阅读说明：本技术 一种视频监控系统中视频质量检测方法及装置 (Video quality detection method and device in video monitoring system ) 是由 祝接金 于 2018-06-12 设计创作，主要内容包括：本发明公开了一种视频监控系统中视频质量检测方法及装置,通过定制的视频源播放在显示设备上,通过采集摄像机采集显示设备的画面,客户端点播该采集摄像机的实况,获取实况视频流,对实况视频流进行解码检测,或直接从视频监控系统获取解码后的视频图像帧,进行检测。然后根据GOP帧组中的数字水印和每一帧的灰度值,输出检测结果。采用本发明的技术方案,实现了全自动的检测,提高了检测的效率,并且大大提高了检测的准确度。(The invention discloses a method and a device for detecting video quality in a video monitoring system, wherein a customized video source is played on a display device, a picture of the display device is collected by a collection camera, a client requests the live of the collection camera to obtain a live video stream, the live video stream is decoded and detected, or a decoded video image frame is directly obtained from the video monitoring system to be detected. And then outputting a detection result according to the digital watermark in the GOP frame group and the gray value of each frame. By adopting the technical scheme of the invention, full-automatic detection is realized, the detection efficiency is improved, and the detection accuracy is greatly improved.)

1. A video quality detection method in a video monitoring system is used for detecting the video quality of the video monitoring system to be detected, and is characterized in that the video quality detection method in the video monitoring system comprises the following steps:

ordering a pre-customized video source through a video monitoring system to be detected, wherein the gray value of each frame in a GOP frame group in the pre-customized video source is different, and a preset digital watermark is superposed on each GOP frame group;

acquiring a decoded video image frame corresponding to the pre-customized video source;

and analyzing the decoded video image frame, and outputting a detection result according to the digital watermark in the GOP frame group and the gray value of each frame.

2. The method of claim 1, wherein outputting the detection result according to the digital watermark in the GOP frame group and the gray level value of each frame comprises:

and detecting the digital watermark superposed in each GOP frame group, recording the detected digital watermark if the digital watermark is detected, and outputting a detection result of incorrect decoding if the digital watermark is not detected.

3. The method of claim 1, wherein outputting the detection result according to the digital watermark in the GOP frame group and the gray level value of each frame comprises:

and detecting the gray value of each frame in each GOP frame group, comparing the gray value with the original gray value of a video source customized in advance, judging that the decoding is abnormal if the gray value is inconsistent with the original gray value of the video source customized in advance, and outputting a detection result of the decoding abnormality.

4. The method of detecting video quality in a video surveillance system according to claim 2, wherein outputting the detection result based on the digital watermark in the GOP frame group and the gray level value of each frame, further comprises:

counting the digital watermark detection result on the decoded video image within a preset time period, comparing the digital watermark detection result with the original digital watermark of the video source customized in advance, if the digital watermark detection result is inconsistent with the original digital watermark of the video source customized in advance, determining that the digital watermark detection result is blocked, and outputting the detection result of the blocked picture;

or counting the digital watermark detection result on the decoded video image within the preset time period, checking whether continuous and repeated digital watermarks exist, if so, determining that the image is stuck, and outputting the detection result of the image stuck.

5. The method as claimed in claim 1, wherein the gray value interval of each frame in the GOP frame group is a predetermined value.

6. The utility model provides a video quality detection device among video monitor system for treating the video quality who detects video monitor system detects, its characterized in that, video quality detection device among the video monitor system includes:

the system comprises an acquisition module, a video processing module and a video processing module, wherein the acquisition module is used for requesting a pre-customized video source through a video monitoring system to be detected, the gray value of each frame in a GOP frame group in the pre-customized video source is different, a preset digital watermark is superposed on each GOP frame group, and a decoded video image frame corresponding to the pre-customized video source is acquired;

and the analysis module is used for analyzing the decoded video image frames and outputting a detection result according to the digital watermark in the GOP frame group and the gray value of each frame.

7. The video quality detection device of claim 6, wherein the analysis module outputs the detection result according to the digital watermark in the GOP frame group and the gray level value of each frame, and performs the following operations:

and detecting the digital watermark superposed in each GOP frame group, recording the detected digital watermark if the digital watermark is detected, and outputting a detection result of incorrect decoding if the digital watermark is not detected.

8. The video quality detection device of claim 6, wherein the analysis module outputs the detection result according to the digital watermark in the GOP frame group and the gray level value of each frame, and performs the following operations:

and detecting the gray value of each frame in each GOP frame group, comparing the gray value with the original gray value of a video source customized in advance, judging that the decoding is abnormal if the gray value is inconsistent with the original gray value of the video source customized in advance, and outputting a detection result of the decoding abnormality.

