CN112887623B - Image generation method, device and electronic equipment - Google Patents

Abstract

The embodiment of the present application discloses an image generation method, device and electronic equipment. The method includes: receiving the user's first input on the long-exposure image. The long-exposure image and the target video are captured by the camera at the target scene at the same time; the target video includes A plurality of video frames; in response to the first input, fusion processing is performed on the first video frame in the target video to generate the first target image; wherein, the first video frame is obtained by removing the target object from multiple video frames; the target object Including: a second video frame including the first target area, or a first target area in the second video frame, the first target area being associated with the first input. According to the embodiment of the present application, the problem that it often takes a long time for a user to take a satisfactory long-exposure image can be solved.

Description

Image generation method, device and electronic equipment

technical field

The embodiments of the present application relate to the field of information processing, and in particular, to an image generation method, device, and electronic equipment.

Background technique

At present, as the photography functions of electronic devices are becoming more and more powerful, streamer shutters can automatically extend the shutter time and integrate the dynamic changes of the subject within a period of time into one image to obtain long-exposure images, which are widely welcomed by users. When a user takes a long-exposure image, because the electronic device is easily shaken by the user, the quality of the obtained long-exposure image is poor.

During the process of implementing this application, the applicant found that at least the following problems existed in the prior art:

In order to obtain a satisfactory long-exposure image, the user needs to take multiple shots, and the operation is cumbersome.

Contents of the invention

Embodiments of the present application provide an image generation method, device, and electronic equipment, which can solve the problem that a user needs to take multiple shots in order to obtain a satisfactory long-exposure image, and the operation is cumbersome.

In order to solve the above-mentioned technical problems, the application is implemented as follows:

In the first aspect, the embodiment of the present application provides an image generation method, which may include:

receiving the user's first input on the long-exposure image, the long-exposure image and the target video are obtained by shooting the target scene simultaneously by the camera; the target video includes multiple video frames;

In response to the first input, fusion processing is performed on the first video frame in the target video to generate the first target image;

Wherein, the first video frame is obtained by removing the target object from multiple video frames; the target object includes: the second video frame including the first target area, or the first target area in the second video frame, the first target area and The first input is associated.

In a second aspect, the embodiment of the present application provides an image generating device, which may include:

The receiving module is configured to receive the user's first input to the long-exposure image, the long-exposure image and the target video are obtained by shooting the target scene simultaneously by the camera; the target video includes a plurality of video frames;

A generating module, configured to perform fusion processing on the first video frame in the target video to generate the first target image in response to the first input;

Wherein, the first video frame is obtained by removing the target object from multiple video frames; the target object includes: the second video frame including the first target area, or the first target area in the second video frame, the first target area and The first input is associated.

In the third aspect, the embodiment of the present application provides an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored in the memory and operable on the processor. When the program or instruction is executed by the processor, the The steps of the method of the first aspect.

In a fourth aspect, the embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method in the first aspect are implemented.

In the fifth aspect, the embodiment of the present application provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method in the first aspect.

In the embodiment of the present application, the first target image is generated by synthesizing the first video frame obtained by removing the target object from the video frames of the target video in response to the user's first input of the long exposure image. Since the long-exposure image and the target video are captured by the camera at the same time of the target scene, the dynamic information and static information in the long-exposure image are recorded in the target video. Wherein, the target object includes: the second video frame including the first target area associated with the first input, or the first target area in the second video frame. Therefore, by performing fusion processing on the first video frame, an image can be synthesized based on the video frame without the first target area to generate the first target image desired by the user, which improves the error tolerance in the process of shooting long exposure images and reduces Number of shots.

Description of drawings

The present application can be better understood from the following description of specific embodiments of the present application in conjunction with the accompanying drawings, wherein the same or similar reference numerals represent the same or similar features.

FIG. 1 is a schematic diagram of an application scenario of an image generation method provided in an embodiment of the present application;

FIG. 2 is a flow chart of an image generation method provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of an interface for displaying long-exposure images and target videos provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of an interface for displaying a second target area provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of an interface for displaying a first target area provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of an interface for displaying a second logo provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of an interface for displaying a target time period provided by an embodiment of the present application;

FIG. 8 is a schematic diagram of an interface for displaying removal of the first target area provided by the embodiment of the present application;

FIG. 9 is a schematic diagram of an interface for displaying and merging a third target area provided by an embodiment of the present application;

FIG. 10 is a schematic structural diagram of an image generation device provided by an embodiment of the present application;

FIG. 11 is a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the present application;

FIG. 12 is a schematic diagram of a hardware structure of another electronic device provided by an embodiment of the present application.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

The terms "first", "second" and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the application can be practiced in sequences other than those illustrated or described herein. In addition, "and/or" in the specification and claims means at least one of the connected objects, and the character "/" generally means that the related objects are an "or" relationship.

The image generation method provided in the embodiment of the present application can be applied to at least the following application scenarios, which will be described below.

