Quality evaluation method and device of traffic monitoring video, electronic equipment and storage medium

Abstract

The invention discloses a traffic monitoring video quality assessment method and device, electronic equipment and a storage medium, the method is applied to a monitoring system, and the method comprises the steps: obtaining to-be-assessed element information of a traffic monitoring video, the to-be-assessed element information comprises a to-be-assessed monitoring area, polling frequency and flow taking time limit, the to-be-evaluated monitoring area comprises a plurality of cameras, and the flow taking time limit represents the maximum duration of the monitoring system waiting for the flow taking response; determining a plurality of target cameras based on the to-be-evaluated monitoring area, the polling frequency and the flow taking time limit; obtaining a to-be-evaluated video stream of each target camera; and evaluating each to-be-evaluated video stream based on a preset evaluation strategy to obtain a quality evaluation result, the quality evaluation result being used for indicating the shooting quality of the camera in the to-be-evaluated monitoring area. By adopting the method provided by the invention, the accuracy of evaluating the quality of the traffic monitoring video can be improved.

Description

Technical Field

[0001] The present application relates to the field of video surveillance technology, and in particular to a method, device, electronic device, storage medium and computer program product for evaluating the quality of traffic surveillance videos. Background Art

[0002] In recent years, local transportation authorities have actively promoted the construction of transportation operation monitoring systems, and the visual management functions of the transportation industry have been continuously improved, and the service level has been continuously improved. However, due to the large differences in the construction time of video facilities, the scope of networking, and system functions of various regions, the process of transmitting traffic monitoring videos from front-end cameras to municipal, provincial, and ministerial platforms is affected by multiple factors such as multiple transmission network elements, multiple cascade platforms, unstable networks, and insufficient bandwidth. Traffic monitoring videos usually face the problem of inaccurate quality assessment, which makes it difficult to meet the needs of efficient operation of the road network, timely handling of emergencies, and providing high-quality travel services. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a method, device, electronic device, storage medium and computer program product for evaluating the quality of traffic surveillance videos, aiming to improve the accuracy of evaluating the quality of traffic surveillance videos.

[0004] The technical solution of the embodiment of the present application is implemented as follows: In a first aspect, the present application proposes a quality assessment method for traffic monitoring videos, which is applied to a monitoring system; the method comprises: Obtaining the element information to be evaluated of the traffic monitoring video, wherein the element information to be evaluated includes the monitoring area to be evaluated, the patrol frequency, and the flow collection time limit, wherein the monitoring area to be evaluated includes multiple cameras, and the flow collection time limit represents the maximum time length that the monitoring system waits for a flow collection response; Determine a plurality of target cameras based on the monitoring area to be evaluated, the patrol frequency and the flow limit time; Obtaining the video stream to be evaluated of each of the target cameras; Each of the video streams to be evaluated is evaluated based on a preset evaluation strategy to obtain a quality evaluation result, where the quality evaluation result is used to indicate the shooting quality of the camera in the monitoring area to be evaluated.

[0005] In one embodiment, the monitoring system includes a camera, and the camera is communicatively connected with each of the target cameras; after obtaining the video stream to be evaluated of each of the target cameras, the method further includes: Acquire status information sent by the camera, and determine the status of each of the target cameras based on the status information, wherein the status information includes information indicating whether the transmission status between the camera and each of the target cameras is normal or abnormal; The stream acquisition duration of each of the video streams to be evaluated is obtained, and the stream acquisition state of the monitoring system is determined based on the stream acquisition duration.

[0006] In one embodiment, determining the state of each of the target cameras based on the state information includes: If it is determined based on the status information that the transmission status between each of the target cameras and the video camera is normal, then it is determined that the status of each of the target cameras is normal.

[0007] In one embodiment, the preset evaluation strategy includes a preset image processing strategy and a preset scoring table; the step of evaluating each of the video streams to be evaluated based on the preset evaluation strategy to obtain a quality evaluation result includes: Performing image processing on each of the video streams to be evaluated based on the preset image processing strategy to obtain index information of the picture of each of the video streams to be evaluated, wherein the index information is used to indicate information of multiple indicators of the quality of the picture of the corresponding video stream to be evaluated; Determining the score of the index of each video stream to be evaluated based on the index information of each video stream to be evaluated and the preset scoring table, wherein the preset scoring table includes the score corresponding to when the index of each video stream to be evaluated is normal or abnormal; The quality assessment result is determined based on the score of the indicator of each video stream to be assessed.

[0008] In one embodiment, determining the quality assessment result based on the score of the indicator of each video stream to be assessed includes: Performing weighted sum processing on the scores of the indicators of each of the video streams to be evaluated to obtain a score for each of the video streams to be evaluated; A weighted summation process is performed based on the scores of each of the video streams to be evaluated to obtain the quality evaluation result.

[0009] In one embodiment, the index of each video stream to be evaluated includes the brightness of the picture of the video stream to be evaluated, whether there is jitter, rolling stripes, picture occlusion, picture freezing, image noise and picture blur, and whether it is displayed as a black and white image; the image processing is performed on each video stream to be evaluated based on the preset image processing strategy to obtain the index information of the picture of each video stream to be evaluated, including at least one of the following: Based on each of the video streams to be evaluated and a preset brightness detection algorithm, determining whether the brightness of the picture of each of the video streams to be evaluated is abnormal or normal; Based on each of the video streams to be evaluated, a preset image segmentation algorithm, a preset image matching algorithm, and a preset jitter frame judgment algorithm, determining whether a picture of each of the video streams to be evaluated has jitter; Based on each of the video streams to be evaluated, a preset gradient map generation algorithm and a preset straight line detection algorithm, determining whether there are scrolling stripes in the picture of each of the video streams to be evaluated; Based on each of the video streams to be evaluated, a preset background image extraction algorithm, a preset texture map acquisition and feature vector construction algorithm, and a preset similarity calculation and occlusion judgment algorithm, determining whether there is screen occlusion in the screen of each of the video streams to be evaluated; Based on each of the video streams to be evaluated, a preset image frame extraction algorithm, a preset histogram calculation algorithm, and a preset histogram similarity calculation and analysis algorithm, determining whether a picture of each of the video streams to be evaluated is frozen; Based on each of the video streams to be evaluated and a preset image noise evaluation algorithm, determining whether there is image noise in a picture of each of the video streams to be evaluated; Based on each of the video streams to be evaluated, a preset color space conversion algorithm, and a preset UV component separation degree analysis algorithm, determining whether the picture of each of the video streams to be evaluated is displayed as a black and white image; