group of video frames, and then the compressed data obtained by each compression is sent to the receiving end device.

For example, referring to FIG. 10 , FIG. 10 shows video frames of pre-stored video data, and the pre-stored video data includes 10 frames of video frames. The sending end device can divide the 10 video frames of video data into 3 groups of video frames according to preset rules, for example, the 1st frame, the 5th frame and the 9th frame can be used as the first group, and the 2nd frame, the The 4th frame, the 6th frame, the 8th frame and the 10th frame are used as the second group, and the 3rd frame and the 7th frame can be used as the third group. Afterwards, the sending device can down-sample the second group of video frames and the third group of video frames respectively to obtain two groups of low-resolution video frames, and the resolution of the third group of video frames is lower than that of the second group of video frames corresponding resolution. Finally, the sending end device can respectively encode the first group of video frames, the second group of downsampled video frames, and the third group of downsampled video frames through the encoder to obtain the first encoded data, the second encoded data and third encoded data.

Correspondingly, the receiver device may receive multiple coded data sent by the sender device, and decode the multiple coded data to obtain multiple sets of video frames with different resolutions. Afterwards, the pre-set AI super-resolution model can be used to restore video frames of different resolutions based on video frames of different resolutions to obtain restored frames, thereby improving the accuracy of restored restored frames.

To sum up, in the video transmission method provided by the embodiment of the present application, the sending device determines two sets of video frames according to the video data of the target video, and encodes and compresses each set of video frames to obtain the encoded data corresponding to each set of video frames. Afterwards, each encoded data is sent to the receiving end device, and the encoded data of different resolutions can be transmitted by encoding, which can increase the compression rate by 30%-40%, thereby effectively improving the compression rate of the video data of the target video and reducing the time spent on transmitting video data. Occupied network bandwidth resources, avoiding the waste of network bandwidth resources, and reducing the cost of transmitting video data.

Moreover, the receiving end device decodes the first encoded data and the second encoded data to obtain the first decoded data and the second decoded data, and then synthesizes the first decoded data and the second decoded data to obtain the synthesized video data, The receiving end device only stores the first encoded data and the second encoded data which occupy less storage space, and can realize playing the video data of the target video, without storing the video data of the high-resolution target video, which can reduce the occupied storage space, Improve storage space utilization.

Similarly, there is no need to store video data of multiple resolutions of the target video in the server, which can reduce the storage space occupied by the video data of the target video in the server, improve the utilization rate of the storage space of the server, and reduce the maintenance cost of the server.

In addition, the sending device obtains the video data of the target video in different ways, and encodes the video data of the target video in a manner corresponding to the acquisition method, which can improve the flexibility of obtaining video data and improve the accuracy of the target video. Video data is encoded with flexibility.

In addition, the process of encoding to obtain the first coded data and the second coded data, and the process of decoding to obtain the first decoded data and the second decoded data are independent of the standard codec stage, and can be compatible with any standard codec technology, improving the transmission efficiency. Compatibility of video data.

Furthermore, the receiver device synthesizes the first decoded data and the second decoded data that can complement the video frame through the preset AI super-resolution model, which can improve the accuracy of the restored video frame, thereby improving the synthesized video. Data playback effect.

Moreover, the receiver device uses the AI super-resolution model to process the low-resolution video frames according to the high-resolution video frames adjacent to the frame number, and utilizes the high-frequency spatial information of the high-resolution video frames, which can reduce the super-resolution network The complexity of the AI super-resolution model can be reduced, and the AI super-resolution model can be run through a portable terminal, which improves the versatility of the AI super-resolution model.

In addition, in the process of processing video frames through the AI super-resolution model, the receiver device can obtain information about missing frames based on low-resolution video frames, which not only saves network bandwidth resources, but also reduces the complexity of processing video frames and improves to improve the accuracy of the restored frame.

It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

Corresponding to the video transmission method described in the above embodiments, FIG. 11 is a structural block diagram of a video transmission device provided in the embodiments of the present application. For ease of description, only parts related to the embodiments of the present application are shown.

Referring to Figure 11, the device includes:

The encoding module 1101 is configured to determine two groups of video frames according to the video data of the target video, the resolution of each video frame in each group of video frames is the same, and the resolution of one group of video frames is greater than the resolution of another group of video frames, The frame number of any video frame in one group of video frames is different from the frame number of any video frame in another group of video frames, and each group of video frames includes a plurality of video frames with intermittent frame numbers;

The encoding module 1101 is further configured to encode each group of video frames respectively to obtain the corresponding encoded data of each group of video frames;

A sending module 1102, configured to send the coded data.

Optionally, the video data of the target video includes: first video data and second video data;

The encoding module 1101 is specifically configured to down-sample the first video data to obtain the second video data, and the resolution of each video frame in the first video data is higher than the resolution of each video frame in the second video data rate; respectively select a plurality of video frames from the first video data and the second video data to obtain the two groups of video frames.

Optionally, each video frame in the video data of the target video has the same resolution;

The encoding module 1101 is specifically used to select a part of video frames from the video data of the target video to obtain a group of video frames; down-sample another part of the video frames in the video data of the target video to obtain another group of video frames .

Optionally, in the group of video frames with a higher resolution of the two groups of video frames, the difference between the frame numbers of every two adjacent video frames is m, where m is a positive integer greater than 1.

Optionally, in the group of video frames with smaller resolutions of the two groups of video frames, multiple groups of video frames with continuous frame numbers are included, and the number of video frames included in each group of video frames with continuous frame numbers is n, where n is a positive integer greater than or equal to 1.

Optionally, the frame numbers of the video frames obtained after combining the two groups of video frames are continuous.

Optionally, referring to Figure 12, the device also includes:

Obtaining module 1103, for obtaining the video data of this target video from storage space;

Alternatively, the obtaining module 1103 is configured to collect video data of the target video in real time.

Optionally, the sending module 1102 is specifically configured to send the coded data to the receiving end device;

Alternatively, the sending module is specifically configured to send the coded data to a server, and the server is used to forward the coded data to the receiving end device.

FIG. 13 is a structural block diagram of another video transmission device provided by the embodiment of the present application. For convenience of description, only parts related to the embodiment of the present application are shown.

Referring to Figure 13, the device includes:

The receiving module 1301 is configured to receive first encoded data and second encoded data of the target video, where the resolutions corresponding to the first encoded data and the second encoded data are different;

A decoding module 1302, configured to decode the first encoded data and the second encoded data respectively, to obtain first decoded data corresponding to the first encoded data and second decoded data corresponding to the second encoded data, the first The resolution of the decoded data is greater than the resolution of the second decoded data;

A processing module 1303, configured to process the second decoded data according to the first decoded data, to obtain restored frames with the same resolution as the first decoded data;

The processing module 1303 is further configured to combine the first decoded data and the restored frame to obtain video data of the target video.

Optionally, the processing module 1303 is specifically configured to process the video frame of the second decoded data according to the video frame of the first decoded data through a preset AI super-resolution model to obtain the restored frame.

Optionally, the processing module 1303 is specifically configured to input the first video frame of the second decoded data and at least one video frame whose frame number is continuous with the first video frame into the AI super-resolution model to obtain the The restoration frame corresponding to the first video frame.

To sum up, in the video transmission device provided by the embodiment of the present application, the sending end device encodes and compresses the video data of the target video, obtains and sends the high-resolution first encoded data and the low-resolution second encoded data to the receiving end device. Encoded data, by compressing and transmitting the first encoded data and the second encoded data of different resolutions, the compression rate can be increased by 30%-40%, so that the compression rate of the video data of the target video can be effectively improved, and the time for transmitting video data can be reduced. Occupied network bandwidth resources, avoiding the waste of network bandwidth resources, and reducing the cost of transmitting video data.

The following takes electronic equipment as an example to introduce the sending end equipment and the receiving end equipment involved in the embodiment of the present application. Please refer to FIG. 14 , which is a schematic structural diagram of an electronic device provided in the embodiment of the present application.

The electronic device may include a processor 1410, an external memory interface 1420, an internal memory 1421, a universal serial bus (universal serial bus, USB) interface 1430, a charging management module 1440, a power management module 1441, a battery 1442, an antenna 1, an antenna 2, Mobile communication module 1450, wireless communication module 1460, audio module 1470, speaker 1470A, receiver 1470B, microphone 1470C, earphone interface 1470D, sensor module 1480, button 1490, motor 1491, indicator 1492, camera 1493, display screen 1494, and user An identification module (subscriber identification module, SIM) card interface 1495 and the like. The sensor module 1480 may include a pressure sensor 1480A, a gyroscope sensor 1480B, an air pressure sensor 1480C, a magnetic sensor 1480D, an acceleration sensor 1480E, a distance sensor 1480F, a proximity light sensor 1480G, a fingerprint sensor 1480H, a temperature sensor 1480J, a touch sensor 1480K, and ambient light Sensor 1480L, bone conduction sensor 1480M, etc.

It can be understood that, the structure shown in the embodiment of the present invention does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown in the illustrations, or combine certain components, or separate certain components, or arrange different components. The illustrated components can be realized in hardware, software or a combination of software and hardware.

The processor 1410 may include one or more processing units, for example: the processor 1410 may include an application processor (application processor, AP), a modem processor, a graphics processing unit (graphics processing unit, GPU), an image signal processor ( image signal processor, ISP), controller, memory, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural network processor (neural-network processing unit, NPU), etc. . Wherein, different processing units may be independent devices, or may be integrated in one or more processors.

Wherein, the controller may be the nerve center and command center of the electronic equipment. The controller can generate an operation control signal according to the instruction opcode and timing signal, and complete the control of fetching and executing the instruction.

A memory may also be provided in the processor 1410 for storing instructions and data. In some embodiments, the memory in processor 1410 is a cache memory. The memory may hold instructions or data that the processor 1410 has just used or recycled. If the processor 1410 needs to use the instruction or data again, it can be called directly from the memory. Repeated access is avoided, and the waiting time of the processor 1410 is reduced, thus improving the efficiency of the system.

In some embodiments, processor 1410 may include one or more interfaces. The interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuitsound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver (universal asynchronous receiver) /transmitter, UART) interface, mobile industry processor interface (mobile industry processor interface, MIPI), general-purpose input and output (general-purpose input/output, GPIO) interface, subscriber identity module (subscriber identity module, SIM) interface, and/or A universal serial bus (universal serial bus, USB) interface, etc.

The I2C interface is a bidirectional synchronous serial bus, including a serial data line (serial data line, SDA) and a serial clock line (derail clock line, SCL). In some embodiments, processor 1410 may include multiple sets of I2C buses. The processor 1410 may be respectively coupled to the touch sensor 1480K, the charger, the flashlight, the camera 1493 and the like through different I2C bus interfaces. For example, the processor 1410 may be coupled to the touch sensor 1480K through the I2C interface, so that the processor 1410 and the touch sensor 1480K communicate through the I2C bus interface to realize the touch function of the electronic device.

The UART interface is a universal serial data bus used for asynchronous communication. The bus can be a bidirectional communication bus. It converts the data to be transmitted between serial communication and parallel communication. In some embodiments, a UART interface is generally used to connect the processor 1410 and the wireless communication module 1460 . For example: the processor 1410 communicates with the Bluetooth module in the wireless communication module 1460 through the UART interface to realize the Bluetooth function. In some embodiments, the audio module 1470 can transmit audio signals to the wireless communication module 1460 through the UART interface, so as to realize the function of playing music through the Bluetooth headset.

The MIPI interface can be used to connect the processor 1410 with the display screen 1494, the camera 1493 and other peripheral devices. The MIPI interface includes a camera serial interface (camera serial interface, CSI), a display serial interface (display serial interface, DSI), etc. In some embodiments, the processor 1410 communicates with the camera 1493 through the CSI interface to realize the shooting function of the electronic device. The processor 1410 communicates with the display screen 1494 through the DSI interface to realize the display function of the electronic device.

The GPIO interface can be configured by software. The GPIO interface can be configured as a control signal or as a data signal. In some embodiments, the GPIO interface can be used to connect the processor 1410 with the camera 1493 , the display screen 1494 , the wireless communication module 1460 , the audio module 1470 , the sensor module 1480 and so on. The GPIO interface can also be configured as an I2C interface, I2S interface, UART interface, MIPI interface, etc.