At present, with the continuous development of electronic equipment, most electronic equipment can provide shooting functions related to the streamer shutter. The Ambilight Shutter can capture the movement trajectory of dynamic objects and automatically extend the shutter time, allowing you to take pictures with radiant and beautiful special light and shadow.

Because the essence of the streamer shutter is to fuse the changes of dynamic objects within a period of time into a long exposure image, it will inevitably take a certain amount of time to shoot a long exposure image. When a user takes a long-exposure image, because the electronic device is easily shaken by the user, the quality of the obtained long-exposure image is poor. In order to obtain a satisfactory long-exposure image, the user needs to consume time for secondary shooting, or even multiple shooting, and the operation is cumbersome.

As shown in FIG. 1 , the long exposure image includes the subject 10 that the user expects to appear in the long exposure image, and also includes impurity objects 20 , where the impurity object 20 is not expected by the user to appear in the long exposure image. For example, if the user wants to take a long-exposure image that can reflect "heavy traffic", then the vehicle driving on the road is the subject 10 that the user expects to appear in the long-exposure image, and the pedestrian passing by the road is the impurity object 20 . If the user wants to obtain a long-exposure image that does not contain the impurity object 20, only re-shooting is required. However, during the re-shooting process, there may still be pedestrians passing by, resulting in a low success rate of shooting a long-exposure image satisfactory to the user, and the operation is cumbersome.

In view of the problems in related technologies, the embodiments of the present application provide an image generation method, device, electronic equipment and storage medium, which can solve the problems in related technologies that users need to take multiple shots in order to obtain satisfactory long-exposure images, and the operation is relatively cumbersome. question.

In addition to being applicable to the above application scenarios, the method provided in the embodiment of the present application may also be applied to any scene where the captured long-exposure image quality is poor.

Through the method provided by the embodiment of the present application, the first target image is generated by synthesizing the first video frame obtained by removing the target object from the video frames of the target video in response to the user's first input of the long exposure image. Since the long-exposure image and the target video are captured by the camera at the same time of the target scene, the dynamic information and static information in the long-exposure image are recorded in the target video. Wherein, the target object includes: the second video frame including the first target area associated with the first input, or the first target area in the second video frame. Therefore, by performing synthesis processing on the first video frame, an image can be synthesized based on the video frame without the first target area to generate the first target image desired by the user, which improves the error tolerance in the process of taking long exposure images and reduces Number of shots.

Based on the above application scenarios, the image generation method provided by the embodiment of the present application will be described in detail below.

FIG. 2 is a flow chart of an image generation method provided by an embodiment of the present application.

As shown in Figure 2, the image generation method may include steps 210-step 220, the method is applied to an image generation device, specifically as follows:

Step 210, receiving the user's first input on the long exposure image, the long exposure image and the target video are obtained by shooting the target scene simultaneously by the camera; the target video includes multiple video frames.

Step 220, in response to the first input, synthesize the first video frame in the target video to generate a first target image; wherein, the first video frame is obtained by removing the target object from multiple video frames; the target object includes: A second video frame including the first target area, or a first target area in the second video frame, the first target area being associated with the first input.

In the image generation method provided by the embodiment of the present application, the first target image is generated by synthesizing the first video frame obtained by removing the target object from the video frames of the target video in response to the user's first input of the long exposure image. Since the long-exposure image and the target video are captured by the camera at the same time of the target scene, the dynamic information and static information in the long-exposure image are recorded in the target video. Wherein, the target object includes: the second video frame including the first target area associated with the first input, or the first target area in the second video frame. Therefore, by performing synthesis processing on the first video frame, an image can be synthesized based on the video frame without the first target area to generate the first target image desired by the user, which improves the error tolerance in the process of taking long exposure images and reduces Number of shots.

Below, the contents of step 210-step 220 are described respectively:

First, step 210 is involved.

Wherein, the long-exposure image and the target video are obtained by shooting the target scene simultaneously by the camera; the target video includes multiple video frames.

Wherein, the following steps may also be included before the above-mentioned step of receiving the user's first input on the long-exposure image:

When the viewfinder frame of the camera displays the target scene, a user's shooting input is received; in response to the shooting input, a long-exposure image of the target scene and a target video are captured.

That is, the long-exposure image and the target video can be captured simultaneously by the same camera pair using a target scene, and the target video records the dynamic information and static information in the long-exposure image.

As shown in Figure 3, in response to the shooting input, the target scene is shot at the same time, and the associated long exposure image and target video are obtained. The long exposure image retains the dynamic information of the target scene within the shooting time (such as: a moving vehicle , pedestrians and light tracks, etc.) and static information (such as: image areas corresponding to buildings, etc.), the target video also retains the dynamic information and static information of the target scene within the shooting time.

