Panoramic video fused video image quality optimization method and system

Abstract

The invention discloses an image quality optimization method and system for a panoramic video fused video, and relates to the technical field of video data processing, and the method comprises the steps: carrying out the integration of a plurality of video image frame data sets based on video image frame coding information, performing image quality evaluation on the integrated video sequence image frame data set through a video image quality evaluation index set to obtain a video sequence image frame image quality evaluation parameter set; and performing mapping processing on a video sequence image frame data set based on the video sequence image frame image quality evaluation parameter set by using video image quality optimization dual channels, and further performing panoramic video enhancement fusion on the processed video sequence image quality optimization image frame data set according to video image frame coding information. And obtaining the target panoramic optimization fusion video. The targeted image quality optimization of the panoramic video is realized through the video image quality optimization dual-channel, the image quality definition and optimization processing efficiency of the panoramic fusion video are improved, and the panoramic video monitoring effect is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of video data processing, and in particular to a method and system for optimizing the image quality of panoramic video fusion videos. Background Art

[0002] With the rapid development of digital media and virtual reality technology, panoramic video has become an important form of video surveillance. Panoramic video fusion technology can perform global real-time monitoring of large scenes and quickly trace back historical events, greatly reducing the work efficiency of operation and maintenance personnel. However, during the panoramic video fusion process, due to differences in viewing angles, lighting, color, etc. between different cameras, the quality of the fused video often deteriorates. Therefore, how to optimize the quality of panoramic video fusion has become an urgent problem to be solved. Summary of the invention

[0003] The present application solves the technical problem in the prior art that panoramic video fusion leads to a decrease in video quality, thereby affecting the video surveillance effect, by providing a method and system for optimizing the image quality of panoramic video fusion videos. The application achieves the goal of achieving targeted image quality optimization of panoramic videos through dual channels of video quality optimization, improving the image quality clarity and optimization processing efficiency of panoramic fusion videos, thereby ensuring the technical effect of panoramic video surveillance effects.

[0004] In view of the above problems, the present invention provides a method and system for optimizing the image quality of panoramic video fusion video.

[0005] In a first aspect, the present application provides a method for optimizing the image quality of a panoramic video fusion video, the method comprising: obtaining video information collected by multiple cameras, extracting image frames from the video information collected by the multiple cameras respectively, and obtaining multiple video image frame data sets; indexing and encoding the multiple video image frame data sets according to the video surveillance scene to obtain video image frame encoding information, and integrating video images of the multiple video image frame data sets based on the video image frame encoding information to determine a video sequence image frame data set; obtaining a video quality evaluation index set, performing multi-dimensional image quality evaluation extraction on the video sequence image frame data set through the video quality evaluation index set, and obtaining a video sequence image frame quality evaluation parameter set; constructing a dual channel for video quality optimization, using the dual channel for video quality optimization to perform mapping and association processing on the video sequence image frame data set based on the video sequence image frame quality evaluation parameter set to determine a video sequence quality optimized image frame data set; performing panoramic video enhancement fusion on the video sequence quality optimized image frame data set according to the video image frame encoding information to obtain a target panoramic optimized fusion video.

[0006] On the other hand, the present application also provides a system for optimizing the image quality of panoramic video fusion video, the system comprising: an image frame extraction module, used to obtain video information collected by multiple cameras, and to extract image frames from the video information collected by the multiple cameras respectively, to obtain multiple video image frame data sets; a video image integration module, used to index and encode the multiple video image frame data sets according to the video surveillance scene, to obtain video image frame encoding information, and to perform video image integration on the multiple video image frame data sets based on the video image frame encoding information, to determine a video sequence image frame data set; and a multi-dimensional image quality evaluation module, used to obtain video image quality evaluation indicators. A set of video quality evaluation indicators is used to perform multi-dimensional quality evaluation and extraction on the video sequence image frame data set to obtain a video sequence image frame quality evaluation parameter set; a video quality optimization module is used to construct a dual-channel video quality optimization, and the dual-channel video quality optimization is used to perform mapping and association processing on the video sequence image frame data set based on the video sequence image frame quality evaluation parameter set to determine the video sequence quality optimized image frame data set; a panoramic video enhancement fusion module is used to perform panoramic video enhancement fusion on the video sequence quality optimized image frame data set according to the video image frame encoding information to obtain a target panoramic optimized fused video.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The method adopts the method of extracting image frames from video information collected by multiple cameras, indexing and encoding and integrating the extracted multiple video image frame data sets according to the video surveillance scene, determining the video sequence image frame data set, extracting the image quality of the video sequence image frame data set in multiple dimensions through the video image quality assessment index set, obtaining the video sequence image frame image quality assessment parameter set, mapping and associating the video sequence image frame data set based on the video sequence image frame image quality assessment parameter set using the video image quality optimization dual channel, determining the video sequence image quality optimization image frame data set, performing panoramic video enhancement fusion according to the video image frame coding information, and obtaining the technical solution of the target panoramic optimized fusion video. Thus, the method achieves the technical effect of realizing the targeted image quality optimization of the panoramic video through the video image quality optimization dual channel, improving the image quality clarity and optimization processing efficiency of the panoramic fusion video, and thus ensuring the panoramic video surveillance effect.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A flowchart of a method for optimizing the image quality of a panoramic video fusion video according to the present application; Figure 2 A schematic diagram of a process for constructing a dual-channel video quality optimization method in a panoramic video fusion video quality optimization method of the present application; Figure 3 This is a structural schematic diagram of a panoramic video fusion video quality optimization system for the present application.