The USB interface 1430 is an interface conforming to the USB standard specification, specifically, it may be a Mini USB interface, a Micro USB interface, a USB Type C interface, and the like. The USB interface 1430 can be used to connect a charger to charge the electronic device, and can also be used to transmit data between the electronic device and peripheral devices. It can also be used to connect headphones and play audio through them. This interface can also be used to connect other electronic devices, such as AR devices.

It can be understood that the interface connection relationship between the modules shown in the embodiment of the present invention is only a schematic illustration, and does not constitute a structural limitation of the electronic device. In other embodiments of the present application, the electronic device may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

The power management module 1441 is used for connecting the battery 1442 , the charging management module 1440 and the processor 1410 . The power management module 1441 receives the input of the battery 1442 and/or the charging management module 1440, and supplies power for the processor 1410, the internal memory 1421, the external memory, the display screen 1494, the camera 1493, and the wireless communication module 1460, etc. The power management module 1441 can also be used to monitor parameters such as battery capacity, battery cycle times, and battery health status (leakage, impedance). In some other embodiments, the power management module 1441 can also be set in the processor 1410 . In some other embodiments, the power management module 1441 and the charging management module 1440 may also be set in the same device.

The wireless communication function of the electronic device can be realized by the antenna 1, the antenna 2, the mobile communication module 1450, the wireless communication module 1460, the modem processor and the baseband processor.

Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in an electronic device can be used to cover a single or multiple communication frequency bands. Different antennas can also be multiplexed to improve the utilization of the antennas. For example: Antenna 1 can be multiplexed as a diversity antenna of a wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

The mobile communication module 1450 can provide wireless communication solutions including 2G/3G/4G/5G applied to electronic devices. The mobile communication module 1450 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA) and the like. The mobile communication module 1450 can receive electromagnetic waves through the antenna 1, filter and amplify the received electromagnetic waves, and send them to the modem processor for demodulation. The mobile communication module 1450 can also amplify the signal modulated by the modem processor, convert it into electromagnetic wave and radiate it through the antenna 1 . In some embodiments, at least part of the functional modules of the mobile communication module 1450 may be set in the processor 1410 . In some embodiments, at least part of the functional modules of the mobile communication module 1450 and at least part of the modules of the processor 1410 may be set in the same device.

A modem processor may include a modulator and a demodulator. Wherein, the modulator is used for modulating the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low frequency baseband signal. Then the demodulator sends the demodulated low-frequency baseband signal to the baseband processor for processing. The low-frequency baseband signal is passed to the application processor after being processed by the baseband processor. The application processor outputs sound signals through audio equipment (not limited to speaker 1470A, receiver 1470B, etc.), or displays images or videos through display screen 1494 . In some embodiments, the modem processor may be a stand-alone device. In some other embodiments, the modem processor may be independent of the processor 1410, and be set in the same device as the mobile communication module 1450 or other functional modules.

The wireless communication module 1460 can provide wireless local area networks (wireless local area networks, WLAN) (such as wireless fidelity (Wi-Fi) network), bluetooth (bluetooth, BT), global navigation satellite system ( Global navigation satellite system (GNSS), frequency modulation (frequency modulation, FM), near field communication (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions. The wireless communication module 1460 may be one or more devices integrating at least one communication processing module. The wireless communication module 1460 receives electromagnetic waves via the antenna 2 , frequency-modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 1410 . The wireless communication module 1460 can also receive the signal to be sent from the processor 1410 , frequency-modulate it, amplify it, and convert it into electromagnetic waves through the antenna 2 for radiation.

In some embodiments, the antenna 1 of the electronic device is coupled to the mobile communication module 1450, and the antenna 2 is coupled to the wireless communication module 1460, so that the electronic device can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (general packet radio service, GPRS), code division multiple access (codedivision multiple access, CDMA), wideband code Wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM , and/or IR technology, etc. The GNSS may include a global positioning system (global positioning system, GPS), a global navigation satellite system (global navigation satellite system, GLONASS), a Beidou satellite navigation system (beidounavigation satellite system, BDS), a quasi-zenith satellite system (quasi- zenith satellite system (QZSS) and/or satellite based augmentation systems (SBAS).

