Projected image data analysis method, system, equipment and medium

By decomposing the video frame into multiple regions and calculating the average attribute value, combining the hollow convolution UNNET network and boundary detection technology, the problem of the inability to differentiate the image content in the existing technology is solved, and the accuracy and intelligence of the projection effect are improved Environmental control capability.

CN118972529AInactive Publication Date: 2024-11-15SHENZHEN WEPROTALK TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411006265.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing image data analysis methods cannot adjust the projection effect according to the image content, resulting in the projection effect being unsatisfactory, especially when processing complex images, it is difficult to achieve differentiated processing.

Method used

By decomposing the target video frame into multiple regions, obtaining the attribute value of each pixel point, calculating and packaging the average attribute value of each region, sending it to external devices for display control, and using technologies such as hollow convolutional UNNET network and boundary detection and other technologies Carry out automated and efficient image segmentation processing.

Benefits of technology

It improves the accuracy of data analysis and flexibility of projection effects, supports intelligent environment control, such as adjusting indoor lighting according to video content, and realizes automated and efficient video frame segmentation and data processing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118972529A_ABST
    Figure CN118972529A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of image processing and data analysis, in particular to a projected image data analysis method, system and device and a medium, and the method comprises the steps: decomposing a target video frame into a plurality of regions, obtaining the attribute value of each region pixel, and calculating the average attribute value of each region, and the data are packaged and sent for display control of external equipment, so that efficient image data analysis and projection control are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of image processing and data analysis, and in particular to a method, system, device and medium for analyzing projected image data. Background Art

[0002] With the development of science and technology, projection technology is increasingly widely used in various fields, such as home theater, business presentation, education and training, etc. During the projection process, accurate data analysis of the projected image in order to adjust the projection effect according to the image content and improve the user experience has become a hot topic in current research.

[0003] At present, the existing image data analysis methods usually process the entire image globally, without distinguishing different areas in the image, and cannot perform differentiated processing on different areas in the picture. This results in the inability to adjust the projection effect according to the image content when projecting complex images, making the projection effect less than ideal, so there is room for improvement. Summary of the invention

[0004] In order to improve the projection effect, the present application provides a projected image data analysis method, system, device and medium.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A method for analyzing projected image data, the method comprising: Decomposing a target video frame into N regions, wherein the target video frame is any frame of video in a set of video frames corresponding to the target video, and N is an integer greater than or equal to 2; Obtaining an attribute value of an attribute corresponding to each pixel in a target area, wherein the target area is any one of the N areas, and the attribute corresponding to each pixel includes at least one of transparency, a red component, a green component, and a blue component; Calculating an average attribute value of each of the N areas according to the attribute value of the attribute corresponding to each pixel point; Packing the average attribute value of each area in the N areas to obtain a packed array of each area in the N areas; The packed array of each area in the N areas is sent to an external device, so that after receiving the packed array, the external device parses the packed array and performs display control according to the parsed data.

[0006] By adopting the above technical solution, the video frame is analyzed and decomposed into N regions, and the value of N can be adjusted as needed to adapt to video frames of different resolutions and different analysis requirements. Obtaining the attribute value corresponding to each pixel in the target area and calculating the average attribute value of each area can reduce the impact of noise and outliers and improve the accuracy of data analysis. Packing the average attribute value of each area in the N areas to obtain a packed array of each area in the N areas, and sending the packed array of each area in the N areas to an external device can support intelligent environmental control systems, such as adjusting indoor lighting according to video content.

[0007] In a preferred example, the present application may be further configured as follows: decomposing the target video frame into N regions includes: Constructing a training data set, wherein the training data set includes a plurality of images and a segmentation result of each of the plurality of images; The initial segmentation model is constructed using the dilated convolutional UNET network; Training the initial segmentation model based on the training data set until a preset iteration termination condition is reached to obtain a target model; The target video frame is segmented according to the target model to obtain the N regions.

[0008] By adopting the above technical solution, the image segmentation technical solution based on the dilated convolutional UNET network is adopted, the initial segmentation model is trained based on the training data set until the preset iteration termination condition is reached to obtain the target model, and the target video frame is segmented according to the target model to obtain the N regions. Automated and efficient video frame segmentation processing is achieved, and accurate N region divisions are generated, which has the advantages of improving segmentation accuracy, enhancing model generalization ability, supporting real-time applications and improving computing efficiency.