[0010] Explanation of the reference numerals: image frame extraction module 11 , video image integration module 12 , image quality multi-dimensional evaluation module 13 , video quality optimization module 14 , panoramic video enhancement and fusion module 15 . DETAILED DESCRIPTION

[0011] The present application solves the technical problem in the prior art that panoramic video fusion leads to a decrease in video quality, thereby affecting the video surveillance effect, by providing a method and system for optimizing the image quality of panoramic video fusion videos. The application achieves the goal of achieving targeted image quality optimization of panoramic videos through dual channels of video quality optimization, improving the image quality clarity and optimization processing efficiency of panoramic fusion videos, thereby ensuring the technical effect of panoramic video surveillance effects.

[0012] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0013] The present application is described below in conjunction with the drawings in the present application.

[0014] Embodiment 1

[0015] like Figure 1 As shown, the present application provides a method for optimizing the image quality of a panoramic video fusion video, the method comprising: Step S1: acquiring video information collected by multiple cameras, respectively extracting image frames from the video information collected by the multiple cameras, and obtaining multiple video image frame data sets.

[0016] Specifically, in order to achieve targeted image quality optimization of panoramic fusion video, firstly, multiple camera-collected video information is obtained through multiple monitoring devices, and the multiple camera-collected video information is monitoring video information of multiple areas and multiple angles for monitoring and collecting monitoring scene areas. Image frames are extracted from the multiple camera-collected video information through video stream decoding, and each decoded frame image is saved as a picture file to obtain corresponding multiple video image frame data sets, providing a data basis for subsequent video quality optimization.

[0017] Step S2: index encoding the multiple video image frame data sets according to the video surveillance scene to obtain video image frame encoding information, and perform video image integration on the multiple video image frame data sets based on the video image frame encoding information to determine a video sequence image frame data set.

[0018] Furthermore, the step of obtaining the video image frame encoding information also includes: Acquire regional distribution information of the video surveillance scene, use three-dimensional modeling technology to perform stereo modeling on the regional distribution information, and construct a three-dimensional space model of the scene; perform regional labeling segmentation on the three-dimensional space model of the scene to determine a set of labeled regions for the surveillance scene; determine image frame coding element information based on the set of labeled regions for the surveillance scene and the timestamp of the video image frame; design a coding system based on the coding element information to determine image frame coding rules, wherein the image frame coding rules include a coding order, a coding length, and a coding identifier; based on the image frame coding rules, index and encode the multiple video image frame data sets to obtain the video image frame coding information.

[0019] Specifically, the plurality of video image frame data sets are indexed and encoded according to the video surveillance scene, wherein the video surveillance scene is the surveillance scene area captured by the camera video, such as the power inspection area. To encode the video image frame, the regional distribution information of the video surveillance scene is first obtained, and the regional distribution information includes the spatial regional distribution position of the video surveillance scene and the distribution structure of the spatial region. The regional distribution information is stereoscopically modeled using three-dimensional modeling technology to construct a three-dimensional spatial model of the scene, and the three-dimensional spatial model of the scene is used to visually display the spatial distribution information of the video surveillance scene.