Wherein, the long exposure image includes dynamic information and static information of the target scene, the dynamic information is used to indicate the image area corresponding to the dynamic object in the target scene, and the static information is used to indicate the image area corresponding to the static object in the target scene. In the step of performing fusion processing on the first video frame in the target video to generate the first target image, it may specifically include the following steps:

Identify the dynamic object and static object in the first video frame; extract the dynamic information of the dynamic object and the static information of the static object from the first video frame; perform fusion processing on the dynamic information in multiple first video frames to generate a target dynamic information; performing fusion processing on static information and target motion information to generate a first target image.

Among them, the dynamic objects may include: moving vehicles, pedestrians and light tracks. Static objects may include immobile stationary objects such as buildings and roads. By identifying and retaining the static information of the static object, extracting the dynamic information of the dynamic object in each first video frame to synthesize the dynamic effect (and target dynamic information), and finally presenting the first target of motion blur, or light trail and other effects image.

Then, step 220 is involved.

In response to the first input, a first video frame in the target video is synthesized to generate a first target image; wherein, the first video frame is obtained by removing the target object from multiple video frames.

Wherein, the target object includes: the second video frame including the first target area, or the first target area in the second video frame.

Here, the second video frame of the first target area, or the first target area in the second video frame is removed from multiple video frames, and then a more perfect picture can be generated by the first video frame obtained after removal first target image.

Wherein, the first target area is associated with the first input. The first input can be used to indicate the first target area in the long-exposure image, that is, the area that the user wants to remove; the first input can also be used to indicate the second target area in the long-exposure image, that is, the area that the user wants to keep, that is In the long-exposure image, all regions except the second target region may be the first target region. Wherein, the first input mentioned above is used to indicate the second target area in the long exposure image, and the first target area does not overlap with the second target area.

The first input is used to indicate a second target area in the long exposure image, and the second target area may include a subject that the user expects to appear in the long exposure image.

As shown in FIG. 4 , the long-exposure image includes a light-shadow trajectory similar to a circle, and the long-exposure image also includes some other impurity regions. Since the second target area may include objects that the user expects to remain in the long-exposure image, correspondingly, the first target area may include foreign objects that the user does not expect to appear in the long-exposure image.

First, in response to the user's first input on the second target area, identify the area of the long exposure image except the second target area; then, remove the target object from multiple video frames to obtain the first video frame; finally, the target video The first video frame in is synthesized to generate the first target image.

Here, by removing the second video frame including the first target area, or the first target area in the second video frame from multiple video frames, a more detailed image can be generated by removing the first video frame obtained The first target image that matches the user's expectations.

In a possible embodiment, the first input is used to indicate the first target area, and before the above-mentioned step of performing fusion processing on the first video frame in the target video, the following steps may also be included:

Identifying a second video frame including the first target area in the target video; removing the second video frame from the video frame to obtain the first video frame.

In response to the first input, some second video frames including the first target area are deleted, and then the remaining first video frames are re-fused to generate a more perfect long-exposure image. As shown in FIG. 5 , the long-exposure image includes a light-shadow trajectory similar to a circle, and the long-exposure image also includes some other impurity objects. Wherein, the first target area may include an area where impurity objects that the user does not expect to appear in the long-exposure image are located.

First, in response to a user's first input on the first target area, a first target area of the long-exposure image is identified; then, a second video frame including the first target area is removed from a plurality of video frames to obtain the first video frame ; Finally, the first video frame in the target video is synthesized to generate the first target image.

Here, by removing the second video frame including the first target area from multiple video frames, a first target image that is more in line with user expectations can be generated by removing the first video frame obtained after the second video frame .

In a possible embodiment, the step of removing the second video frame from the video frame to obtain the first video frame may specifically include the following steps:

Display the first mark on the time axis of the target video, the first mark is used to indicate the third video frame including the first target area, the third video frame includes the second video frame; receive the user's second mark in the first mark For the second input, the second identifier corresponds to the second video frame; in response to the second input, the second video frame is removed from the video frame to obtain the first video frame.

The first identifier is displayed on the time axis of the target video, for the user to select which second video frames to delete. As shown in FIG. 6 , the time axis of the target video includes a plurality of first markers, the first markers are used to indicate the third video frame including the first target area, and the second markers correspond to the second video frame. The first identifier includes the second identifier, and correspondingly, the third video frame includes the second video frame. At this time, in response to the user's second input of the second identifier, the second video frame may be removed from the video frame to obtain the first video frame.

Here, by detecting the third video frame including the first target area, the third video frame containing the "impurity object" can be quickly determined, and the first mark corresponding to the third video frame is displayed on the time axis for The user selects the second identifier corresponding to the second video frame from the first identifier, and then the second video frame including the first target area can be removed from the plurality of video frames, and then the second video frame obtained after removing the second video frame can be A video frame is used to generate a first target image that is more in line with user expectations.

In another possible embodiment, the above-mentioned step of removing the second video frame from the video frame to obtain the first video frame may specifically include the following steps:

Displaying the target video including the time axis; receiving the third input from the user to the target time period in the time axis; the video segment corresponding to the target time period includes the second video frame; in response to the third input, removing the second video from the video frame frame to get the first video frame.