[0009] In a preferred example, the present application may be further configured as follows: decomposing the target video frame into N regions includes: Performing boundary judgment on each pixel value in the target video frame to determine all boundary pixels in the target video frame; The matched boundary pixels among all the boundary pixels in the target video frame are divided into the same region to obtain the N regions.

[0010] By adopting the above technical solution, a method for image segmentation based on boundary detection is provided, which divides the region by identifying and matching the boundary pixels in the target video frame, thereby realizing automated and efficient image analysis. This method can accurately define the boundaries of the image, help improve the accuracy of segmentation, and enhance the logic of region division.

[0011] In a preferred example, the present application may be further configured as follows: decomposing the target video frame into N regions includes: Determining a characteristic of each pixel value in the target video frame; The pixels in the target video frame are classified according to the features of each pixel, and pixels of the same category are divided into the same region to obtain the N regions.

[0012] By adopting the above technical solution, a pixel feature-based image segmentation method is provided, which realizes region division by analyzing and classifying the features of each pixel in the target video frame. The advantage of this method is that it improves the accuracy and flexibility of image segmentation, making the result more consistent with the natural boundaries of the image content.

[0013] In a preferred example, the present application may be further configured as follows: summing the attribute values ​​of the attributes corresponding to each pixel point to obtain the sum value of the attributes corresponding to each pixel point; Determine the number of pixels contained in the target area; The average attribute value of each of the N areas is determined according to the sum value and the number of pixels.

[0014] By adopting the above technical solution, the average attribute value of each area in N areas is calculated according to the attribute value corresponding to each pixel point, including summing the attribute value of the attribute corresponding to each pixel point, determining the number of pixels contained in the target area, and determining the average attribute value according to the sum and the number of pixels, so as to accurately calculate the representative characteristics of the area.

[0015] In a preferred example, the present application may be further configured to: determine a set frame rate of the target video, and acquire a video frame of the target video based on the set frame rate; The acquired video frames of the target video are synchronously saved with the timestamps of the video frames of the target video to obtain the video frame set.

[0016] By adopting the above technical solution, a method for ensuring video frame acquisition and time synchronization is realized, which obtains video frames according to the set frame rate of the target video and saves these frames synchronously with their timestamps, thereby obtaining a time-ordered video frame set. This helps to improve the efficiency of video data processing and ensure the consistency and reliability of video frames in subsequent processing and analysis.

[0017] The second object of the invention is achieved by the following technical solutions: A projected image data analysis system, the projected image data analysis system comprising: A decomposition module, used to decompose a target video frame into N regions, wherein the target video frame is any frame of video in a set of video frames corresponding to the target video, and N is an integer greater than or equal to 2; an acquisition module, used to acquire an attribute value of an attribute corresponding to each pixel in a target area, wherein the target area is any one of the N areas, and the attribute corresponding to each pixel includes at least one of transparency, a red component, a green component, and a blue component; A calculation module, used for calculating an average attribute value of each of the N areas according to the attribute value of the attribute corresponding to each pixel point; A packing module, used for packing the average attribute value of each area in the N areas to obtain a packing array of each area in the N areas; The sending module is used to send the packed array of each area in the N areas to an external device, so that after the external device receives the packed array, it parses the packed array and performs display control according to the parsed data.

[0018] By adopting the above technical solution, the video frame is analyzed and decomposed into N regions, and the value of N can be adjusted as needed to adapt to video frames of different resolutions and different analysis requirements. Obtaining the attribute value corresponding to each pixel in the target area and calculating the average attribute value of each area can reduce the impact of noise and outliers and improve the accuracy of data analysis. Packing the average attribute value of each area in the N areas to obtain a packed array of each area in the N areas, and sending the packed array of each area in the N areas to an external device can support intelligent environmental control systems, such as adjusting indoor lighting according to video content.

[0019] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned projection image data analysis method when executing the computer program.

[0020] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned projection image data analysis method are implemented.

