阅读说明：本技术 视频数据来源解析系统及方法 (Video data source analysis system and method ) 是由 不公告发明人 于 2019-09-20 设计创作，主要内容包括：本发明涉及一种视频数据来源解析系统,包括：数据补偿设备,用于基于待处理亮度值对当前播放帧进行亮度补偿操作,待处理亮度值距离预设亮度阈值的差值越大,对当前播放帧进行亮度补偿操作的补偿值越大；信号检测设备,用于基于头部成像特征匹配出已处理图像中的各个头部对象分别所在的头部子图像,并在存在某一个头部对象的景深距离其他头部对象的各个景深的最小值的数值超限时,发出头部游离命令。本发明还涉及一种视频数据来源解析方法。本发明的视频数据来源解析系统及方法直观有效、节约人工成本。由于在当前视频帧中存在某一个头部对象的景深远远浅于其他头部对象时,认定为影院现场偷录的视频,从而有效鉴别了视频数据的来源。(The invention relates to a video data source analysis system, comprising: the data compensation equipment is used for performing brightness compensation operation on the current playing frame based on the brightness value to be processed, and the larger the difference value of the brightness value to be processed from a preset brightness threshold value is, the larger the compensation value of the brightness compensation operation on the current playing frame is; and the signal detection equipment is used for matching head sub-images in which all head objects in the processed image are respectively positioned based on the head imaging characteristics, and sending a head dissociation command when the numerical value of the minimum value of the depth of field of a certain head object to the depth of fields of other head objects exceeds the limit. The invention also relates to a video data source analysis method. The video data source analysis system and method are visual and effective, and labor cost is saved. When the depth of field of a certain head object is far shallower than that of other head objects in the current video frame, the video recorded in the cinema scene is identified, and therefore the source of the video data is effectively identified.)

1. A video data source parsing system, said system comprising:

the parameter identification device is used for acquiring a current playing frame sent by a video application program, and identifying the definition of the current playing frame to obtain a corresponding definition grade, wherein the higher the corresponding definition grade is, the clearer the current playing frame is, and the current playing frame is a current picture of a video played by the video application program;

the signal conversion device is connected with the parameter identification device and is used for performing average segmentation action on the current playing frame based on the definition level to obtain each segmentation block;

in the signal conversion apparatus, the higher the definition level is, the greater the number of obtained individual divided blocks;

the signal selection device is connected with the signal conversion device and used for receiving each segmentation block of the current playing frame, selecting four segmentation blocks of the upper left corner, the upper right corner, the lower left corner and the lower right corner of the current playing frame as four segmentation blocks to be analyzed and outputting the four segmentation blocks;

the parameter output equipment is connected with the signal selection equipment and used for detecting the brightness values of the four to-be-analyzed segmented blocks and taking the average value of the brightness values of the four to-be-analyzed segmented blocks as a to-be-processed brightness value;

the data compensation equipment is connected with the parameter output equipment and is used for performing brightness compensation operation on the current playing frame based on the brightness value to be processed, and the larger the difference value of the brightness value to be processed from a preset brightness threshold value is, the larger the compensation value of the brightness compensation operation on the current playing frame is;

the signal detection equipment is connected with the data compensation equipment and is used for matching head sub-images in which each head object in the processed image is respectively positioned based on the head imaging characteristics, and sending a head dissociating command when the numerical value of the minimum value of the depth of field of a certain head object to the depth of fields of other head objects exceeds the limit, or sending a head non-dissociating command;

the time division duplex communication equipment is connected with the signal detection equipment and is used for packaging and sending the head dissociating command and a playing address of a video played by a video application program to a remote video auditing server when receiving the head dissociating command;

wherein the data compensation device further outputs a processed image obtained after the brightness compensation operation is performed.

2. The video data source parsing system of claim 1, wherein said system further comprises:

the signal analysis equipment is used for acquiring a current playing frame sent by a video application program, acquiring a gray value of each pixel point in the current playing frame, and executing the following actions aiming at each pixel point: judging each gradient from the gray value to each pixel point around, judging the gradient as an edge pixel point when each gradient is greater than or equal to a preset gradient threshold, and judging the pixel point as a non-edge pixel point when each gradient is less than the preset gradient threshold;

the signal analysis device is further configured to connect all edge pixel points in the current playing frame to obtain one or more closed curves, and divide one or more image regions from the current playing frame based on the one or more closed curves.

3. The video data source parsing system of claim 2, wherein said system further comprises:

the repeatability extracting device is connected with the signal analyzing device and used for executing the following actions for each image area: determining the repetition degree of each pixel point based on each pixel value of each pixel point;

and the adaptive interpolation device is respectively connected with the signal analysis device and the repeatability extraction device and is used for executing the adaptive interpolation action only on each image area in the current playing frame and not executing the adaptive interpolation action on areas outside one or more image areas in the current playing frame.

4. The video data source parsing system of claim 3 wherein:

in the adaptive interpolation device, performing the adaptive interpolation action on each image region includes: when the repetition degree of the image area is greater than or equal to a preset repetition degree, performing Krigin interpolation processing on the image area, and when the repetition degree of the image area is less than the preset repetition degree, not performing the Krigin interpolation processing on the image area;

the adaptive interpolation device takes the current playing frame of each image area after the adaptive interpolation action is executed as an adaptive processing image to replace the current playing frame and sends the adaptive processing image to the parameter identification device.