The electronic device realizes the display function through the GPU, the display screen 1494, and the application processor. The GPU is a microprocessor for image processing, connected to the display screen 1494 and the application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. Processor 1410 may include one or more GPUs that execute program instructions to generate or change display information.

The display screen 1494 is used to display images, videos and the like. Display 1494 includes a display panel. The display panel may be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (active-matrix organic light emitting diode). , AMOLED), flexible light-emitting diode (flex light-emitting diode, FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diodes (quantum dot light emitting diodes, QLED), etc. In some embodiments, the electronic device may include 1 or N display screens 1494, where N is a positive integer greater than 1.

The electronic device can realize the shooting function through ISP, camera 1493 , video codec, GPU, display screen 1494 and application processor.

The ISP is used to process the data fed back by the camera 1493 . For example, when taking a picture, open the shutter, the light is transmitted to the photosensitive element of the camera through the lens, and the light signal is converted into an electrical signal, and the photosensitive element of the camera transmits the electrical signal to the ISP for processing, and converts it into an image visible to the naked eye. ISP can also perform algorithm optimization on image noise, brightness, and skin color. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some embodiments, the ISP may be located in the camera 1493.

Camera 1493 is used to capture still images or video. The object generates an optical image through the lens and projects it to the photosensitive element. The photosensitive element may be a charge coupled device (charge coupled device, CCD) or a complementary metal-oxide-semiconductor (complementary metal-oxide-semiconductor, CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. DSP converts digital image signals into standard RGB, YUV and other image signals. In some embodiments, the electronic device may include 1 or N cameras 1493, where N is a positive integer greater than 1.

Digital signal processors are used to process digital signals. In addition to digital image signals, they can also process other digital signals. For example, when an electronic device selects a frequency point, a digital signal processor is used to perform Fourier transform on the frequency point energy, etc.

Video codecs are used to compress or decompress digital video. An electronic device may support one or more video codecs. In this way, the electronic device can play or record videos in various encoding formats, such as: moving picture experts group (moving picture experts group, MPEG) 1, MPEG2, MPEG3, MPEG4 and so on.

The NPU is a neural-network (NN) computing processor. By referring to the structure of biological neural networks, such as the transfer mode between neurons in the human brain, it can quickly process input information and continuously learn by itself. Applications such as intelligent cognition of electronic devices can be realized through NPU, such as: image recognition, face recognition, speech recognition, text understanding, etc.

The external memory interface 1420 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device. The external memory card communicates with the processor 1410 through the external memory interface 1420 to implement a data storage function. Such as saving music, video and other files in the external memory card.

The internal memory 1421 may be used to store computer-executable program codes including instructions. The processor 1410 executes various functional applications and data processing of the electronic device by executing instructions stored in the internal memory 1421 . The internal memory 1421 may include an area for storing programs and an area for storing data. Wherein, the stored program area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.) and the like. The storage data area can store data (such as audio data, phone book, etc.) created during the use of the electronic device. In addition, the internal memory 1421 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, universal flash storage (universal flash storage, UFS) and the like.

The electronic device can implement audio functions through the audio module 1470, the speaker 1470A, the receiver 1470B, the microphone 1470C, the earphone interface 1470D, and the application processor. Such as music playback, recording, etc.

The audio module 1470 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signal. The audio module 1470 may also be used to encode and decode audio signals. In some embodiments, the audio module 1470 may be set in the processor 1410 , or some functional modules of the audio module 1470 may be set in the processor 1410 .

Loudspeaker 1470A, also called "horn", is used to convert audio electrical signals into sound signals. The electronic device can listen to music through speaker 1470A, or listen to hands-free calls.

Receiver 1470B, also called "earpiece", is used to convert audio electrical signals into audio signals. When the electronic device receives a call or a voice message, the receiver 1470B can be placed close to the human ear to hear the voice.