[0020] The three-dimensional spatial model of the scene is segmented into regions by labeling, and a set of labeled regions for monitoring scenes is determined. The set of labeled regions for monitoring scenes is the types of regions and spatial positions contained in the monitoring scene regions, such as type labels such as power production regions and power distribution regions. Based on the set of labeled regions for monitoring scenes and the timestamp of the video image frames, the image frame coding element information is determined. The image frame coding element information is the coding requirement type of each image frame data, including the labeling of the monitoring scene regions and the timestamp of the image frame. A coding system is designed based on the coding element information, and image frame coding rules are determined. The image frame coding rules are the basis for the coding content of the coding elements, including the coding order, i.e., the front-to-back order of the coding elements; the coding length, i.e., the information length of the coding elements; and the coding identifier, i.e., the identifier of the coding element, such as numbers, letters, etc.

[0021] Based on the image frame coding rules, each image frame in the multiple video image frame data sets is indexed and coded to obtain corresponding video image frame coding information, which is a unique information code for each image frame, so as to facilitate the subsequent rapid indexing of the image frame data. Based on the video image frame coding information, the multiple video image frame data sets are integrated with video images. According to the image frame coding, the image frame data can be arranged and integrated in the order of the acquisition area type and position, and the image frame timestamp from early to late, and the integrated video sequence image frame data set is determined. Rapid and reasonable coding of video image frames is achieved, and the image frame information processing efficiency is improved, thereby ensuring the subsequent panoramic video quality optimization processing efficiency.

[0022] Step S3: obtaining a set of video quality assessment indicators, performing multi-dimensional quality assessment extraction on the video sequence image frame data set using the video quality assessment indicator set, and obtaining a set of video sequence image frame quality assessment parameters.

[0023] Specifically, a video quality evaluation index set is formulated, and the video quality evaluation index set is an important index set for multi-dimensional evaluation of video quality, including resolution, color depth, color reproduction, contrast, etc. The video sequence image frame data set is subjected to multi-dimensional quality evaluation extraction through the video quality evaluation index set, and the quality evaluation result is mapped and extracted to obtain a corresponding video sequence image frame quality evaluation parameter set, and the video sequence image frame quality evaluation parameter set includes quality evaluation parameters of all video image frame data, providing a reference basis for subsequent image frame quality optimization.

[0024] Step S4: constructing a dual channel for video quality optimization, and utilizing the dual channel for video quality optimization to perform mapping and association processing on the video sequence image frame data set based on the video sequence image frame quality evaluation parameter set to determine a video sequence quality optimized image frame data set.

[0025] like Figure 2 As shown, further, the steps of constructing a dual-channel for video quality optimization in this application also include: A scene video image frame data set is acquired according to the video surveillance scene acquisition, and a background image frame data set is selected from the scene video image frame data set according to the background step length; data is selected from the scene video image frame data set according to the foreground step length to obtain a foreground image frame data set, wherein the foreground step length is smaller than the background step length; the background image frame data set and the foreground image frame data set are respectively used as training data for image quality optimization analysis training until a preset convergence condition is reached to obtain a background optimization processing channel and a foreground optimization processing channel; the background optimization processing channel and the foreground optimization processing channel are connected in parallel to construct the video image quality optimization dual channel.

[0026] Furthermore, the step of obtaining the foreground image frame data set in this application also includes: According to the scene video image frame data set, a standard monitoring scene grayscale image is determined; grayscale distribution recognition is performed on the standard monitoring scene grayscale image to obtain the monitoring scene grayscale interval, and the monitoring scene grayscale interval is used as the scene background feature; foreground target recognition is performed on the scene video image frame data set to obtain a foreground target set, and grayscale distribution recognition is performed on the foreground target set to obtain scene foreground features; based on the scene background features and the scene foreground features, an attention mechanism module is constructed, and data selection is performed on the scene video image frame data set according to the foreground step size through the attention mechanism module to obtain the foreground image frame data set.

[0027] Specifically, in order to improve the efficiency of image frame optimization processing, a dual channel for video quality optimization is constructed, and the dual channel for video quality optimization is used to simultaneously and efficiently optimize the image quality of the foreground data and background data of the image frame. The specific construction process is as follows: first, a scene video image frame data set is acquired according to the video surveillance scene acquisition, and the scene video image frame data set is the historical video image frame data of the video surveillance scene. The scene video image frame data set is image acquisition and selection is performed according to the background step length to obtain a corresponding background image frame data set, wherein the background step length is the extraction time interval of the image frame, and the image frame background is static background data, including scene buildings, etc., and the change is small. Therefore, the background step length is large, such as 10s to collect one frame. Then, the scene video image frame data set is image data selected according to the foreground step length to obtain a corresponding foreground image frame data set. The foreground of the image frame is dynamic motion target data, which changes greatly. Therefore, the foreground step length is smaller than the background step length, such as 5s to collect one frame.

