CN114647472B - Image processing method, device, device, storage medium and program product - Google Patents

Abstract

Embodiments of the present disclosure relate to a method, apparatus, device, storage medium, and program product for processing a picture, where the method includes: analyzing a configuration file, and constructing an algorithm operation time sequence diagram, wherein the algorithm operation time sequence diagram comprises a plurality of input nodes and algorithm operation nodes associated with the input nodes; aiming at least one input node in a plurality of input nodes, acquiring an input picture corresponding to the input node according to configuration information of the input node included in a configuration file; and sending the input picture to an algorithm running node associated with the input node so that the algorithm running node associated with the input node processes the input picture. The embodiment of the disclosure solves the problem of single input source in the image algorithm by expanding and configuring the algorithm protocol, designs the multi-input source configuration protocol of the algorithm system, and improves the function, the operation speed and the efficiency of the related algorithm.

Description

Image processing method, device, device, storage medium and program product

technical field

The present disclosure relates to the technical field of data processing, and in particular to an image processing method, device, equipment, storage medium and program product.

Background technique

Existing algorithms are based on an input image to generate algorithm results. The algorithm system is also designed around this premise, and only supports a single input source. The current single-input algorithm system architecture cannot support and expand new algorithm capabilities.

Contents of the invention

In order to solve the above technical problems, the embodiments of the present disclosure provide a picture processing method, device, equipment, storage medium and program product. By expanding and configuring the algorithm protocol, the problem of a single input source in the picture algorithm is solved, and a The multi-input source configuration protocol of the algorithm system improves the operation speed and efficiency of related algorithms.

In a first aspect, an embodiment of the present disclosure provides an image processing method, the method including:

Analyzing the configuration file, constructing an algorithm running sequence diagram, wherein the algorithm running sequence diagram includes a plurality of input nodes and algorithm running nodes associated with the input nodes;

For at least one input node among the plurality of input nodes, obtain an input image corresponding to the input node according to configuration information of the input node included in the configuration file;

sending the input picture to the algorithm running node associated with the input node, so that the algorithm running node associated with the input node processes the input picture.

In a second aspect, an embodiment of the present disclosure provides an image processing device, the device comprising:

A timing diagram building module, configured to parse configuration files and construct an algorithm running timing diagram, wherein the algorithm running timing diagram includes a plurality of input nodes and algorithm running nodes associated with the input nodes;

An input picture acquisition module, configured to acquire an input picture corresponding to the input node according to the configuration information of the input node included in the configuration file for at least one input node among the plurality of input nodes;

The input picture sending module is configured to send the input picture to the algorithm running node associated with the input node, so that the algorithm running node associated with the input node processes the input picture.

In a third aspect, an embodiment of the present disclosure provides an electronic device, and the electronic device includes:

one or more processors;

storage means for storing one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors are made to implement the image processing method according to any one of the first aspect above.

In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the image processing method described in any one of the above-mentioned first aspects is implemented.

In a fifth aspect, an embodiment of the present disclosure provides a computer program product, the computer program product includes a computer program or an instruction, and when the computer program or instruction is executed by a processor, the image processing described in any one of the above first aspects is realized method.

Embodiments of the present disclosure provide an image processing method, device, device, storage medium, and program product. The method includes: parsing a configuration file, and constructing an algorithm running time sequence diagram, wherein the algorithm running time sequence diagram includes a plurality of input nodes and an algorithm running node associated with the input node; for at least one input node in a plurality of input nodes, according to the configuration information of the input node included in the configuration file, the input picture corresponding to the input node is obtained; the input picture is sent to The algorithm running node associated with the input node, so that the algorithm running node associated with the input node processes the input picture. The embodiment of the present disclosure solves the problem of a single input source in the image algorithm by expanding and configuring the algorithm protocol, and designs a multi-input source configuration protocol for the algorithm system, which improves the operation speed and efficiency of related algorithms.