5. The video data source parsing system of claim 4 wherein:

the signal analysis equipment comprises a pixel point detection sub-equipment and a curve processing sub-equipment, and the pixel point detection sub-equipment is connected with the curve processing sub-equipment;

the pixel point detection sub-device is used for acquiring the gray value of each pixel point in the current playing frame, and executing the following actions aiming at each pixel point: and judging each gradient from the gray value to each pixel point around, judging the gradient as an edge pixel point when each gradient is greater than or equal to a preset gradient threshold, and judging the pixel point as a non-edge pixel point when each gradient is less than the preset gradient threshold.

6. A method for parsing a video data source, the method comprising:

the method comprises the steps that parameter identification equipment is used for obtaining a current playing frame sent by a video application program, and identifying the definition of the current playing frame to obtain a corresponding definition grade, wherein the higher the corresponding definition grade is, the clearer the current playing frame is, and the current playing frame is a current picture of a video played by the video application program;

a signal conversion device connected with the parameter identification device and used for performing an average segmentation action on the current playing frame based on the definition level to obtain each segmentation block;

in the signal conversion apparatus, the higher the definition level is, the greater the number of obtained individual divided blocks;

the used signal selection equipment is connected with the signal conversion equipment and is used for receiving each segmentation block of the current playing frame, and selecting four segmentation blocks of the upper left corner, the upper right corner, the lower left corner and the lower right corner of the current playing frame as four segmentation blocks to be analyzed and outputting the four segmentation blocks;

the using parameter output equipment is connected with the signal selection equipment and used for detecting the brightness values of the four to-be-analyzed segmented blocks and taking the average value of the brightness values of the four to-be-analyzed segmented blocks as a to-be-processed brightness value;

the data compensation equipment is connected with the parameter output equipment and is used for performing brightness compensation operation on the current playing frame based on the brightness value to be processed, and the larger the difference value of the brightness value to be processed from a preset brightness threshold value is, the larger the compensation value of the brightness compensation operation on the current playing frame is;

using signal detection equipment, connected with the data compensation equipment, for matching head sub-images in which each head object in the processed image is respectively located based on head imaging characteristics, and sending a head dissociating command when the numerical value of the minimum value of the depth of field of a certain head object from the depth of fields of other head objects exceeds the limit, otherwise, sending a head non-dissociating command;

the system comprises a signal detection device, a head dissociating command, a video application program and a video auditing server, wherein the signal detection device is connected with the signal detection device through time division duplex communication equipment and used for receiving the head dissociating command and packaging the head dissociating command and a playing address of a video played by the video application program to send to the remote video auditing server;

wherein the data compensation device further outputs a processed image obtained after the brightness compensation operation is performed.

7. The video data source parsing method of claim 6, wherein said method further comprises:

the method comprises the following steps of using a signal analysis device for obtaining a current playing frame sent by a video application program, obtaining a gray value of each pixel point in the current playing frame, and executing the following actions aiming at each pixel point: judging each gradient from the gray value to each pixel point around, judging the gradient as an edge pixel point when each gradient is greater than or equal to a preset gradient threshold, and judging the pixel point as a non-edge pixel point when each gradient is less than the preset gradient threshold;

the signal analysis device is further configured to connect all edge pixel points in the current playing frame to obtain one or more closed curves, and divide one or more image regions from the current playing frame based on the one or more closed curves.

8. The video data source parsing method of claim 7, wherein said method further comprises:

using a repetition degree extraction device, connected to the signal analysis device, for performing the following actions for each image area: determining the repetition degree of each pixel point based on each pixel value of each pixel point;

and using an adaptive interpolation device respectively connected with the signal analysis device and the repeatability extraction device, and used for only performing the adaptive interpolation action on each image area in the current playing frame and not performing the adaptive interpolation action on areas outside one or more image areas in the current playing frame.

9. The method for parsing a source of video data according to claim 8, wherein:

in the adaptive interpolation device, performing the adaptive interpolation action on each image region includes: when the repetition degree of the image area is greater than or equal to a preset repetition degree, performing Krigin interpolation processing on the image area, and when the repetition degree of the image area is less than the preset repetition degree, not performing the Krigin interpolation processing on the image area;

the adaptive interpolation device takes the current playing frame of each image area after the adaptive interpolation action is executed as an adaptive processing image to replace the current playing frame and sends the adaptive processing image to the parameter identification device.

10. The method for parsing a source of video data according to claim 9, wherein:

the signal analysis equipment comprises a pixel point detection sub-equipment and a curve processing sub-equipment, and the pixel point detection sub-equipment is connected with the curve processing sub-equipment;

the pixel point detection sub-device is used for acquiring the gray value of each pixel point in the current playing frame, and executing the following actions aiming at each pixel point: and judging each gradient from the gray value to each pixel point around, judging the gradient as an edge pixel point when each gradient is greater than or equal to a preset gradient threshold, and judging the pixel point as a non-edge pixel point when each gradient is less than the preset gradient threshold.