[0028] The extraction process of foreground image frame data is as follows: first, according to the scene video image frame data set, determine the standard monitoring scene grayscale image, the standard monitoring scene grayscale image is the monitoring scene area grayscale image when there is no moving target, perform grayscale distribution recognition on the standard monitoring scene grayscale image, obtain the corresponding monitoring scene grayscale interval, and use the monitoring scene grayscale interval as the scene background feature. Perform foreground target recognition on the scene video image frame data set to obtain a foreground target set, the foreground target set is a set of moving targets in the monitoring scene, such as power personnel, etc. Perform grayscale distribution recognition on the foreground target set to obtain corresponding scene foreground features, the scene foreground features are grayscale distribution feature sets of foreground targets. Based on the scene background features and the scene foreground features, construct an attention mechanism module, the attention mechanism module is used to quickly identify and extract the image foreground area and image background area of ​​the video monitoring scene. Through the attention mechanism module, according to the foreground step length, perform image extraction and acquisition on the scene video image frame data set, and then select foreground data on the acquired image frame to obtain the corresponding foreground image frame data set after processing.

[0029] The background image frame data set and the foreground image frame data set are used as training data respectively, and the image quality parameters are evaluated by the video image quality evaluation index set, and then the image quality optimization analysis training is performed by the image quality evaluation parameters until the preset convergence condition is reached. The preset convergence condition can be that the model performance index is stable or the preset number of iterations is reached, and the trained background image quality optimization model and foreground image quality optimization model are obtained, and they are used as the background optimization processing channel and the foreground optimization processing channel. The background optimization processing channel and the foreground optimization processing channel are connected in parallel to construct a dual-channel for video image quality optimization, so as to simultaneously perform efficient parallel image quality optimization processing of the image frame background data and the image frame foreground data. The dual-channel for video image quality optimization is used to optimize the channel mapping association and step size extraction optimization processing of the background image frame data and the foreground image frame data of the video sequence image frame data set based on the video sequence image frame quality evaluation parameter set, and determine the video sequence image quality optimization image frame data set after the output video image frame quality optimization processing. Targeted and efficient image quality optimization of the dual-channel for video image quality optimization is achieved, thereby improving the image quality clarity and image frame optimization processing efficiency of the panoramic fusion video.

[0030] Step S5: performing panoramic video enhancement fusion on the video sequence quality optimized image frame data set according to the video image frame coding information to obtain a target panoramic optimized fused video.

[0031] Furthermore, the step of obtaining the target panoramic optimized fusion video also includes: The overlapping blending areas of the video sequence image quality optimized image frame data set are marked to obtain a video blending area set; weights are assigned to the video sequence image quality optimized image frame data set based on the video blending area set to determine sequence video fusion weight factor information; based on the sequence video fusion weight factor information and in accordance with the video image frame encoding information, panoramic video fusion is performed on the video sequence image quality optimized image frame data set to obtain the target panoramic optimized fused video.

[0032] Specifically, the video sequence quality optimization image frame data set is subjected to panoramic video enhancement fusion according to the video image frame encoding information, and an adaptive weighted fusion algorithm is used in the fusion process. First, the overlapping and blending areas in the video sequence quality optimization image frame data set are marked to obtain a corresponding video blending area set, which is an adjacent and overlapping area of ​​each collected video image frame. Based on the video blending area set, the video sequence quality optimization image frame data set is weighted, and the image frames with overlapping areas can be fused according to the amount of information contained in the image frames. The image frames with larger detail information have larger corresponding fusion weight factors, so as to determine the sequence video fusion weight factor information to retain more video details and color information. Based on the sequence video fusion weight factor information and the video image frame encoding information, the video sequence quality optimization image frame data set is subjected to panoramic video fusion to obtain a target panoramic optimized fusion video after image quality optimization. The image quality clarity and fusion efficiency of the panoramic fusion video are improved, and the video image frame fusion is ensured to have a richer amount of information, thereby ensuring the panoramic video monitoring effect.