Receive the user's third input on the target time period. The third input may include the start progress and end progress of the target time period in the time axis, as shown in the two vertical lines in Figure 7. The area between the two vertical lines is The time period you want to remove. In response to the third input, the second video frame included in the time period may be removed.

Here, by displaying the target video including the time axis, in response to the user's third input of the target time period in the time axis, the second video frame corresponding to the target time period is removed from the video frame to obtain the first video frame. The user can select the video frame to be removed by himself, and then the second video frame including the first target area can be removed from multiple video frames, and a first video frame obtained after removing the second video frame can be used to generate a The first target image that is more in line with user expectations.

As an implementation of the present application, the target object is the first target area in the second video frame. In order to improve the synthesis effect of the long-exposure image, in the above-mentioned fusion processing of the first video frame in the target video Before the step, you can also include the following steps:

In response to the first input, identifying a second video frame including the first target area in the target video, and a fourth video frame not including the first target area; removing the first target area from the second video frame to obtain the first video frame;

Correspondingly, the first video frame in the target video is synthesized, including:

Fusion processing is performed on the first video frame and the fourth video frame to generate a first target image.

Wherein, the first target area mentioned above may be automatically recognized by the electronic device in response to the first input, or may be the first target area selected by the user in the long-exposure video.

Exemplarily, as shown in FIG. 8 , the long-exposure image includes a light-shadow trajectory similar to a circle, and the long-exposure image also includes some first target regions that the user does not want to keep in the long-exposure image. The user may select the first target area in the long-exposure video, and then in response to the user's input to the "Static" button, the electronic device will regard the first target area as a static area without fusion. Finally, in response to the user's input of the "fusion" button, a first target image that does not include the first target region is generated. As shown in the right figure in Figure 8.

Here, the first target image is generated by synthesizing the first video frame obtained by removing the first target region from the second video frame and the fourth video frame. Since the fourth video frame itself does not include the first target area, and the first video frame is obtained by removing the first target area from the second video frame, the first video frame also does not include the first target area. Therefore, the first target image generated based on the synthesis processing of the first video frame and the fourth video frame does not include the first target area, which meets user expectations.

In yet another possible embodiment, a fourth input from the user on the long-exposure image is received, and the fourth input is used to indicate a third target area in the long-exposure image; in response to the fourth input, combine the third target area with the multiple The first video frame is the video frame in the fused target video.

In order to meet the needs of users who may want to add some special light and shadow areas to long-exposure images, the fourth input of the third target area can be selected in response to the user; the third target area is fused with multiple video frames to obtain the fused The target video, and then synthesize the first target image according to the first video frame in the fused target video.

Exemplarily, as shown in FIG. 9 , in response to the user's fourth input of selecting "little star" (the third target area), and then in response to the user's input of the "Dynamic" button, the electronic device will display the third The target area is determined as a dynamic area, and the "little star" is applied to the video frame, that is, the third target area is fused with multiple video frames to obtain the fused target video. Finally, in response to the user's input of the "fusion" button, the first target image is generated based on the first video frame in the fused target video, providing more possibilities for image synthesis.

Thus, by responding to the fourth input of the user selecting the third target area; the third target area is fused with a plurality of video frames to obtain the fused target video, and then the first video frame in the fused target video is Fusion processing is performed to generate the first target image that satisfies the user's synthesis requirements.

Wherein, the step of merging the third target area and the plurality of video frames in response to the fourth input mentioned above to obtain the fused target video may specifically include the following steps:

In response to the fourth input, identify the target dynamic object in the target video; determine the moving track of the target dynamic object in the target video according to the position of the target dynamic object in the video frame; according to the moving track, combine the third target area with multiple The video frames are fused to obtain the fused target video.

Optionally, in addition to the above-mentioned implementation of fusing the third target area with multiple video frames to obtain the fused target video, the first target image can be generated based on the first video frame in the fused target video In addition to the manner, the following implementation manners may also be included: in response to the fourth input, the third target area is fused with the first video frame to obtain the fused first video frame; the first video frame in the target video is fused The fusion processing to generate the first target image includes: performing fusion processing on the fused first video frame to generate the first target image.

In order to meet the user's need to add some special light and shadow areas to the long-exposure image, the fourth input of the third target area can be selected in response to the user; the third target area is fused with the first video frame to obtain the fused Correspondingly, in the step of performing fusion processing on the first video frame in the target video and generating the first target image, it specifically includes: performing fusion processing on the first video frame after fusion to generate first target image.

Exemplarily, as shown in FIG. 9 , in response to the user's fourth input of selecting "little star" (the third target area), and then in response to the user's input of the "Dynamic" button, the electronic device will display the third The target area is determined as a dynamic area, and the "little star" is applied to the first video frame to obtain the fused first video frame. Finally, in response to the user's input of the "fusion" button, the fused first video frame is fused to generate the first target image, which provides more possibilities for image synthesis.