Description of drawings

The above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

FIG. 1 is a flowchart of an image processing method in an embodiment of the present disclosure;

FIG. 2 is a timing diagram of a single-input algorithm running in an embodiment of the present disclosure;

FIG. 3 is a timing diagram of a double-input algorithm running in an embodiment of the present disclosure;

FIG. 4 is a timing diagram of another double-input algorithm in an embodiment of the present disclosure;

Fig. 5 is a sequence diagram of running a multi-input algorithm in an embodiment of the present disclosure;

FIG. 6 is a schematic structural diagram of a configuration management device in an embodiment of the present disclosure;

FIG. 7 is a schematic structural diagram of an electronic device in an embodiment of the present disclosure.

Detailed ways

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein; A more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for exemplary purposes only, and are not intended to limit the protection scope of the present disclosure.

It should be understood that the various steps described in the method implementations of the present disclosure may be executed in different orders, and/or executed in parallel. Additionally, method embodiments may include additional steps and/or omit performing illustrated steps. The scope of the present disclosure is not limited in this respect.

As used herein, the term "comprise" and its variations are open-ended, ie "including but not limited to". The term "based on" is "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one further embodiment"; the term "some embodiments" means "at least some embodiments." Relevant definitions of other terms will be given in the description below.

It should be noted that concepts such as "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the sequence of functions performed by these devices, modules or units or interdependence.

It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative and not restrictive, and those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as "one or more" multiple".

The names of messages or information exchanged between multiple devices in the embodiments of the present disclosure are used for illustrative purposes only, and are not used to limit the scope of these messages or information.

The image processing method proposed in the embodiment of the present application will be described in detail below with reference to the accompanying drawings.

Fig. 1 is a flow chart of a picture processing method in an embodiment of the present disclosure. This embodiment is applicable to the situation where an algorithm is used to process a picture. The method can be executed by a picture processing device, and the configuration management device can use software and/or or hardware, the configuration management device can be configured in electronic equipment.

For example: the electronic equipment may be a mobile terminal, a fixed terminal or a portable terminal, such as a mobile handset, a station, a unit, a device, a multimedia computer, a multimedia tablet, an Internet node, a communicator, a desktop computer, a laptop computer, a notebook computer, Netbook Computers, Tablet Computers, Personal Communication System (PCS) Devices, Personal Navigation Devices, Personal Digital Assistants (PDAs), Audio/Video Players, Digital Still/Video Cameras, Pointing Devices, Television Receivers, Radio Broadcast Receivers, Electronic Books devices, gaming devices, or any combination thereof, including accessories and peripherals for such devices, or any combination thereof.

For another example: the electronic device may be a server, wherein the server may be a physical server or a cloud server, and the server may be a server or a server cluster.

As shown in Figure 1, the image processing method provided by the embodiment of the present disclosure mainly includes the following steps:

S101. Parse the configuration file, and build an algorithm running sequence diagram, wherein the algorithm running sequence diagram includes a plurality of input nodes and algorithm running nodes associated with the input nodes.

Existing short video image processing algorithms are based on the algorithm results generated by running calculations on an input image, and short video algorithm systems are often designed around a single input source. As shown in Figure 2, the original algorithm running sequence diagram, this type of algorithm configuration only supports a single input image. The camera frame 21 is the input picture, and the input picture is processed through the algorithm system input node blit_022 according to the pre-configured algorithm, such as face algorithm node face_023, background segmentation algorithm node matting_024 background segmentation algorithm node and expression GAN (Generative Adversarial Network ) algorithm node idream_025.

However, with the continuous increase of algorithm calculations and the iterative update of algorithm capabilities, some short video algorithms need to support multiple images as input, such as interactive map-matching algorithm, ColorMapping algorithm, or some special effects props require algorithms to run based on camera video frames , the user-defined image runs another part of the algorithm, which requires multiple input sources, so the original algorithm configuration can no longer meet the requirements. The embodiment of the present disclosure proposes a multi-input algorithm system based on an algorithm running sequence diagram structure, which can enhance the original algorithm system and realize multi-channel input and algorithm parallel processing.