[0021] In summary, the present application includes at least one of the following beneficial technical effects: 1. Analyze the video frame and decompose it into N regions. The value of N can be adjusted as needed to accommodate video frames of different resolutions and different analysis requirements. Obtaining the attribute value corresponding to each pixel in the target area and calculating the average attribute value of each area can reduce the impact of noise and outliers and improve the accuracy of data analysis. Packing the average attribute value of each area in the N areas to obtain a packed array of each area in the N areas, and sending the packed array of each area in the N areas to an external device can support intelligent environmental control systems, such as adjusting indoor lighting or temperature according to video content; 2. Adopting the image segmentation technology solution based on the dilated convolutional UNET network, the initial segmentation model is trained based on the training data set until the preset iteration termination condition is reached to obtain the target model, and the target video frame is segmented according to the target model to obtain the N regions. It realizes automated and efficient video frame segmentation processing, generates accurate N region divisions, and has the advantages of improving segmentation accuracy, enhancing model generalization ability, supporting real-time applications and improving computing efficiency; 3. A method for ensuring video frame acquisition and time synchronization is implemented. This method obtains video frames according to the set frame rate of the target video and saves these frames with their timestamps synchronously, thereby obtaining a time-ordered set of video frames. This helps to improve the efficiency of video data processing and ensure the consistency and reliability of video frames in subsequent processing and analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a method for analyzing projected image data in one embodiment of the present application; Figure 2 is a flowchart for implementing step S10 in a method for analyzing projected image data in one embodiment of the present application; Figure 3 This is another implementation flow chart of step S10 in a method for analyzing projected image data in one embodiment of the present application; Figure 4 This is another implementation flow chart of step S10 in a method for analyzing projected image data in an embodiment of the present application; Figure 5 is a flowchart for implementing step S20 in a method for analyzing projected image data in one embodiment of the present application; Figure 6 is a flowchart for implementing step S30 in a method for analyzing projected image data in one embodiment of the present application; Figure 7 It is a principle block diagram of a projected image data analysis system in one embodiment of the present application. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings.

[0024] In one embodiment, if Figure 1 As shown, the present application discloses a projected image data analysis method, which specifically includes the following steps: S10: Decompose the target video frame into N regions, wherein the target video frame is any frame of video in a set of video frames corresponding to the target video, and N is an integer greater than or equal to 2.

[0025] In this embodiment, the target video frame refers to a random video frame selected from a set of all video frames of the video, and N is an integer greater than or equal to 2.

[0026] Specifically, since the target video includes a lot of picture information, one frame of the video is obtained by selecting all the video frame sets of the target video and using it as the target video frame. The selection method can be random selection or selection based on specific conditions to represent the video content for subsequent processing. The selected target video frame is then divided into N regions, wherein the target video frame can be divided by using a model constructed based on a dilated convolutional UNET network, or by an image segmentation method based on boundary detection, or by an image segmentation method based on pixel features, thereby obtaining N regional image data after the target video frame is divided. Of course, other methods can also be used to divide the target video frame, which are not specifically limited.

[0027] S20: Obtain the attribute value of the attribute corresponding to each pixel in the target area.

[0028] In this embodiment, the target area refers to any one of the N areas after the target video frame is divided. The attribute corresponding to each pixel point refers to each attribute in the ARGB attribute value of the pixel point, namely, transparency (Alpha), red (Red), green (Green) and blue (Blue), and the attribute value refers to the transparency value of the pixel point, the value of the red component, the value of the green component and the value of the blue component.

[0029] Specifically, each pixel in any of the N regions after the target video frame is divided is carefully analyzed to obtain the complete ARGB attribute value of each pixel in each region. This process involves evaluating the transparency of the Alpha channel of each pixel and quantifying the attribute values ​​of the three color channels of Red, Green and Blue for each pixel. High-precision image processing algorithms can be used to ensure the accuracy of these attribute values, thereby capturing the true color and transparency status of each pixel.

[0030] S30: Calculate the average attribute value of each of the N areas according to the attribute value corresponding to each pixel point.