Thus, by responding to the fourth input of selecting the third target area by the user, the third target area is fused with the first video frame to obtain a fused first video frame; performing fusion processing on the fused first video frame , to generate the first target image that meets the user's synthesis requirements.

Wherein, in the step of merging the third target area and the first video frame to obtain the fused first video frame in response to the fourth input mentioned above, the following steps may be specifically included:

In response to the fourth input, identify the target dynamic object in the target video; determine the moving track of the target dynamic object in the target video according to the position of the target dynamic object in the video frame; according to the moving track, combine the third target area with the first The video frames are fused to obtain the fused first video frame.

For example, the user takes a long-exposure image on a highway. The target vehicle driving on the highway may be the target dynamic object in the target video, and the long-exposure image also contains "small stars". At this time, you can respond to The fourth input, according to the position of the "target vehicle" in the video frame, determine the moving track of the "target vehicle" during the shooting process of the target video; according to the moving track, compare the simulated moving track of the "little star" with the first video frame Fusion to obtain the first video frame after fusion.

Thus, the "little star" has a moving track similar to the light and shadow of the vehicle, and the first target image generated based on the first video frame includes the light and shadow track formed by the fast movement of the "little star", forming a beautiful first target image .

In addition, the third target area may be content in images other than the above-mentioned long-exposure images, providing users with more possibilities for image synthesis.

Understandably, through the first input and the fourth input, not only the target object can be removed, but also the information of the third target area can be fused simultaneously to obtain the first target image.

To sum up, in the embodiment of the present application, the first target image is generated by synthesizing the first video frame obtained by removing the target object from the video frames of the target video in response to the user's first input of the long exposure image. Since the long-exposure image and the target video are captured by the camera at the same time of the target scene, the dynamic information and static information in the long-exposure image are recorded in the target video. Wherein, the target object includes: the second video frame including the first target area associated with the first input, or the first target area in the second video frame. Therefore, by performing synthesis processing on the first video frame, an image can be synthesized based on the video frame without the first target area to generate the first target image desired by the user, which improves the error tolerance in the process of taking long exposure images and reduces Number of shots.

It should be noted that, for the image generation method provided in the embodiment of the present application, the execution subject may be an image generation device, or a control module in the image generation device for executing the loading image generation method. In the embodiment of the present application, the method for generating a loaded image executed by the image generating device is taken as an example to illustrate the image generating method provided in the embodiment of the present application.

In addition, based on the above image generation method, an embodiment of the present application further provides an image generation device, which will be described in detail with reference to FIG. 10 .

FIG. 10 is a schematic structural diagram of an image generating device provided by an embodiment of the present application.

As shown in Figure 10, the image generating device 1000 may include:

The receiving module 1010 is configured to receive the user's first input on the long exposure image, the long exposure image and the target video are obtained by shooting the target scene simultaneously by the camera; the target video includes multiple video frames.

The generation module 1020 is configured to perform fusion processing on the first video frame in the target video to generate a first target image in response to the first input.

Wherein, the first video frame is obtained by removing the target object from multiple video frames; the target object includes: the second video frame including the first target area, or the first target area in the second video frame, the first target area and The first input is associated;

The first input is used to indicate the first target area, or the first input is used to indicate the second target area in the long exposure image, and the first target area is at least a partial area in the long exposure image except the second target area.

In a possible embodiment, the long exposure image includes dynamic information and static information of the target scene, the dynamic information is used to indicate the image area corresponding to the dynamic object in the target scene, and the static information is used to indicate the static object in the target scene The corresponding image area, generating module 1020, includes:

The identification module is used to identify dynamic objects and static objects in the first video frame.

The extraction module is used to extract the dynamic information of the dynamic object and the static information of the static object from the first video frame.

The fusion module is configured to perform fusion processing on dynamic information in multiple first video frames to generate target dynamic information.

The fusion module is further configured to perform fusion processing on the static information and the target motion information to generate the first target image.

In a possible embodiment, the first input is used to indicate the first target area, and the identification module is further used to identify a second video frame including the first target area in the target video.

The removal module is used to remove the second video frame from the video frame to obtain the first video frame.

In a possible embodiment, the removal module includes:

The display module is configured to display the first mark on the time axis of the target video, the first mark is used to indicate the third video frame including the first target area, and the third video frame includes the second video frame.

The receiving module 1010 is further configured to receive a second input from the user on the second identifier in the first identifier, where the second identifier corresponds to the second video frame.

The removing module is specifically configured to, in response to the second input, remove the second video frame from the video frame to obtain the first video frame.

In a possible embodiment, the removal module includes:

The display module is used for displaying the target video including a time axis.

The receiving module 1010 is further configured to receive a third input from the user on the target time period in the time axis; the video segment corresponding to the target time period includes the second video frame.

The removing module is specifically configured to, in response to the third input, remove the second video frame from the video frame to obtain the first video frame.