Wherein, the configuration file can be understood as the configuration information of the algorithm, and links the graphics processing unit (Graphics Processing Unit, GPU) data with the image processing algorithm through the code language, and the configuration file is used to process the relationship between the two through the computer language such as code. The inter-communication is to transmit the GPU data to the relevant algorithm for processing according to the preset. The algorithm running sequence diagram is the operation relationship between the GPU data and the relevant algorithm through the representation of the directed graph.

Wherein, the input node can be understood as a node in the algorithm running sequence diagram for receiving input pictures. Wherein, the input picture may include camera frames in the camera stream, and may also include static picture textures. The algorithm running sequence diagram provided in this embodiment includes at least two input nodes. Optionally, two input nodes are included in the algorithm running sequence diagram, one of which is used to receive camera frames in the camera stream, and the other input node is used for static image textures, where static image textures can be uploaded by users The image texture in the photo album, or the image texture captured in the camera stream that needs to be processed separately. It should be noted that the input image received by the input node can be switched based on the configuration or the script system. For example, the input node receiving the camera frame in the camera stream can receive the static image texture, and the input node receiving the static image texture can also receive the Camera frames in the camera stream.

It should be noted that, in this embodiment, only the number of input nodes is described, not limited.

Wherein, the algorithm running node refers to a node that has direct or indirect connection with the input node and executes preset algorithmic logic. For example: the face algorithm node is used to implement the face recognition detection algorithm, and the expression GAN algorithm is used to implement the facial expression recognition algorithm.

In a possible implementation, the configuration file also includes the definition of each node and the dependencies between each node, parsing the configuration file, and constructing an algorithm running sequence diagram, including: based on the definition of each node in the configuration file and each Dependency relationship between nodes, build algorithm running sequence diagram.

Specifically, all node information needs to be defined in the configuration file. For example, "nodes" defines the algorithm node, and the configuration parameters of the node can be defined. The "intParam" algorithm defines the int type parameter, that is, the integer type parameter, and the "floatParam" algorithm defines The float type parameter is a floating point type parameter, and the string type parameter defined by the "stringParam" algorithm is a reference type parameter. The configuration file includes dependencies between nodes, such as "links" to define the connection dependencies of nodes. Dependencies can also be understood as the sequence relationship between two nodes. For example, B can only be executed after node A is executed, that is B depends on A. It should be noted that the definition types of the above nodes are only exemplary descriptions rather than limitations.

In this embodiment, the configuration file is used to construct the algorithm running sequence diagram. Since the configuration file is easy to modify, the algorithm running sequence diagram can be conveniently modified according to different application scenarios.

S102. For at least one input node among the plurality of input nodes, acquire an input picture corresponding to the input node according to configuration information of the input node included in the configuration file.

Specifically, the configuration file defines dependencies between input nodes and related algorithms, and the input nodes obtain input images according to their corresponding configuration information. For example, input node 1 corresponds to algorithms related to camera frames, such as background segmentation algorithms, and input node 2 corresponds to algorithms for user-defined images, such as face algorithms. When the input is camera frame data, input node 1 to obtain the camera frame, and when the input is image texture data, input node 2 to obtain the image texture.

In a possible implementation, the configuration information of the input node includes: the input channel corresponding to the input node; obtaining the corresponding input picture according to the configuration information of the input node included in the configuration file includes: using the input channel corresponding to the input node The input channel obtains the input image corresponding to the input node.

Specifically, in order to support multiple input nodes, the embodiments of the present disclosure need to expand the existing algorithm system and the configuration information of the input nodes, and the configuration information of the input nodes can be realized by fixing corresponding interface channels. For example, the key value corresponding to the blit_1 node is data_1, and it is necessary to consume data_1 input image data, which can be realized through the input channel 1, and the corresponding code is "input_channel=1", and the input image is transmitted to the node blit_1 through the channel 1, so as to carry out the node blit_1 related algorithms.

In this embodiment, the input picture corresponding to the input node is determined through the input channel, so that the input picture can be accurately input to its corresponding input node.

In a possible implementation, the configuration information of the input node includes: the parameter type corresponding to the input node; obtaining the corresponding input picture according to the configuration information of the input node included in the configuration file includes: The parameter type gets the input image corresponding to the input node.