[0031] In this embodiment, after determining the attribute value of the attribute corresponding to each pixel in each area, the average attribute value of each area can be calculated according to the attribute value of the attribute corresponding to each pixel. The average attribute value refers to the sum of each channel divided by the total number of pixels. The result is the average attribute value of each area. The average attribute value includes the average transparency (Average Alpha), average red (Average Red), average green (Average Green) and average blue (Average Blue) values.

[0032] Specifically, for any target area among the N areas, the ARGB attribute values ​​of each pixel in the area are first obtained, which include their respective transparency (Alpha), red (Red), green (Green) and blue (Blue) components, and then the attribute values ​​of each channel are summed, that is, the Alpha, Red, Green and Blue values ​​of all pixels in the target area are accumulated respectively, and the total number of pixels in the target area is determined, which is obtained by calculating the number of each pixel in the area. With the sum of each channel and the total number of pixels, the average attribute value of the target area is calculated. These average values ​​can reflect the overall color tendency and transparency level of the target area, providing important quantitative information for image analysis. For example, a high average red component in a region may indicate that the region is dominated by red, while a low average transparency may mean that the region is visually dim. In this way, each region can be deeply analyzed and understood, thereby achieving more accurate image processing and intelligent control.

[0033] S40: Packing the average attribute value of each of the N regions to obtain a packing array of each of the N regions.

[0034] In this embodiment, after determining the average attribute value of each area in the N areas, the average attribute value of each area can be packaged to obtain packaged data. The packaged array refers to organizing and storing the average attribute value (i.e., average transparency value, average red value, average green value, average blue value) calculated for each area according to a certain data structure for effective transmission and subsequent processing. The external device refers to a device that receives these packaged array data.

[0035] Specifically, the average attribute value of each region is encapsulated into an array element, such as [Average Alpha, Average Red, Average Green, Average Blue], and then the array elements of all regions are assembled into a list or array to form the final packed array. The external device refers to the device that receives these packed array data. It can be an ambient light controller in a smart home system, an intelligent lighting system, or any other device that can parse and respond to this data. These devices adjust their own display or behavior based on the received average attribute value. For example, the ambient light may change its luminous color based on the received color value to synchronize with the video content and enhance the viewing experience.

[0036] S50: Sending the packed array of each area in the N areas to an external device, so that after receiving the packed array, the external device parses the packed array and performs display control according to the parsed data.

[0037] In this embodiment, after the average attributes of each area in the N areas are packaged to obtain a packaged array, the packaged array can be sent to an external device. After receiving the packaged array, the external device can parse the packaged data to obtain parsed data, and perform display control according to the parsed data. The external device refers to a device that receives the packaged array data, has a built-in receiving module, and can parse the received array data.

[0038] Specifically, the external device receives data packets from the projector through its built-in receiving module, such as a Wi-Fi or Bluetooth receiver, and the received data is first parsed to determine the average ARGB value of each area. This usually involves mapping each element in the data packet to the corresponding area and color channel. Based on the average color value obtained by parsing, the external device maps it to a displayable color space. For example, if the external device is a smart LED atmosphere light, these values ​​will be used to set the color of the light.

[0039] By adopting the above technical solution, the video frame is analyzed and decomposed into N areas, and the value of N can be adjusted as needed to adapt to video frames of different resolutions and different analysis requirements. Obtaining the attribute value corresponding to each pixel in the target area and calculating the average attribute value of each area can reduce the impact of noise and outliers and improve the accuracy of data analysis. The average attribute value of each area in the N areas is packaged to obtain a packaged array of each area in the N areas, and the packaged array of each area in the N areas is sent to an external device. The external device can perform precise display control based on these data, thereby improving the quality and accuracy of the projection effect. It can support intelligent environmental control systems, such as adjusting indoor lighting according to video content.

[0040] In one embodiment, if Figure 2 As shown, in step S10, the target video frame is decomposed into N regions, specifically including: S11: construct a training data set, where the training data set includes multiple images and a segmentation result of each of the multiple images; Specifically, a training data set is constructed, which includes multiple image samples. Image processing technology or an existing segmentation model is used to generate segmentation results for each image. These results together with the original images will constitute the training data set.