[0033] Furthermore, the steps of obtaining the background optimization processing channel and the foreground optimization processing channel in this application also include: The background image frame data set and the foreground image frame data set are screened according to a preset video quality standard to obtain a high-quality image frame data set, wherein the high-quality image frame data set includes a background high-quality data set and a foreground high-quality data set; the high-quality image frame data set is subjected to image quality loss processing to obtain a low-quality image frame data set, and the low-quality image frame data set is subjected to image quality evaluation by using the video quality evaluation index set to obtain a low-quality image frame evaluation parameter set; the high-quality image frame data set and the low-quality image frame data set are subjected to mapping association analysis to determine an image frame quality sample data set; and the low-quality image frame evaluation parameter set and the image frame quality sample data set are subjected to image quality enhancement training optimization by using a convolutional neural network structure to obtain the background optimization processing channel and the foreground optimization processing channel.

[0034] Furthermore, the steps of obtaining the background optimization processing channel and the foreground optimization processing channel in this application also include: Performing an image quality generation cause and a low image quality level analysis on the low image quality image frame evaluation parameter set to determine low image quality generation cause parameters and low image quality level parameters; performing an image quality optimization program configuration on the image frame image quality sample data set based on the low image quality generation cause parameters and low image quality level parameters to obtain an image quality optimization program set; performing image quality enhancement training optimization on the image quality optimization program set and the image frame image quality sample data set using a convolutional neural network structure to obtain the background optimization processing channel and the foreground optimization processing channel.

[0035] Specifically, the background image frame data set and the foreground image frame data set are respectively used as training data for image quality optimization analysis training, and the specific process is: first, the background image frame data set and the foreground image frame data set are screened according to the preset video quality standard, wherein the preset video quality standard is the quality standard of the panoramic fusion video, which can be set according to the application requirements, and a high-quality image frame data set that meets the preset video quality standard is obtained, and the high-quality image frame data set includes a background high-quality data set and a foreground high-quality data set. The high-quality image frame data set is subjected to image quality loss processing, including image quality loss methods such as reducing the video image frame resolution, image frame compression, and adding noise, to obtain a low-quality image frame data set after loss processing. The low-quality image frame data set is subjected to image quality evaluation through the video quality evaluation index set to obtain a corresponding low-quality image frame evaluation parameter set. The high-quality image frame data set and the low-quality image frame data set are mapped and associated with each other to determine an image frame quality sample data set, wherein the image frame quality sample data set includes a high-quality image frame data set that meets a preset video quality standard and a corresponding low-quality image frame data set after loss processing.

[0036] The low-quality image frame evaluation parameter set and the image frame quality sample data set are optimized for image quality enhancement training using a convolutional neural network structure. First, the image quality generation cause and low quality level of the low-quality image frame evaluation parameter set are analyzed to determine the low-quality generation cause parameters, such as noise impact, information loss, etc.; low quality level parameters, the low quality severity level of the current image frame quality evaluation parameters. Based on the low-quality generation cause parameters and low-quality level parameters, the image frame quality sample data set is configured with an image quality optimization program, and the image quality optimization steps are analyzed according to the low-quality generation cause and its low-quality level. For example, the low-quality image quality affected by noise is configured with corresponding low-quality level filter parameters, and then filtered by a filter. The image quality optimization program set is obtained by integrating the processing steps of each low-quality image frame, and the image quality optimization program set is used to match the corresponding optimization processing steps according to each low-quality generation cause and low-quality level.

[0037] The image quality optimization program set and the image frame image quality sample data set are trained and optimized using a convolutional neural network structure. The image frame image quality sample data set is used as training data, and the image quality optimization program set is used as output identification data to perform image quality optimization processing training for video image frames until the preset convergence condition is reached. The trained background image quality optimization model and foreground image quality optimization model are obtained and used as the background optimization processing channel and foreground optimization processing channel. Efficient parallel image quality optimization processing of image frame background data and image frame foreground data is achieved, the image quality clarity of panoramic fusion video and the image frame optimization processing efficiency are improved, and the panoramic video monitoring effect is ensured.