Microphone 1470C, also known as "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can make a sound by approaching the microphone 1470C with a human mouth, and input the sound signal to the microphone 1470C. The electronic device may be provided with at least one microphone 1470C. In other embodiments, the electronic device can be provided with two microphones 1470C, which can also implement a noise reduction function in addition to collecting sound signals. In some other embodiments, the electronic device can also be equipped with three, four or more microphones 1470C to realize the collection of sound signals, noise reduction, identification of sound sources, and realization of directional recording functions, etc.

The earphone interface 1470D is used to connect wired earphones. The earphone interface 1470D may be a USB interface 1430, or a 3.5mm open mobile terminal platform (OMTP) standard interface, or a cellular telecommunications industry association of the USA (CTIA) standard interface.

The pressure sensor 1480A is used to sense the pressure signal and convert the pressure signal into an electrical signal. In some embodiments, pressure sensor 1480A may be located on display screen 1494 . There are many types of pressure sensors 1480A, such as resistive pressure sensors, inductive pressure sensors, and capacitive pressure sensors. A capacitive pressure sensor may be comprised of at least two parallel plates with conductive material. When a force is applied to the pressure sensor 1480A, the capacitance between the electrodes changes. Electronics determine the strength of the pressure based on the change in capacitance. When a touch operation acts on the display screen 1494, the electronic device detects the intensity of the touch operation according to the pressure sensor 1480A. The electronic device may also calculate the touched position according to the detection signal of the pressure sensor 1480A. In some embodiments, touch operations acting on the same touch position but with different touch operation intensities may correspond to different operation instructions. For example: when a touch operation with a touch operation intensity less than the first pressure threshold acts on the short message application icon, an instruction to view short messages is executed. When a touch operation whose intensity is greater than or equal to the first pressure threshold acts on the icon of the short message application, the instruction of creating a new short message is executed.

The acceleration sensor 1480E can detect the acceleration of the electronic device in various directions (generally three axes). When the electronic device is stationary, the magnitude and direction of gravity can be detected. It can also be used to recognize the posture of electronic devices, and can be used in applications such as horizontal and vertical screen switching, pedometers, etc.

Touch sensor 1480K, also known as "touch panel". The touch sensor 1480K can be arranged on the display screen 1494, and the touch sensor 1480K and the display screen 1494 form a touch screen, also called “touch screen”. The touch sensor 1480K is used to detect a touch operation acting on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to touch operations can be provided through the display screen 1494 . In some other embodiments, the touch sensor 1480K may also be disposed on the surface of the electronic device, which is different from the position of the display screen 1494 .

The keys 1490 include a power key, a volume key, and the like. Key 1490 may be a mechanical key. It can also be a touch button. The electronic device can receive key input and generate key signal input related to user settings and function control of the electronic device.

The indicator 1492 can be an indicator light, and can be used to indicate charging status, power change, and can also be used to indicate messages, missed calls, notifications, and the like.

SIM card interface 1495 is used for connecting SIM card. The SIM card can be inserted into the SIM card interface 1495 or pulled out from the SIM card interface 1495 to achieve contact and separation with the electronic device. The electronic device can support 1 or N SIM card interfaces, where N is a positive integer greater than 1. SIM card interface 1495 can support Nano SIM card, Micro SIM card, SIM card and so on. The same SIM card interface 1495 can insert multiple cards at the same time. The types of the multiple cards may be the same or different. The SIM card interface 1495 is also compatible with different types of SIM cards. The SIM card interface 1495 is also compatible with external memory cards. The electronic device interacts with the network through the SIM card to realize functions such as calling and data communication. In some embodiments, the electronic device adopts an eSIM, that is, an embedded SIM card. The eSIM card can be embedded in the electronic device and cannot be separated from the electronic device.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Completion of modules means that the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware It can also be implemented in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the above system, reference may be made to the corresponding process in the foregoing method embodiments, and details will not be repeated here.

In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases, and for parts that are not detailed or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

In the embodiments provided in this application, it should be understood that the disclosed devices and methods may be implemented in other ways. For example, the system embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be Incorporation may either be integrated into another system, or some features may be omitted, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the procedures in the methods of the above embodiments in the present application can be completed by instructing related hardware through computer programs, and the computer programs can be stored in a computer-readable storage medium. The computer program When executed by a processor, the steps in the above-mentioned various method embodiments can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program codes to electronic equipment, recording media, computer memory, read-only memory (ROM, Read-Only Memory), random-access memory (RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media. Such as U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunication signals under legislation and patent practice.