[0041] S12: Use the dilated convolutional UNET network to build the initial segmentation model; Specifically, a UNET network based on void convolution is initialized, which can distinguish different regions and objects and provide a basic model for image analysis and processing tasks.

[0042] S13: training the initial segmentation model based on the training data set until a preset iteration termination condition is reached to obtain a target model; Specifically, the UNET model is trained through a continuous supervised learning process, and the network weights are continuously optimized using the training data set until the performance of the model reaches the preset iteration termination condition, ensuring the accuracy and generalization ability of the model.

[0043] S14: Segment the target video frame according to the target model to obtain N regions.

[0044] Specifically, the target model can effectively segment the target video frame into N regions, providing structured data for further image analysis and processing.

[0045] In one embodiment, if Figure 3 As shown, in step S10, the target video frame is decomposed into N regions, specifically including: S15: performing boundary judgment on each pixel value in the target video frame to determine all boundary pixels in the target video frame; Specifically, an image segmentation method based on boundary detection is introduced. This method performs boundary judgment on each pixel in the target video frame and uses image processing algorithms to identify pixels located at the edge of the image. These pixels mark the dividing lines between different areas.

[0046] S16: Divide the matched boundary pixels among all boundary pixels in the target video frame into the same region to obtain N regions.

[0047] Specifically, by intelligently matching and grouping these boundary pixels, pixels with common boundary features are divided into the same region, thereby automatically constructing N regions, each of which is composed of pixels with similar visual characteristics. This method can not only improve the accuracy of image segmentation and ensure the naturalness and logic of regional division, but also significantly improve the efficiency of image analysis through automated processing procedures, laying the foundation for further image understanding.

[0048] In one embodiment, if Figure 4 As shown, in step S10, the target video frame is decomposed into N regions, specifically including: S17: Determine the characteristics of each pixel value in the target video frame; Specifically, a pixel feature-based image segmentation method is adopted to first comprehensively analyze the features of each pixel in the target video frame. These features may include but are not limited to color intensity, texture information, local contrast, etc.

[0049] S18: Classify the pixels in the target video frame according to the features of each pixel, and divide the pixels of the same category into the same region to obtain N regions.

[0050] Specifically, clustering algorithms such as K-means, hierarchical clustering, or density-based DBSCAN are used to classify pixels into different categories based on their feature vectors. Based on the clustering results, pixels belonging to the same category are divided into the same region. These regions may represent different objects or background parts in the video. The boundaries of the generated regions are determined to ensure that the boundaries of each region are clear and correspond to the natural boundaries of the video frame content. Image segmentation methods based on pixel features can effectively decompose the target video frame into N regions with common visual characteristics, providing structured data for further image analysis and understanding.

[0051] In one embodiment, if Figure 5 As shown, in step S20, the attribute value corresponding to each pixel point in the target area is obtained, which specifically includes: S21: Obtaining an attribute value corresponding to each pixel in a target area, where the target area is any one of the N areas, and the attribute corresponding to each pixel includes at least one of transparency, a red component, a green component, and a blue component.

[0052] Specifically, each pixel in any of the N regions after the target video frame is divided is carefully analyzed to obtain the complete ARGB attribute value of each pixel in each region. This process involves evaluating the transparency of the Alpha channel of each pixel and quantifying the attribute values ​​of the three color channels of Red, Green and Blue for each pixel. High-precision image processing algorithms can be used to ensure the accuracy of these attribute values, thereby capturing the true color and transparency status of each pixel.

[0053] In one embodiment, if Figure 6 As shown, in step S30, the average attribute value of each area in the N areas is calculated according to the attribute value of the attribute corresponding to each pixel point, which specifically includes: S31: summing the attribute values ​​corresponding to each pixel point to obtain the sum value of the attribute corresponding to each pixel point; Specifically, the attribute values ​​corresponding to each pixel are summed, that is, the attribute values ​​of the three color channels of Red, Green and Blue of each pixel are accumulated respectively.

[0054] S32: Determine the number of pixels contained in the target area; Specifically, the total number of pixels in the target area is determined, which is obtained by calculating the number of each pixel in the area.