In a possible embodiment, the identification module is further configured to, in response to the first input, identify a second video frame including the first target area and a fourth video frame not including the first target area in the target video.

The removal module is further configured to remove the first target area from the second video frame to obtain the first video frame.

The generation module 1020 is specifically configured to perform fusion processing on the first video frame and the fourth video frame to generate the first target image.

In a possible embodiment, the receiving module 1010 is further configured to receive a fourth input from the user on the long exposure image, where the fourth input is used to indicate the third target area in the long exposure image.

The fusion module is further configured to, in response to the fourth input, fuse the third target area with multiple video frames to obtain a fused target video; the first video frame is a video frame in the fused target video.

The fusion module is further configured to, in response to the fourth input, fuse the third target area with the first video frame to obtain a fused first video frame.

The fusion module is further configured to perform fusion processing on the fused first video frame to generate the first target image.

In a possible embodiment, the fusion module is further configured to identify a target dynamic object in the target video in response to the fourth input.

The determination module is further configured to determine the moving track of the target dynamic object in the target video according to the position of the target dynamic object in the video frame.

The fusion module is further configured to fuse the third target area with the first video frame according to the movement track to obtain the first video frame after fusion.

In a possible embodiment, the receiving module 1010 is further configured to receive a user's shooting input when the target scene is displayed in the viewfinder frame of the camera.

The image generating device 1000 may also include:

The photographing module is used for photographing a long-exposure image of a target scene and a target video in response to a photographing input.

To sum up, the image generating device provided by the embodiment of the present application generates the first target object by synthesizing the first video frame obtained by removing the target object from the video frame of the target video in response to the user’s first input to the long exposure image. image. Since the long-exposure image and the target video are captured by the camera at the same time of the target scene, the dynamic information and static information in the long-exposure image are recorded in the target video. Wherein, the target object includes: the second video frame including the first target area associated with the first input, or the first target area in the second video frame. Therefore, by performing synthesis processing on the first video frame, an image can be synthesized based on the video frame without the first target area to generate the first target image desired by the user, which improves the error tolerance in the process of taking long exposure images and reduces Number of shots.

The image generating device in the embodiment of the present application may be a device, or may be a component, an integrated circuit, or a chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, tablet computer, notebook computer, palmtop computer, vehicle electronic device, wearable device, ultra-mobile personal computer (ultra-mobile personal computer, UMPC), netbook or personal digital assistant (personal digital assistant) , PDA), etc., the non-mobile electronic device can be a server, a network attached storage (NetworkAttached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., the embodiment of the present application Not specifically limited.

The image generation device in the embodiment of the present application may be a device with an operating system. The operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, which are not specifically limited in this embodiment of the present application.

The image generation device provided in the embodiment of the present application can implement various processes implemented by the image generation device in the method embodiments in FIGS. 2-9 . To avoid repetition, details are not repeated here.

Optionally, as shown in FIG. 11 , the embodiment of the present application also provides an electronic device 1100, including a processor 1101, a memory 1102, and a program or instruction stored in the memory 1102 and operable on the processor 1101. The program Or, when the instructions are executed by the processor 1101, each process of the above-mentioned chat group creation method embodiment can be realized, and the same technical effect can be achieved. To avoid repetition, details are not repeated here.

It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

FIG. 12 is a schematic diagram of a hardware structure of another electronic device provided by an embodiment of the present application.

The electronic device 1200 includes, but is not limited to: a radio frequency unit 1201, a network module 1202, an audio output unit 1203, an input unit 1204, a sensor 1205, a display unit 1206, a user input unit 1207, an interface unit 1208, a memory 1209, and a processor 1210, etc. part. Wherein, the input unit 1204 may include a graphics processor 12041 and a microphone 12042; the display unit 1206 may include a display panel 12061; the user input unit 1207 may include a touch panel 12071 and other input devices 12072; the memory 1209 may include an application program and an operating system.

Those skilled in the art can understand that the electronic device 1200 can also include a power supply (such as a battery) for supplying power to various components, and the power supply can be logically connected to the processor 1210 through the power management system, so that the management of charging, discharging, and function can be realized through the power management system. Consumption management and other functions. The structure of the electronic device shown in FIG. 12 does not constitute a limitation to the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine some components, or arrange different components, and details will not be repeated here. .

The user input unit 1207 is configured to receive the user's first input on the long exposure image. The long exposure image and the target video are obtained by shooting the target scene simultaneously by the camera; the target video includes multiple video frames.

The processor 1210 is configured to, in response to a first input, perform synthesis processing on a first video frame in the target video to generate a first target image.

Optionally, the processor 1210 is further configured to identify dynamic objects and static objects in the first video frame.

The processor 1210 is further configured to extract dynamic information of a dynamic object and static information of a static object from the first video frame.

The processor 1210 is further configured to perform fusion processing on dynamic information in multiple first video frames to generate target dynamic information.

The processor 1210 is further configured to perform fusion processing on static information and target motion information to generate a first target image.