[0038] In summary, the method for optimizing the image quality of panoramic video fusion video provided by this application has the following technical effects: The method adopts the method of extracting image frames from video information collected by multiple cameras, indexing and encoding and integrating the extracted multiple video image frame data sets according to the video surveillance scene, determining the video sequence image frame data set, extracting the image quality of the video sequence image frame data set in multiple dimensions through the video image quality assessment index set, obtaining the video sequence image frame image quality assessment parameter set, mapping and associating the video sequence image frame data set based on the video sequence image frame image quality assessment parameter set using the video image quality optimization dual channel, determining the video sequence image quality optimization image frame data set, performing panoramic video enhancement fusion according to the video image frame coding information, and obtaining the technical solution of the target panoramic optimized fusion video. Thus, the method achieves the technical effect of realizing the targeted image quality optimization of the panoramic video through the video image quality optimization dual channel, improving the image quality clarity and optimization processing efficiency of the panoramic fusion video, and thus ensuring the panoramic video surveillance effect.

[0039] Embodiment 2

[0040] Based on the same inventive concept as the method for optimizing the image quality of a panoramic video fusion video in the aforementioned embodiment, the present invention also provides a system for optimizing the image quality of a panoramic video fusion video, such as Figure 3 As shown, the system comprises: The image frame extraction module 11 is used to obtain video information collected by multiple cameras, and respectively extract image frames from the video information collected by the multiple cameras to obtain multiple video image frame data sets; the video image integration module 12 is used to index and encode the multiple video image frame data sets according to the video surveillance scene, obtain video image frame encoding information, and perform video image integration on the multiple video image frame data sets based on the video image frame encoding information to determine the video sequence image frame data set; the image quality multi-dimensional evaluation module 13 is used to obtain a video image quality evaluation index set, and evaluate the video quality through the video image quality evaluation index set. The video sequence image frame data set is subjected to multi-dimensional image quality evaluation extraction to obtain a video sequence image frame image quality evaluation parameter set; a video image quality optimization module 14 is used to construct a dual-channel for video image quality optimization, and utilizes the dual-channel for video image quality optimization to perform mapping and association processing on the video sequence image frame data set based on the video sequence image frame image quality evaluation parameter set to determine the video sequence image quality optimized image frame data set; a panoramic video enhancement fusion module 15 is used to perform panoramic video enhancement fusion on the video sequence image quality optimized image frame data set according to the video image frame encoding information to obtain a target panoramic optimized fused video.

[0041] Furthermore, the video image integration module 12 is also used for: Acquire regional distribution information of the video surveillance scene, use three-dimensional modeling technology to perform stereo modeling on the regional distribution information, and construct a three-dimensional space model of the scene; perform regional labeling segmentation on the three-dimensional space model of the scene to determine a set of labeled regions for the surveillance scene; determine image frame coding element information based on the set of labeled regions for the surveillance scene and the timestamp of the video image frame; design a coding system based on the coding element information to determine image frame coding rules, wherein the image frame coding rules include a coding order, a coding length, and a coding identifier; based on the image frame coding rules, index and encode the multiple video image frame data sets to obtain the video image frame coding information.

[0042] Furthermore, the video quality optimization module 14 is also used for: A scene video image frame data set is acquired according to the video surveillance scene acquisition, and a background image frame data set is selected from the scene video image frame data set according to the background step length; data is selected from the scene video image frame data set according to the foreground step length to obtain a foreground image frame data set, wherein the foreground step length is smaller than the background step length; the background image frame data set and the foreground image frame data set are respectively used as training data for image quality optimization analysis training until a preset convergence condition is reached to obtain a background optimization processing channel and a foreground optimization processing channel; the background optimization processing channel and the foreground optimization processing channel are connected in parallel to construct the video image quality optimization dual channel.

[0043] Furthermore, the video quality optimization module 14 is also used for: According to the scene video image frame data set, a standard monitoring scene grayscale image is determined; grayscale distribution recognition is performed on the standard monitoring scene grayscale image to obtain the monitoring scene grayscale interval, and the monitoring scene grayscale interval is used as the scene background feature; foreground target recognition is performed on the scene video image frame data set to obtain a foreground target set, and grayscale distribution recognition is performed on the foreground target set to obtain scene foreground features; based on the scene background features and the scene foreground features, an attention mechanism module is constructed, and data selection is performed on the scene video image frame data set according to the foreground step size through the attention mechanism module to obtain the foreground image frame data set.