[0055] S33: Determine the average attribute value of each of the N regions according to the sum value and the number of pixels.

[0056] Specifically, after determining the attribute value of the attribute corresponding to each pixel in each area, the average attribute value of each area can be calculated according to the attribute value of the attribute corresponding to each pixel. The average attribute value refers to the sum of each channel divided by the total number of pixels. The result is the average attribute value of each area, which includes the average transparency (Average Alpha), average red (Average Red), average green (Average Green) and average blue (Average Blue) values. These average values ​​can reflect the overall color tendency and transparency level of the target area, providing important quantitative information for image analysis. For example, a higher average red component in an area may indicate that the area is dominated by red, while a lower average transparency may mean that the area is visually dim. In this way, each area can be deeply analyzed and understood, thereby achieving more accurate image processing and intelligent control.

[0057] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0058] In one embodiment, a projection image data analysis system is provided, and the projection image data analysis system corresponds one-to-one to a projection image data analysis method in the above embodiment. Figure 7 As shown, the projected image data analysis system includes a decomposition module, an acquisition module, a calculation module, a packaging module, a sending module, and a receiving module. The detailed description of each functional module is as follows: A decomposition module, used for decomposing a target video frame into N regions, wherein the target video frame is any frame of video in a set of video frames corresponding to the target video, and N is an integer greater than or equal to 2; An acquisition module, used to acquire an attribute value corresponding to each pixel in a target area, where the target area is any one of the N areas, and the attribute corresponding to each pixel includes at least one of transparency, a red component, a green component, and a blue component; A calculation module, used for calculating the average attribute value of each area in the N areas according to the attribute value of the attribute corresponding to each pixel point; A packing module, used for packing the average attribute value of each area in the N areas to obtain a packing array of each area in the N areas; The sending module is used to send the packaged array of each area in the N areas to the external device, so that after the external device receives the packaged array, it parses the packaged array and performs display control according to the parsed data.

[0059] Specifically, the projected image data analysis system realizes an efficient image processing process through a carefully designed modular architecture. A decomposition module is used to decompose the target video frame into N regions, wherein the target video frame is any frame of video in the set of video frames corresponding to the target video, and N is an integer greater than or equal to 2. An acquisition module is used to obtain the attribute value of the attribute corresponding to each pixel in the target region, the target region is any region in the N regions, and the attribute corresponding to each pixel includes at least one of transparency, red component, green component and blue component. A calculation module is used to calculate the average attribute value of each region in the N regions according to the attribute value of the attribute corresponding to each pixel. A packaging module is used to package the average attribute value of each region in the N regions to obtain a packaged array of each region in the N regions. A sending module is used to send the packaged array of each region in the N regions to an external device, so that after the external device receives the packaged array, it parses the packaged array and performs display control according to the parsed data. Among them, the external device can be an ambient light controller, which is used to control the display of the ambient light according to the analyzed average attribute value, such as adjusting the color and brightness of the ambient light to synchronize with the video content, thereby achieving an immersive viewing experience. The entire system is designed to provide an automated, high-precision image data analysis solution suitable for a variety of scenarios, including home theaters, commercial displays, or intelligent environmental control systems.

[0060] For the specific definition of a projected image data analysis system, please refer to the definition of a projected image data analysis method above, which will not be repeated here. Each module in the above-mentioned projected image data analysis system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0061] In one embodiment, a computer device is provided, which may be a server, and includes a processor, a memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for analyzing projected image data is implemented.

[0062] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Decomposing a target video frame into N regions, wherein the target video frame is any frame of video in a set of video frames corresponding to the target video, and N is an integer greater than or equal to 2; Obtaining an attribute value of an attribute corresponding to each pixel in a target area, wherein the target area is any one of the N areas, and the attribute corresponding to each pixel includes at least one of transparency, a red component, a green component, and a blue component; Calculating an average attribute value of each of the N areas according to the attribute value of the attribute corresponding to each pixel point; Packing the average attribute value of each area in the N areas to obtain a packed array of each area in the N areas; The packed array of each area in the N areas is sent to an external device, so that after receiving the packed array, the external device parses the packed array and performs display control according to the parsed data.