Optionally, the first input is used to indicate the first target area, and the processor 1210 is further used to identify a second video frame including the first target area in the target video.

The processor 1210 is further configured to remove the second video frame from the video frame to obtain the first video frame.

The display unit 1206 is configured to display a first mark on the time axis of the target video, where the first mark is used to indicate a third video frame including the first target area, and the third video frame includes the second video frame.

The user input unit 1207 is further configured to receive a second input from the user on the second identifier in the first identifier, where the second identifier corresponds to the second video frame.

The processor 1210 is further configured to, in response to the second input, remove the second video frame from the video frame to obtain the first video frame.

Optionally, the display unit 1206 is configured to display the target video including a time axis.

The user input unit 1207 is further configured to receive a third input from the user on the target time period in the time axis; the video segment corresponding to the target time period includes the second video frame.

The processor 1210 is further configured to, in response to the third input, remove the second video frame from the video frame to obtain the first video frame.

Optionally, the processor 1210 is further configured to, in response to the first input, identify a second video frame including the first target area and a fourth video frame not including the first target area in the target video.

The processor 1210 is further configured to remove the first target area from the second video frame to obtain the first video frame.

The processor 1210 is further configured to perform fusion processing on the first video frame and the fourth video frame to generate the first target image.

Optionally, the user input unit 1207 is further configured to receive a fourth input from the user on the long exposure image, where the fourth input is used to indicate the third target area in the long exposure image.

The processor 1210 is further configured to, in response to the fourth input, fuse the third target area with multiple video frames to obtain a fused target video; the first video frame is a video frame in the fused target video.

Optionally, the processor 1210 is further configured to, in response to a fourth input, fuse the third target area with the first video frame to obtain a fused first video frame;

The processor 1210 is further configured to perform fusion processing on the fused first video frame to generate a first target image.

Optionally, the processor 1210 is further configured to identify a target dynamic object in the target video in response to a fourth input.

The processor 1210 is further configured to determine the moving track of the target dynamic object in the target video according to the position of the target dynamic object in the video frame.

The processor 1210 is further configured to fuse the third target area with the first video frame according to the movement track to obtain the first video frame after fusion.

Optionally, the user input unit 1207 is further configured to receive a user's shooting input when the target scene is displayed in the viewfinder frame of the camera.

The processor 1210 is further configured to capture a long-exposure image of a target scene and a target video in response to a shooting input.

In the embodiment of the present application, the first target image is generated by synthesizing the first video frame obtained by removing the target object from the video frames of the target video in response to the user's first input of the long exposure image. Since the long-exposure image and the target video are captured by the camera at the same time of the target scene, the dynamic information and static information in the long-exposure image are recorded in the target video. Wherein, the target object includes: the second video frame including the first target area associated with the first input, or the first target area in the second video frame. Therefore, by performing synthesis processing on the first video frame, an image can be synthesized based on the video frame without the first target area to generate the first target image desired by the user, which improves the error tolerance in the process of taking long exposure images and reduces Number of shots.

It should be understood that, in the embodiment of the present application, the input unit 1204 may include a graphics processor (Graphics Processing Unit, GPU) 12041 and a microphone 12042. Camera) to process the image data of still pictures or videos. The display unit 1206 may include a display panel 12061, and the display panel 12061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 1207 includes a touch panel 12071 and other input devices 12072 . Touch panel 12071, also called touch screen. The touch panel 12071 may include two parts, a touch detection device and a touch controller. Other input devices 12072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here. The memory 1209 can be used to store software programs as well as various data, including but not limited to application programs and operating systems. The processor 1210 may integrate an application processor and a modem processor, wherein the application processor mainly processes operating systems, user interfaces, and application programs, and the modem processor mainly processes wireless communications. It can be understood that the foregoing modem processor may not be integrated into the processor 1210 .

The embodiment of the present application also provides a readable storage medium. The readable storage medium stores programs or instructions. When the program or instructions are executed by the processor, the various processes of the above-mentioned image generation method embodiments can be achieved, and the same To avoid repetition, the technical effects will not be repeated here.

Wherein, the processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.

The embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the above image generation method embodiment Each process can achieve the same technical effect, so in order to avoid repetition, it will not be repeated here.

It should be understood that the chips mentioned in the embodiments of the present application may also be called system-on-chip, system-on-chip, system-on-a-chip, or system-on-a-chip.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. Functions are performed, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM, disk, CD) contains several instructions to enable a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in various embodiments of the present application.

The embodiments of the present application have been described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementations. The above-mentioned specific implementations are only illustrative and not restrictive. Those of ordinary skill in the art will Under the inspiration of this application, without departing from the purpose of this application and the scope of protection of the claims, many forms can also be made, all of which belong to the protection of this application.