Finally, it should be noted that: the above is only a specific implementation of the application, but the scope of protection of the application is not limited thereto, and any changes or replacements within the technical scope disclosed in the application shall be covered by this application. within the scope of the application. Therefore, the protection scope of the present application should be determined by the protection scope of the claims.

Claims (23)

1. A video transmission method, characterized in that, the method is applied to a video transmission system composed of a sending end device and a receiving end device, and the method comprises: The sending end device determines two groups of video frames according to the video data of the target video, the resolution of each video frame in each group of video frames is the same, and the resolution of one group of video frames is greater than the resolution of the other group of video frames, one group of video frames The frame number of any video frame in the group of video frames is different from the frame number of any video frame in another group of video frames, and each group of video frames includes a plurality of video frames with intermittent frame numbers; The sending end device encodes each group of video frames respectively, to obtain encoded data corresponding to each group of video frames; The sending end device sends first coded data and second coded data respectively corresponding to the two groups of video frames, the resolution corresponding to the first coded data is greater than the resolution corresponding to the second coded data; The receiver device receives the first coded data and the second coded data; Decoding the first encoded data and the second encoded data by the receiving end device respectively, to obtain first decoded data corresponding to the first encoded data and second decoded data corresponding to the second encoded data, The resolution of the first decoded data is greater than the resolution of the second decoded data; The receiving end device processes the second decoded data according to the first decoded data to obtain a restored frame with the same resolution as the first decoded data; The receiver device combines the first decoded data and the restoration frame to obtain video data of the target video. 2. method according to claim 1, is characterized in that, the video data of described target video comprises: first video data and second video data; The sending end device determines two groups of video frames according to the video data of the target video, including: The sending end device down-samples the first video data to obtain the second video data, and the resolution of each video frame in the first video data is higher than that of each video frame in the second video data resolution; The sending device selects a plurality of video frames from the first video data and the second video data to obtain the two groups of video frames. 3. method according to claim 1, is characterized in that, the resolution of each video frame in the video data of described target video is identical; The sending end device determines two groups of video frames according to the video data of the target video, including: The sending end device selects a part of video frames from the video data of the target video to obtain a set of video frames; The sending end device down-samples another part of video frames in the video data of the target video to obtain another group of video frames. 4. The method according to claim 2 or 3, characterized in that, in a group of video frames whose resolution of the two groups of video frames is relatively large, the difference between the frame numbers of every two adjacent video frames The value is m, where m is a positive integer greater than 1. 5. The method according to any one of claims 2 to 4, characterized in that, in a group of video frames with smaller resolutions of the two groups of video frames, multiple groups of video frames with continuous frame numbers are included, each group The video frames with consecutive frame numbers include n video frames, where n is a positive integer greater than or equal to 1. 6. The method according to any one of claims 1 to 5, wherein the frame numbers of the video frames obtained after combining the two groups of video frames are continuous. 7. The method according to any one of claims 1 to 6, wherein, before the sending device determines two groups of video frames according to the video data of the target video, the method further comprises: The sending end device obtains the video data of the target video from the storage space; Alternatively, the sending end device collects video data of the target video in real time. 8. The method according to any one of claims 1 to 7, wherein the sending device sends the first encoded data and the second encoded data respectively corresponding to the two groups of video frames, comprising: The sending end device sends the first encoded data and the second encoded data respectively corresponding to the two groups of video frames to the receiving end device; Alternatively, the sending end device sends the first encoded data and the second encoded data respectively corresponding to the two groups of video frames to the server, and the server is used to forward the two groups of video frames to the receiving end device The frames respectively correspond to the first encoded data and the second encoded data. 9. The method according to claim 1, wherein the receiver device processes the second decoded data according to the first decoded data to obtain the same resolution as the first decoded data. The restore frame, including: The receiver device processes the video frames of the second decoded data according to the video frames of the first decoded data through a preset artificial intelligence AI super-resolution model to obtain the restored frames. 