[0063] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Decomposing a target video frame into N regions, wherein the target video frame is any frame of video in a set of video frames corresponding to the target video, and N is an integer greater than or equal to 2; Obtaining an attribute value of an attribute corresponding to each pixel in a target area, wherein the target area is any one of the N areas, and the attribute corresponding to each pixel includes at least one of transparency, a red component, a green component, and a blue component; Calculating an average attribute value of each of the N areas according to the attribute value of the attribute corresponding to each pixel point; Packing the average attribute value of each area in the N areas to obtain a packed array of each area in the N areas; The packed array of each area in the N areas is sent to an external device, so that after receiving the packed array, the external device parses the packed array and performs display control according to the parsed data.

[0064] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0065] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0066] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for analyzing projected image data, characterized in that: The projected image data analysis method comprises: Decomposing a target video frame into N regions, wherein the target video frame is any frame of video in a set of video frames corresponding to the target video, and N is an integer greater than or equal to 2; Obtaining an attribute value of an attribute corresponding to each pixel in a target area, wherein the target area is any one of the N areas, and the attribute corresponding to each pixel includes at least one of transparency, a red component, a green component, and a blue component; Calculating an average attribute value of each of the N areas according to the attribute value of the attribute corresponding to each pixel point; Packing the average attribute value of each area in the N areas to obtain a packed array of each area in the N areas; The packed array of each area in the N areas is sent to an external device, so that after receiving the packed array, the external device parses the packed array and performs display control according to the parsed data.

2. The projected image data analysis method according to claim 1, characterized in that: Decomposing the target video frame into N regions specifically includes: Constructing a training data set, wherein the training data set includes a plurality of images and a segmentation result of each of the plurality of images; The initial segmentation model is constructed using the dilated convolutional UNET network; Training the initial segmentation model based on the training data set until a preset iteration termination condition is reached to obtain a target model; The target video frame is segmented according to the target model to obtain the N regions.

3. The projected image data analysis method according to claim 1, characterized in that: Decomposing the target video frame into N regions specifically includes: Performing boundary judgment on each pixel value in the target video frame to determine all boundary pixels in the target video frame; The matched boundary pixels among all the boundary pixels in the target video frame are divided into the same region to obtain the N regions.

4. The projected image data analysis method according to claim 1, characterized in that: Decomposing the target video frame into N regions specifically includes: Determining a characteristic of each pixel value in the target video frame; The pixels in the target video frame are classified according to the features of each pixel, and pixels of the same category are divided into the same region to obtain the N regions.

5. The method for analyzing projected image data according to any one of claims 1 to 4, characterized in that: Calculating the average attribute value of each of the N regions according to the attribute value corresponding to each pixel point includes: Sum the attribute values ​​of the attributes corresponding to each pixel point to obtain the sum value of the attributes corresponding to each pixel point; Determine the number of pixels contained in the target area; The average attribute value of each of the N areas is determined according to the sum value and the number of pixels.

6. The method for analyzing projected image data according to any one of claims 1 to 4, characterized in that: The method further comprises: Determining a set frame rate of the target video, and acquiring video frames of the target video based on the set frame rate; The acquired video frames of the target video are synchronously saved with the timestamps of the video frames of the target video to obtain the video frame set.

7. A projected image data analysis system, characterized in that: The projected image data analysis system comprises: A decomposition module, used to decompose a target video frame into N regions, wherein the target video frame is any frame of video in a set of video frames corresponding to the target video, and N is an integer greater than or equal to 2; an acquisition module, used to acquire an attribute value of an attribute corresponding to each pixel in a target area, wherein the target area is any one of the N areas, and the attribute corresponding to each pixel includes at least one of transparency, a red component, a green component, and a blue component; A calculation module, used for calculating an average attribute value of each of the N areas according to the attribute value of the attribute corresponding to each pixel point; A packing module, used for packing the average attribute value of each area in the N areas to obtain a packing array of each area in the N areas; The sending module is used to send the packed array of each area in the N areas to an external device, so that after the external device receives the packed array, it parses the packed array and performs display control according to the parsed data.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the projection image data analysis method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the projection image data analysis method according to any one of claims 1 to 6 are implemented.