Claims (10)

1. An image generation method, comprising:

receiving a first input of a user to a long exposure image, wherein the long exposure image and a target video are obtained by shooting a target scene by a camera at the same time; the target video comprises a plurality of video frames;

responding to the first input, performing fusion processing on a first video frame in the target video, and generating a first target image;

the first video frame is obtained by removing a target object from the plurality of video frames; the target object includes: a second video frame comprising a first target area, or the first target area in the second video frame;

the first input is used for indicating the first target area, or indicating a second target area in the long-exposure image, and the first target area is at least a partial area except the second target area in the long-exposure image;

the generating a first target image by performing fusion processing on a first video frame in the target video, where the long-exposure image includes dynamic information and static information of the target scene, the dynamic information is used to indicate an image region corresponding to a dynamic object in the target scene, and the static information is used to indicate an image region corresponding to a static object in the target scene, and the generating the first target image includes:

identifying a dynamic object and a static object in the first video frame;

extracting the dynamic information of the dynamic object and the static information of the static object from the first video frame;

performing fusion processing on the dynamic information in the plurality of first video frames to generate target dynamic information;

and performing fusion processing on the static information and the target dynamic information to generate the first target image.

2. The method of claim 1, wherein the first input is indicative of the first target region, and wherein prior to the fusing the first video frame of the target video, the method further comprises:

identifying a second video frame in the target video that includes the first target region;

and removing the second video frame from the video frame to obtain the first video frame.

3. The method of claim 2, wherein said removing the second video frame from the video frames to obtain the first video frame comprises:

displaying a first identifier on a time axis of the target video, wherein the first identifier is used for indicating a third video frame comprising the first target area, and the third video frame comprises the second video frame;

receiving a second input of a second identifier of the first identifiers by the user, wherein the second identifier corresponds to the second video frame;

in response to the second input, removing the second video frame from the video frames to obtain the first video frame.

4. The method of claim 2, wherein said removing the second video frame from the video frames to obtain the first video frame comprises:

displaying the target video including a timeline;

receiving a third input of the user for a target time period in the timeline; the video segment corresponding to the target time period comprises the second video frame;

in response to the third input, removing the second video frame from the video frames resulting in the first video frame.

5. The method according to claim 1, wherein the target object is the first target region in the second video frame, and before the fusing the first video frame in the target video, the method further comprises:

in response to the first input, identifying a second video frame of the target video that includes the first target region, and a fourth video frame that does not include the first target region;

removing the first target area from the second video frame to obtain the first video frame;

the fusing the first video frame in the target video comprises:

and performing fusion processing on the first video frame and the fourth video frame to generate the first target image.

6. The method of claim 1, further comprising:

receiving a fourth input of the long-exposure image by the user, wherein the fourth input is used for indicating a third target area in the long-exposure image;

in response to the fourth input, fusing the third target area with the plurality of video frames to obtain a fused target video; the first video frame is a video frame in the fused target video; or,

in response to the fourth input, fusing the third target area and the first video frame to obtain a fused first video frame; the fusing the first video frame in the target video to generate a first target image includes: and performing fusion processing on the fused first video frame to generate the first target image.

7. The method of claim 6, wherein said fusing the third target region with the first video frame in response to the fourth input to obtain a fused first video frame comprises:

identifying a target dynamic object in the target video in response to the fourth input;

determining the moving track of the target dynamic object in the target video according to the position of the target dynamic object in the video frame;

and fusing the third target area and the first video frame according to the movement track to obtain a fused first video frame.

8. The method of claim 1, wherein prior to said receiving a first user input of a long exposure image, the method further comprises:

receiving a photographing input of the user in a case where a finder frame of a camera displays the target scene;

capturing the long-exposure image of the target scene and the target video in response to the capture input.

9. An image generation apparatus, characterized by comprising:

the receiving module is used for receiving first input of a long exposure image by a user, wherein the long exposure image and a target video are obtained by simultaneously shooting a target scene by a camera; the target video comprises a plurality of video frames;

the generating module is used for responding to the first input, performing fusion processing on a first video frame in the target video and generating a first target image;

the first video frame is obtained by removing a target object from the plurality of video frames; the target object includes: a second video frame comprising a first target region, or the first target region in the second video frame, the first target region being associated with the first input;

the first input is used for indicating the first target area, or indicating a second target area in the long-exposure image, and the first target area is at least a partial area except the second target area in the long-exposure image;

the long-exposure image includes dynamic information and static information of the target scene, where the dynamic information is used to indicate an image area corresponding to a dynamic object in the target scene, and the static information is used to indicate an image area corresponding to a static object in the target scene, and the generating module includes:

an identification module for identifying a dynamic object and a static object in the first video frame;

an extraction module for extracting the dynamic information of the dynamic object and the static information of the static object from the first video frame;

the fusion module is used for performing fusion processing on the dynamic information in the plurality of first video frames to generate target dynamic information;

and the fusion module is further used for performing fusion processing on the static information and the target dynamic information to generate the first target image.

10. An electronic device, comprising a processor, a memory and a program stored on the memory and executable on the processor, the program, when executed by the processor, implementing the steps of the image generation method according to any one of claims 1 to 8.

Images