[0044] Furthermore, the video quality optimization module 14 is also used for: The background image frame data set and the foreground image frame data set are screened according to a preset video quality standard to obtain a high-quality image frame data set, wherein the high-quality image frame data set includes a background high-quality data set and a foreground high-quality data set; the high-quality image frame data set is subjected to image quality loss processing to obtain a low-quality image frame data set, and the low-quality image frame data set is subjected to image quality evaluation by using the video quality evaluation index set to obtain a low-quality image frame evaluation parameter set; the high-quality image frame data set and the low-quality image frame data set are subjected to mapping association analysis to determine an image frame quality sample data set; and the low-quality image frame evaluation parameter set and the image frame quality sample data set are subjected to image quality enhancement training optimization by using a convolutional neural network structure to obtain the background optimization processing channel and the foreground optimization processing channel.

[0045] Furthermore, the video quality optimization module 14 is also used for: Performing an image quality generation cause and a low image quality level analysis on the low image quality image frame evaluation parameter set to determine low image quality generation cause parameters and low image quality level parameters; performing an image quality optimization program configuration on the image frame image quality sample data set based on the low image quality generation cause parameters and low image quality level parameters to obtain an image quality optimization program set; performing image quality enhancement training optimization on the image quality optimization program set and the image frame image quality sample data set using a convolutional neural network structure to obtain the background optimization processing channel and the foreground optimization processing channel.

[0046] Furthermore, the panoramic video enhancement fusion module 15 is also used for: The overlapping blending areas of the video sequence image quality optimized image frame data set are marked to obtain a video blending area set; weights are assigned to the video sequence image quality optimized image frame data set based on the video blending area set to determine sequence video fusion weight factor information; based on the sequence video fusion weight factor information and in accordance with the video image frame encoding information, panoramic video fusion is performed on the video sequence image quality optimized image frame data set to obtain the target panoramic optimized fused video.

[0047] The foregoing Figure 1 The various variations and specific examples of the method for optimizing the image quality of a panoramic video fusion video in Example 1 are also applicable to a system for optimizing the image quality of a panoramic video fusion video in this embodiment. Through the above detailed description of the method for optimizing the image quality of a panoramic video fusion video, those skilled in the art can clearly know the implementation method of the system for optimizing the image quality of a panoramic video fusion video in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0048] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for optimizing the image quality of panoramic video fusion video, characterized in that: The method comprises: Acquire video information collected by multiple cameras, extract image frames from the video information collected by the multiple cameras respectively, and obtain multiple video image frame data sets; Index encoding the multiple video image frame data sets according to the video surveillance scene to obtain video image frame encoding information, and perform video image integration on the multiple video image frame data sets based on the video image frame encoding information to determine a video sequence image frame data set; Acquire a set of video quality evaluation indicators, perform multi-dimensional quality evaluation extraction on the video sequence image frame data set using the video quality evaluation indicator set, and obtain a set of video sequence image frame quality evaluation parameters; Constructing a dual channel for video quality optimization, and using the dual channel for video quality optimization to perform mapping and association processing on the video sequence image frame data set based on the video sequence image frame quality evaluation parameter set to determine the video sequence quality optimized image frame data set; The video sequence quality optimized image frame data set is subjected to panoramic video enhancement fusion according to the video image frame coding information to obtain a target panoramic optimized fused video.

2. The method for optimizing the image quality of a panoramic video fusion video according to claim 1, characterized in that: The obtaining of video image frame coding information comprises: Acquire regional distribution information of the video surveillance scene, perform stereoscopic modeling on the regional distribution information using three-dimensional modeling technology, and construct a three-dimensional spatial model of the scene; Performing region labeling segmentation on the three-dimensional spatial model of the scene to determine a set of labeled regions of the monitoring scene; Determining image frame coding element information according to the monitoring scene labeled area set and the video image frame timestamp; Designing a coding system based on the coding element information to determine an image frame coding rule, wherein the image frame coding rule includes a coding order, a coding length, and a coding identifier; Based on the image frame coding rule, the multiple video image frame data sets are indexed and coded to obtain the video image frame coding information.

3. The method for optimizing the image quality of a panoramic video fusion video according to claim 1, characterized in that: The construction of the dual-channel video quality optimization includes: Acquire a scene video image frame data set according to the video surveillance scene acquisition, and select a background image frame data set from the scene video image frame data set according to the background step length; Selecting data from the scene video image frame data set according to the foreground step length to obtain a foreground image frame data set, wherein the foreground step length is smaller than the background step length; The background image frame data set and the foreground image frame data set are respectively used as training data for image quality optimization analysis training until a preset convergence condition is reached to obtain a background optimization processing channel and a foreground optimization processing channel; The background optimization processing channel and the foreground optimization processing channel are connected in parallel to construct the video quality optimization dual channel.