Specifically, the input node obtains the corresponding input image data through the parameter type of the data. For example, the key value corresponding to the blit_1 node is src_data_1, and it is necessary to consume src_data_1 input image data, which can be realized through the parameter type src of the data, and the corresponding code is "input_src=src_data_1", and the input image is transmitted to the node blit_1 through the parameter type, so that the node The related algorithm of blit_1.

In this embodiment, the input picture corresponding to the input node is determined through the parameter type, so that the input picture can be accurately input to its corresponding input node.

It should be noted that, in the embodiment of the present disclosure, the manner in which the input node obtains the input picture data is only for illustration, and no specific limitation is made.

S103. Send the input picture to an algorithm running node associated with the input node, so that the algorithm running node associated with the input node processes the input picture.

Among them, the algorithm is mainly executed by the central processing unit CPU (Central Processing Unit, CPU), such as the algorithm mainly for the key point position of the face of the video frame, the neural network algorithm based on "deep learning", etc., the embodiment of the present disclosure is specific to the algorithm Not specifically limited.

In a possible implementation, the algorithm running node associated with the input node processes the input image, including: when each algorithm running node is only associated with one input node, the algorithm running node associated with the input node only The input image corresponding to the input node associated with it is processed.

Specifically, the algorithm is only associated with one input node, as shown in Figure 3, the background segmentation algorithm matting_0 node 36 is only associated with the input blit_0 node 1, and has no relationship with the input blit_1 node 2, even if two input nodes need to be face algorithm, but there are two face algorithm face_0 nodes 35 and face_1 nodes 38 running respectively.

Specifically, as shown in Figure 3, the input blit_0 node 33 is used to receive the camera frame 31 in the camera stream, the input blit_1 node 34 is the user-defined uploaded image texture 32, and the camera frames input through the blit_0 node need to be input into the face algorithm respectively The face_0 node 35 and the background segmentation algorithm matting_0 node 36, the image texture input through the blit_1 node needs to be input to the face algorithm face_1 node 38 and the expression GAN algorithm idream_0 node 37, and the face algorithm face_1 node 38 after the image texture processing is completed and input to Expression GAN algorithm idream_0 node 37. After the algorithm system is executed, the algorithm result is handed over to the rendering system for post-processing.

For example, in the mother’s day expression GAN props gameplay on the short video platform, the video frame data needs to run the background segmentation algorithm, and the user-defined uploaded pictures need to run the face and expression GAN algorithm. You can configure the input first through the image configuration file. The first input node blit_0 is connected to the background segmentation algorithm, and the second input node blit_1 is connected to the face and expression GAN algorithm.

In another example, the interactive matting algorithm in the short video platform needs to input video frames and a mask image, so the first input node blit_0 and the second input node blit_1 can be configured with this image configuration file. The interactive matting algorithm nodes are connected, only blit_0 processes the video frame, and blit_1 processes the mask image.

In this embodiment, the algorithm running node only processes the input image received by one input node, which reduces the difficulty of writing configuration files.

In a possible implementation, the algorithm running node associated with the input node processes the input image, including: when the same algorithm running node is associated with at least two input nodes, the algorithm running node processes at least two input nodes Nodes are associated with input images for processing.

Specifically, the same algorithm is associated with multiple input nodes. As shown in FIG. 4 , the colormapping algorithm colormapping_0 node 47 is associated with both the input blit_0 node 43 and the input blit_1 node 44. In this application scenario, the colormapping algorithm colormapping_0 node 47 needs two input pictures, which are the camera frame picture and the reference picture texture, so as to calculate the final color effect.

Specifically, as shown in Figure 4, the input blit_0 node 43 is used to receive the camera frame 41 in the camera stream, the input blit_1 node 44 is the user-defined uploaded image texture 42, and the camera frames input through the blit_0 node need to be input into the face algorithm respectively The face_0 node 45 and the background segmentation algorithm matting_0 node 46, the image texture input through the blit_1 node 44 needs the color mapping algorithm colormapping_0 node 47, and at the same time, the camera frame input through the blit_0 node also needs to input the color mapping algorithm colormapping_0 node 47, that is, the color mapping algorithm The colormapping_0 node 47 needs two input pictures, namely the camera frame picture and the reference picture texture, so as to calculate the final color effect. After the algorithm system is executed, the algorithm result is handed over to the rendering system for post-processing.