10. The method according to claim 9, wherein the receiver device uses a preset artificial intelligence (AI) super-resolution model to analyze the second decoded data according to the video frame of the first decoded data. The video frame is processed to obtain the restored frame, including: The receiving end device inputs the first video frame of the second decoded data and at least one video frame whose frame number is continuous with the first video frame into the AI super-resolution model to obtain the first video frame The frame corresponding to the restored frame. 11. A video transmission method, characterized in that the method comprises: Determine two groups of video frames according to the video data of the target video, the resolution of each video frame in each group of video frames is the same, and the resolution of one group of video frames is greater than the resolution of the other group of video frames, and the resolution of each group of video frames in a group of video frames The frame number of any video frame is different from the frame number of any video frame in another group of video frames, and each group of video frames includes multiple video frames with intermittent frame numbers; Encoding each group of video frames respectively to obtain encoded data corresponding to each group of video frames; Each of said coded data is transmitted. 12. The method according to claim 11, wherein the video data of the target video comprises: first video data and second video data; The said determination of two groups of video frames according to the video data of the target video includes: Downsampling the first video data to obtain the second video data, the resolution of each video frame in the first video data is higher than the resolution of each video frame in the second video data; Selecting a plurality of video frames from the first video data and the second video data to obtain the two groups of video frames. 13. The method according to claim 11, wherein the resolution of each video frame in the video data of the target video is the same; The said determination of two groups of video frames according to the video data of the target video includes: Selecting a part of video frames from the video data of the target video to obtain a set of video frames; Downsampling is performed on another part of video frames in the video data of the target video to obtain another group of video frames. 14. The method according to claim 12 or 13, characterized in that, in a group of video frames with larger resolutions of the two groups of video frames, the difference between the frame numbers of every two adjacent video frames The value is m, where m is a positive integer greater than 1. 15. The method according to any one of claims 12 to 14, characterized in that, in the group of video frames with smaller resolutions of the two groups of video frames, multiple groups of video frames with continuous frame numbers are included, each group The video frames with consecutive frame numbers include n video frames, where n is a positive integer greater than or equal to 1. 16. The method according to any one of claims 11 to 15, wherein the frame numbers of the video frames obtained after combining the two groups of video frames are continuous. 17. A video transmission method, characterized in that the method comprises: receiving first encoded data and second encoded data of the target video, where the resolutions corresponding to the first encoded data and the second encoded data are different; Decoding the first encoded data and the second encoded data respectively to obtain first decoded data corresponding to the first encoded data and second decoded data corresponding to the second encoded data, the first decoded The resolution of the data is greater than the resolution of the second decoded data; Process the second decoded data according to the first decoded data to obtain a restored frame with the same resolution as the first decoded data; Combining the first decoded data and the restored frame to obtain video data of the target video. 18. The method according to claim 17, characterized in that, according to the first decoded data, the second decoded data is processed to obtain a restored frame with the same resolution as the first decoded data ,include: The restored frame is obtained by processing the video frame of the second decoded data according to the video frame of the first decoded data through a preset AI super-resolution model. 19. The method according to claim 18, wherein the video frame of the second decoded data is processed according to the video frame of the first decoded data through the preset AI super-resolution model, Get the restore frame, including: Inputting the first video frame of the second decoded data and at least one video frame whose frame number is continuous with the first video frame into the AI super-resolution model to obtain a restored frame corresponding to the first video frame . 20. A video transmission system, characterized in that, the video transmission system comprises: a sending end device and a receiving end device; The sending end device is configured to execute the video transmission method according to any one of claims 11 to 16; The receiver device is configured to execute the video transmission method according to any one of claims 17-19. 21. An electronic device, characterized in that it comprises: a processor, the processor is configured to run a computer program stored in a memory, so as to realize the process described in any one of claims 11 to 16 or 17 to 19 Video transmission method. 22. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any of claims 11-16 or 17-19 is implemented. A video transmission method described in one item. 23. A system on a chip, characterized in that the system on a chip comprises a memory and a processor, and the processor executes the computer program stored in the memory to implement the The video transmission method described in any one.

Images