4. The method for optimizing the image quality of a panoramic video fusion video according to claim 3, characterized in that: The obtaining of a foreground image frame data set comprises: Determining a standard monitoring scene grayscale image according to the scene video image frame data set; Performing grayscale distribution recognition on the grayscale image of the standard monitoring scene to obtain a grayscale interval of the monitoring scene, and using the grayscale interval of the monitoring scene as a scene background feature; Performing foreground target recognition on the scene video image frame data set to obtain a foreground target set, and performing grayscale distribution recognition on the foreground target set to obtain scene foreground features; Based on the scene background features and the scene foreground features, an attention mechanism module is constructed, and the attention mechanism module is used to select data from the scene video image frame data set according to the foreground step size to obtain the foreground image frame data set.

5. The method for optimizing the image quality of a panoramic video fusion video according to claim 3, characterized in that: The obtaining of the background optimization processing channel and the foreground optimization processing channel comprises: Performing image frame screening on the background image frame data set and the foreground image frame data set according to a preset video quality standard to obtain a high-quality image frame data set, wherein the high-quality image frame data set includes a background high-quality data set and a foreground high-quality data set; Performing image quality loss processing on the high-quality image frame data set to obtain a low-quality image frame data set, and performing image quality evaluation on the low-quality image frame data set using the video quality evaluation index set to obtain a low-quality image frame evaluation parameter set; Performing mapping association analysis on the high-quality image frame data set and the low-quality image frame data set to determine an image frame quality sample data set; The low-quality image frame evaluation parameter set and the image frame quality sample data set are subjected to image quality enhancement training optimization using a convolutional neural network structure to obtain the background optimization processing channel and the foreground optimization processing channel.

6. The method for optimizing the image quality of a panoramic video fusion video according to claim 5, characterized in that: The obtaining of the background optimization processing channel and the foreground optimization processing channel comprises: Analyzing the image quality generation cause and the low image quality level of the low image quality frame evaluation parameter set to determine a low image quality generation cause parameter and a low image quality level parameter; Based on the low image quality generation reason parameter and the low image quality level parameter, performing image quality optimization program configuration on the image frame image quality sample data set to obtain an image quality optimization program set; The image quality optimization program set and the image frame image quality sample data set are subjected to image quality enhancement training optimization using a convolutional neural network structure to obtain the background optimization processing channel and the foreground optimization processing channel.

7. The method for optimizing the image quality of a panoramic video fusion video according to claim 1, characterized in that: The step of obtaining the target panoramic optimized fusion video includes: Marking the overlapping blending regions of the video sequence quality optimization image frame data set to obtain a video blending region set; Based on the video blending area set, weighting is performed on the video sequence quality optimized image frame data set to determine sequence video fusion weight factor information; Based on the sequence video fusion weight factor information and in accordance with the video image frame encoding information, the video sequence quality optimized image frame data set is subjected to panoramic video fusion to obtain the target panoramic optimized fused video.

8. A panoramic video fusion video quality optimization system, characterized in that: A method for optimizing the image quality of a panoramic video fusion video according to any one of claims 1 to 7, the system comprising: An image frame extraction module is used to obtain video information collected by multiple cameras, and respectively extract image frames from the video information collected by the multiple cameras to obtain multiple video image frame data sets; A video image integration module, configured to index and encode the plurality of video image frame data sets according to the video surveillance scene, obtain video image frame encoding information, and perform video image integration on the plurality of video image frame data sets based on the video image frame encoding information to determine a video sequence image frame data set; A multi-dimensional image quality evaluation module is used to obtain a set of video image quality evaluation indicators, and to perform multi-dimensional image quality evaluation extraction on the video sequence image frame data set through the video image quality evaluation indicator set to obtain a set of video sequence image frame quality evaluation parameters; A video quality optimization module, used for constructing a dual channel for video quality optimization, using the dual channel for video quality optimization to perform mapping and association processing on the video sequence image frame data set based on the video sequence image frame quality evaluation parameter set, and determining a video sequence quality optimized image frame data set; The panoramic video enhancement fusion module is used to perform panoramic video enhancement fusion on the video sequence quality optimized image frame data set according to the video image frame coding information to obtain a target panoramic optimized fused video.

Images