In the embodiment of the present disclosure, the input node 1 and the input node 2 are not specifically limited. For example, blit_0 can process image data uploaded by users, and blit_1 can also process video frame data.

In this embodiment, the input picture received by the input node associated with the algorithm running node increases the function of the algorithm running node and simplifies the algorithm running sequence diagram.

The design of the algorithm system provided by the embodiment of the present disclosure is not limited to only supporting two inputs of blit_0 and blit_1, but can be expanded arbitrarily, supporting 3 or more, all of which can be realized through a configuration file or a script system. As shown in Figure 5, 512 inputs any N input pictures such as picture 1, inputs blit_0 node 521 to receive camera frame 511, inputs blit_1 node 522 to receive input picture 1, ..., inputs blit_N node 52N to receive input picture N. Then input their respective associated algorithm running nodes for algorithm processing. For example: input the camera frame 511 received by the blit_0 node 521 into the algA_0 node 531 and algB_0 node 532 respectively, input the input image 1 received by the blit_1 node 522 into the algC_0 node 533, input the input image N received by the blit_N node 52N into the algN_0 node 53N .

In a possible implementation manner, the picture processing method further includes: sending the picture to be processed to the picture database through an application program interface or a script; acquiring the corresponding input picture according to the configuration information of the input node, including: according to the According to the configuration information of the input node, the corresponding input picture is acquired from the picture database.

Specifically, an application programming interface API (Application Programming Interface, API) is a predefined interface, such as a function, an http interface, etc., or refers to a contract for connecting different components of a software system. A script file (Script) refers to a collection of commands such as bind and alias, which is stored as an independent file and then executed when needed for convenience. In the embodiments of the present disclosure, camera frames, pictures uploaded by users or other defined pictures are sent to the picture database through API or Script, and the subsequent processing flow will not be repeated.

In this embodiment, the input picture is stored in the input picture database, and the multi-input node of the algorithm system can go to the picture database to obtain the corresponding input picture according to the parameter configuration of the node itself.

FIG. 6 is a schematic structural diagram of a picture processing device in an embodiment of the present disclosure. This embodiment is applicable to the case of performing algorithmic processing on a picture. The picture processing device can be implemented by software and/or hardware. The picture processing The device can be configured in electronic equipment.

As shown in FIG. 6 , the picture processing device provided by the embodiment of the present disclosure mainly includes a sequence diagram construction module 61 , an input picture acquisition module 62 and an input picture sending module 63 .

Wherein, the sequence diagram construction module 61 is used to analyze the configuration file and construct the algorithm operation sequence diagram, wherein the algorithm operation sequence diagram includes a plurality of input nodes and algorithm operation nodes associated with the input nodes;

The input picture obtaining module 62 is used for at least one input node in a plurality of input nodes, according to the configuration information of the input node included in the configuration file, to obtain the input picture corresponding to the input node;

The input picture sending module 63 is configured to send the input picture to the algorithm running node associated with the input node, so that the algorithm running node associated with the input node processes the input picture.

An embodiment of the present disclosure provides an image processing device for performing the following process: parsing a configuration file and constructing an algorithm running sequence diagram, wherein the algorithm running sequence diagram includes a plurality of input nodes and algorithms associated with the input nodes Run the node; for at least one input node among the plurality of input nodes, obtain an input image corresponding to the input node according to the configuration information of the input node included in the configuration file; send the input image to an algorithm associated with the input node to run node, so that the algorithm running node associated with the input node processes the input picture.

In a possible implementation manner, the configuration information of the input node includes: an input interface corresponding to the input node; an input picture acquisition module 62, specifically configured to acquire the input picture corresponding to the input node through the input interface corresponding to the input node.