9. The video quality detection apparatus of claim 7, wherein the analysis module outputs the detection result according to the digital watermark in the GOP frame group and the gray level value of each frame, and further performs the following operations:

counting the digital watermark detection result on the decoded video image within a preset time period, comparing the digital watermark detection result with the original digital watermark of the video source customized in advance, if the digital watermark detection result is inconsistent with the original digital watermark of the video source customized in advance, determining that the digital watermark detection result is blocked, and outputting the detection result of the blocked picture;

or counting the digital watermark detection result on the decoded video image within the preset time period, checking whether continuous and repeated digital watermarks exist, if so, determining that the image is stuck, and outputting the detection result of the image stuck.

10. The apparatus of claim 6, wherein the interval of the gray values of each frame in the group of GOP frames is a predetermined value.

Technical Field

The invention belongs to the technical field of video quality detection, and particularly relates to a video quality detection method and device in a video monitoring system.

Background

In the field of video monitoring automation test, video pictures are often required to be tested. For example, it is necessary to observe video pictures such as live videos and replays and determine whether the video pictures are displayed on a screen or jammed. Whether the video picture has the phenomena of screen splash, blockage and the like can be conveniently observed by human eyes, but how to detect the video picture by an automatic means is a problem to be solved urgently in the automation field.

The detection of the quality of the video pictures in the current automatic test is still completed in a semi-manual mode, firstly, the video pictures such as live pictures, playback pictures and the like are automatically captured and stored, and then, a tester observes the pictures to confirm whether the pictures are normal or not.

However, the technical problems of the above detection methods are also obvious, such as greatly reducing the efficiency of automated testing by semi-manual method, which affects the testing efficiency; the probability of result recording errors is improved in a manual mode; for some smaller details, the manual mode may not be able to distinguish effectively, so that the test result is not accurate.

Disclosure of Invention

The invention aims to provide a method and a device for detecting video quality in a video monitoring system, which overcome the problems in the background technology, realize full-automatic detection, improve the detection efficiency and greatly improve the detection accuracy.

In order to achieve the purpose, the technical scheme of the invention is as follows:

a video quality detection method in a video monitoring system is used for detecting the video quality of the video monitoring system to be detected, and comprises the following steps:

ordering a pre-customized video source through a video monitoring system to be detected, wherein the gray value of each frame in a GOP frame group in the pre-customized video source is different, and a preset digital watermark is superposed on each GOP frame group;

acquiring a decoded video image frame corresponding to the pre-customized video source;

and analyzing the decoded video image frame, and outputting a detection result according to the digital watermark in the GOP frame group and the gray value of each frame.

Further, the outputting the detection result according to the digital watermark in the GOP frame group and the gray value of each frame includes:

and detecting the digital watermark superposed in each GOP frame group, recording the detected digital watermark if the digital watermark is detected, and outputting a detection result of incorrect decoding if the digital watermark is not detected.

Further, the outputting the detection result according to the digital watermark in the GOP frame group and the gray value of each frame further includes:

counting the digital watermark detection result on the decoded video image within a preset time period, comparing the digital watermark detection result with the original digital watermark of the video source customized in advance, if the digital watermark detection result is inconsistent with the original digital watermark of the video source customized in advance, determining that the digital watermark detection result is blocked, and outputting the detection result of the blocked picture;

or counting the digital watermark detection result on the decoded video image within the preset time period, checking whether continuous and repeated digital watermarks exist, if so, determining that the image is stuck, and outputting the detection result of the image stuck.

Further, the outputting the detection result according to the digital watermark in the GOP frame group and the gray value of each frame includes:

and detecting the gray value of each frame in each GOP frame group, comparing the gray value with the original gray value of a video source customized in advance, judging that the decoding is abnormal if the gray value is inconsistent with the original gray value of the video source customized in advance, and outputting a detection result of the decoding abnormality.

Further, the gray value interval of each frame in the GOP frame group is a set value.

The invention also provides a video quality detection device in a video monitoring system, which is used for detecting the video quality of the video monitoring system to be detected, and the video quality detection device in the video monitoring system comprises:

the system comprises an acquisition module, a video processing module and a video processing module, wherein the acquisition module is used for requesting a pre-customized video source through a video monitoring system to be detected, the gray value of each frame in a GOP frame group in the pre-customized video source is different, a preset digital watermark is superposed on each GOP frame group, and a decoded video image frame corresponding to the pre-customized video source is acquired;

and the analysis module is used for analyzing the decoded video image frames and outputting a detection result according to the digital watermark in the GOP frame group and the gray value of each frame.

Further, the analysis module outputs a detection result according to the digital watermark in the GOP frame group and the gray value of each frame, and executes the following operations:

and detecting the digital watermark superposed in each GOP frame group, recording the detected digital watermark if the digital watermark is detected, and outputting a detection result of incorrect decoding if the digital watermark is not detected.

Further, the analysis module outputs a detection result according to the digital watermark in the GOP frame group and the gray value of each frame, and further performs the following operations:

counting the digital watermark detection result on the decoded video image within a preset time period, comparing the digital watermark detection result with the original digital watermark of the video source customized in advance, if the digital watermark detection result is inconsistent with the original digital watermark of the video source customized in advance, determining that the digital watermark detection result is blocked, and outputting the detection result of the blocked picture;

or counting the digital watermark detection result on the decoded video image within the preset time period, checking whether continuous and repeated digital watermarks exist, if so, determining that the image is stuck, and outputting the detection result of the image stuck.