In a possible implementation manner, the configuration information of the input node includes: a parameter type corresponding to the input node; an input picture acquisition module 62, specifically configured to acquire an input picture corresponding to the input node based on the parameter type corresponding to the input node.

In a possible implementation manner, the timing diagram construction module 61 is specifically configured to construct an algorithm running timing diagram based on the definition of each node in the configuration file and the dependencies between each node.

In a possible implementation, the algorithm running node associated with the input node processes the input image, including: when each algorithm running node is only associated with one input node, the algorithm running node associated with the input node only The input image corresponding to the input node associated with it is processed.

In a possible implementation, the algorithm running node associated with the input node processes the input image, including: when the same algorithm running node is associated with at least two input nodes, the algorithm running node processes at least two input nodes Nodes are associated with input images for processing.

In a possible implementation, the device further includes: a picture-to-be-processed sending module, configured to send the picture to be processed to the picture database through an application program interface or a script; an input picture acquisition module 62, also used to The configuration information of the input node acquires the corresponding input picture from the picture database.

The image processing device provided by the embodiment of the present disclosure can execute the steps performed by the image processing method provided by the embodiment of the present disclosure, and the specific execution steps and beneficial effects will not be repeated here.

FIG. 7 is a schematic structural diagram of an electronic device in an embodiment of the present disclosure. Referring specifically to FIG. 7 , it shows a schematic structural diagram of an electronic device 700 suitable for implementing an embodiment of the present disclosure. The electronic device 700 in the embodiment of the present disclosure may include, but not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), vehicle-mounted terminals ( Mobile terminals such as car navigation terminals), wearable terminal devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, etc. The terminal device shown in FIG. 7 is only an example, and should not limit the functions and scope of use of this embodiment of the present disclosure.

As shown in FIG. 7 , an electronic device 700 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) The program in the memory (RAM) 703 executes various appropriate actions and processes to realize the picture rendering method according to the embodiment of the present disclosure. In the RAM 703, various programs and data necessary for the operation of the terminal device 700 are also stored. The processing device 701 , ROM 702 , and RAM 703 are connected to each other through a bus 704 . An input/output (I/O) interface 705 is also connected to the bus 704 .

Typically, the following devices can be connected to the I/O interface 705: input devices 706 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speaker, vibration an output device 707 such as a computer; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709. The communication means 709 may allow the terminal device 700 to perform wireless or wired communication with other devices to exchange data. While FIG. 7 shows a terminal device 700 having various means, it should be understood that implementing or possessing all of the illustrated means is not a requirement. More or fewer means may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program includes program code for executing the method shown in the flow chart, thereby realizing the above The page jump method described above. In such an embodiment, the computer program may be downloaded and installed from a network via communication means 709 , or from storage means 708 , or from ROM 702 . When the computer program is executed by the processing device 701, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

In some embodiments, the client and the server can communicate using any currently known or future-developed network protocols such as HTTP (HyperText Transfer Protocol, Hypertext Transfer Protocol), and can communicate with digital data in any form or medium (eg, communication network) interconnections. Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network of.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.

The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the terminal device, the terminal device: parses the configuration file, constructs an algorithm running sequence diagram, wherein the algorithm running sequence diagram Including a plurality of input nodes and an algorithm running node associated with the input nodes; for at least one input node in the plurality of input nodes, according to the configuration information of the input node included in the configuration file, the input image corresponding to the input node is obtained; The input picture is sent to the algorithm running node associated with the input node, so that the algorithm running node associated with the input node processes the input picture.

Optionally, when the above one or more programs are executed by the terminal device, the terminal device may also perform other steps described in the foregoing embodiments.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, or combinations thereof, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and Includes conventional procedural programming languages - such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.

The units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. Wherein, the name of a unit does not constitute a limitation of the unit itself under certain circumstances.

The functions described herein above may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), System on Chips (SOCs), Complex Programmable Logical device (CPLD) and so on.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, the present disclosure provides an image processing method, including: parsing a configuration file, and constructing an algorithm running sequence graph, wherein the algorithm running sequence graph includes a plurality of input nodes and the The algorithm operation node associated with the input node; for at least one input node among the plurality of input nodes, according to the configuration information of the input node included in the configuration file, the input picture corresponding to the input node is obtained; the input picture is sent to the The algorithm running node associated with the node enables the algorithm running node associated with the input node to process the input picture.

According to one or more embodiments of the present disclosure, the present disclosure provides a picture processing method, the configuration information of the input node includes: the input interface corresponding to the input node; according to the configuration information of the input node included in the configuration file, the corresponding The input picture includes: obtaining the input picture corresponding to the input node through the input interface corresponding to the input node.

According to one or more embodiments of the present disclosure, the present disclosure provides an image processing method, the configuration information of the input node includes: the parameter type corresponding to the input node; according to the configuration information of the input node included in the configuration file, the corresponding The input picture includes: acquiring the input picture corresponding to the input node based on the parameter type corresponding to the input node.

According to one or more embodiments of the present disclosure, the present disclosure provides an image processing method, the configuration file also includes the definition of each node and the dependencies between each node, parses the configuration file, and constructs an algorithm running sequence diagram , including: based on the definition of each node in the configuration file and the dependencies between each node, construct an algorithm running sequence diagram.

According to one or more embodiments of the present disclosure, the present disclosure provides a picture processing method, the algorithm running node associated with the input node processes the input picture, including: when each algorithm running node only communicates with one When the input node is associated, the algorithm running node associated with the input node only processes the input image corresponding to the associated input node.

According to one or more embodiments of the present disclosure, the present disclosure provides a picture processing method, wherein the algorithm running node associated with the input node processes the input picture, including: when the same algorithm running node and at least two When two input nodes are associated, the algorithm runs the node to process at least two input node-associated input images.

According to one or more embodiments of the present disclosure, the present disclosure provides a picture processing method further comprising: sending the picture to be processed to the picture database through an application program interface or a script; obtaining the corresponding Inputting a picture includes: acquiring a corresponding input picture from the picture database according to the configuration information of the input node.

According to one or more embodiments of the present disclosure, the present disclosure provides an image processing device, including: parsing a configuration file, and constructing an algorithm running sequence graph, wherein the algorithm running sequence graph includes a plurality of input nodes and the The algorithm operation node associated with the input node; for at least one input node among the plurality of input nodes, according to the configuration information of the input node included in the configuration file, the input picture corresponding to the input node is obtained; the input picture is sent to the The algorithm running node associated with the node enables the algorithm running node associated with the input node to process the input picture.

According to one or more embodiments of the present disclosure, the present disclosure provides a picture processing device, the configuration information of the input node includes: the input interface corresponding to the input node; the input picture acquisition module 62, specifically for including: through the The input interface corresponding to the above input node obtains the input image corresponding to the input node.

According to one or more embodiments of the present disclosure, the present disclosure provides an image processing device, the configuration information of the input node includes: the parameter type corresponding to the input node; an input image acquisition module, specifically configured to The corresponding parameter type gets the input image corresponding to the input node.

According to one or more embodiments of the present disclosure, the present disclosure provides an image processing device, the configuration file also includes the definition of each node and the dependencies between each node, parses the configuration file, and constructs an algorithm running sequence diagram , including: based on the definition of each node in the configuration file and the dependencies between each node, construct an algorithm running sequence diagram.

According to one or more embodiments of the present disclosure, the present disclosure provides an image processing device, wherein the timing diagram construction module is specifically used for when each algorithm running node is only associated with one input node, the associated input node The algorithm running node only processes the input image corresponding to the input node associated with it.

According to one or more embodiments of the present disclosure, the present disclosure provides a picture processing device, the algorithm running node associated with the input node processes the input picture, including: when the same algorithm running node and at least two When two input nodes are associated, the algorithm runs the node to process at least two input node-associated input images.

According to one or more embodiments of the present disclosure, the present disclosure provides an image processing device, and the device further includes: a picture-to-be-processed sending module, configured to send the picture to be processed to the picture database through an application program interface or a script The input picture obtaining module is further configured to obtain the corresponding input picture from the picture database according to the configuration information of the input node.