Further, the analysis module outputs a detection result according to the digital watermark in the GOP frame group and the gray value of each frame, and executes the following operations:

and detecting the gray value of each frame in each GOP frame group, comparing the gray value with the original gray value of a video source customized in advance, judging that the decoding is abnormal if the gray value is inconsistent with the original gray value of the video source customized in advance, and outputting a detection result of the decoding abnormality.

The invention provides a method and a device for detecting video quality in a video monitoring system, wherein a customized video source is played on a display device, a collection camera of the video monitoring system collects the picture of the display device, a client requests the live of the collection camera to acquire a live video stream, the live video stream is detected, and a detection result is output according to a digital watermark in a GOP frame group and the gray value of each frame. By adopting the technical scheme of the invention, full-automatic detection is realized, the detection efficiency is improved, and the detection accuracy is greatly improved.

Drawings

Fig. 1 is a flow chart of a video quality detection method in a video monitoring system according to the present invention.

Detailed Description

The technical solutions of the present invention are further described in detail below with reference to the drawings and examples, which should not be construed as limiting the present invention.

The general idea of the invention is to utilize the image detection technology to judge whether the video picture has abnormal situations such as blocking or screen splash. The customized video source is requested through the video monitoring system to be detected (the video stream adopts pure gray pictures, for example, each frame uses a gray image, and each frame group is superposed with a digital watermark), and whether abnormal phenomena such as screen splash, blockage and the like occur in the pictures or not is determined through analyzing the decoded video image frames. When the detected gray value in one frame group is deviated from or consistent with the overall gray value of a customized video source, the picture is considered to be normal (i.e. no screen-skip or stuck phenomenon), otherwise, if a plurality of pictures with the same gray value or pictures with non-pure colors appear in the same frame group, the picture is considered to be abnormal. In addition, for different frame groups, if the digital watermarks appearing on the pictures are the same, the pictures are jammed, otherwise, the pictures are normal.

The customized video source of the present invention is a video file M prepared in advance for testing whether the video decoding function is normal. The video file M needs to customize the video content in addition to meeting specific requirements such as a specified bit rate, resolution, frame rate, etc. The video file M adopted by the technical scheme has the following requirements:

the video content is a pure gray picture, i.e. each frame is decoded to be a pure gray picture.

The gray value of each frame in each GOP frame group is different, the available range of the gray value is 0-255, and a continuous section of gray value or an equal difference gray value can be adopted for each frame picture. For example, assuming that each GOP frame group includes 50 frames, one frame may be given a gray value, e.g., 0, 1, 2, 3 … … 49, respectively; or any gray scale range in the range. Alternatively, an equal difference gray scale value, such as 0, 5, 10, 15 …, and so on, may be used. The technical scheme preferably adopts the equal difference gray value, namely the gray value interval of each frame is a set fixed value, for example, 5, so that the success rate of analyzing the gray value by normal decoding of the picture can be increased.

A gray scale range can be used continuously for a plurality of GOP frame groups, for example, the first frame group is 0-49, the second frame group is 50-99, and the like, until 255 later, the conversion is continued from 0.

Each GOP frame group needs to be superimposed with a digital watermark for distinguishing different GOP frame groups. Digital watermarks may take the form of natural numbers, i.e., 0, 1, 2, 3, 4, 5 … …, and so on. For example, a first frame group is superimposed with digital watermark 0, a second frame group is superimposed with digital watermark 1, and so on, and when a specified number (e.g., 30000) is reached, it may start from the beginning. The digital watermark is superimposed directly into the picture and uses other non-gray colors (assuming red) for differentiation.

And after customizing the video source according to the specification, performing video quality detection by adopting the customized video source.

As shown in fig. 1, a method for detecting video quality in a video monitoring system according to the present technical solution includes:

and step S1, requesting a pre-customized video source through the video monitoring system to be detected, wherein the gray value of each frame in the GOP frame group in the pre-customized video source is different, and a preset digital watermark is superposed on each GOP frame group.

In order to detect the video monitoring system to be detected, the embodiment inputs a pre-customized video source into the video monitoring system to be detected, so that the client can request the video monitoring system to be detected. In order to realize convenience, a simulation IPC is adopted to register and be online on a video management platform to be monitored by a video to be detected, and a customized video source is used as an input stream of the simulation IPC, so that the simulation IPC can be requested through a client.

On the client, a decoder can be configured to put live streams of the simulated IPC on the wall, realize hard decoding and display video image frames on a television wall; the decoded video image frames can also be displayed on the display of the client by soft decoding.

It should be noted that, in the video source customized in advance by the present technical solution, the gray value of each frame in the GOP frame group is different, and each GOP frame group is superimposed with a preset digital watermark, which may be a continuous number or a pattern ordered according to a rule, and is not described here again.

And step S2, acquiring the decoded video image frame corresponding to the pre-customized video source.

There are two specific implementations of this step, which are illustrated by the following examples.