According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device, including:

one or more processors;

memory for storing one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors are made to implement any one of the configuration management methods provided in the present disclosure.

According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the image processing described in any one provided by the present disclosure is realized. method.

An embodiment of the present disclosure further provides a computer program product, where the computer program product includes a computer program or an instruction, and when the computer program or instruction is executed by a processor, the above-mentioned image processing method is realized.

The above description is only a preferred embodiment of the present disclosure and an illustration of the applied technical principles. Those skilled in the art should understand that the disclosure scope involved in this disclosure is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, but also covers the technical solutions formed by the above-mentioned technical features or Other technical solutions formed by any combination of equivalent features. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

In addition, while operations are depicted in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or performed in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while the above discussion contains several specific implementation details, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims (8)

1. A picture processing method, the method comprising:

analyzing a configuration file, and constructing an algorithm operation time sequence diagram, wherein the algorithm operation time sequence diagram comprises a plurality of input nodes and algorithm operation nodes associated with the input nodes;

aiming at least one input node in a plurality of input nodes, acquiring an input picture corresponding to the input node according to configuration information of the input node included in the configuration file; the configuration information of the input node includes: input channels corresponding to the input nodes; acquiring an input picture corresponding to the input node according to configuration information of the input node included in the configuration file, including: acquiring an input picture corresponding to the input node through an input channel corresponding to the input node; alternatively, the configuration information of the input node includes: inputting the parameter types corresponding to the nodes; acquiring an input picture corresponding to the input node according to configuration information of the input node included in the configuration file, including: acquiring an input picture corresponding to the input node based on the parameter type corresponding to the input node;

And sending the input picture to the algorithm running node associated with the input node so that the algorithm running node associated with the input node processes the input picture.

2. The method of claim 1, wherein the configuration file further includes definitions of each node and dependencies between each node,

analyzing the configuration file, constructing an algorithm running time sequence diagram, and comprising the following steps:

and constructing an algorithm running time sequence diagram based on the definition of each node and the dependency relationship among each node in the configuration file.

3. The method of claim 1, wherein an algorithm running node associated with an input node processes the input picture, comprising:

when each algorithm running node is associated with only one input node, the algorithm running node associated with the input node only processes the input picture corresponding to the input node associated with the algorithm running node.

4. The method of claim 1, wherein an algorithm running node associated with an input node processes the input picture, comprising:

when the same algorithm running node is associated with at least two input nodes, the algorithm running node processes at least two input node associated input pictures.

5. The method according to claim 1, wherein the method further comprises:

transmitting the picture to be processed to a picture database through an application program interface or a script mode;

obtaining a corresponding input picture according to the configuration information of the input node, including:

and acquiring a corresponding input picture from the picture database according to the configuration information of the input node.

6. A picture processing apparatus, the apparatus comprising:

the system comprises a timing diagram construction module, a control module and a control module, wherein the timing diagram construction module is used for analyzing a configuration file and constructing an algorithm operation timing diagram, and the algorithm operation timing diagram comprises a plurality of input nodes and algorithm operation nodes associated with the input nodes;

the input picture acquisition module is used for acquiring an input picture corresponding to at least one input node in a plurality of input nodes according to configuration information of the input nodes included in the configuration file; wherein the configuration information of the input node includes: input channels corresponding to the input nodes; acquiring an input picture corresponding to the input node according to configuration information of the input node included in the configuration file, including: acquiring an input picture corresponding to the input node through an input channel corresponding to the input node; alternatively, the configuration information of the input node includes: inputting the parameter types corresponding to the nodes; acquiring an input picture corresponding to the input node according to configuration information of the input node included in the configuration file, including: acquiring an input picture corresponding to the input node based on the parameter type corresponding to the input node;

And the input picture sending module is used for sending the input picture to an algorithm operation node associated with the input node so as to enable the algorithm operation node associated with the input node to process the input picture.

7. An electronic device, the electronic device comprising:

one or more processors;

a storage means for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-5.

8. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-5.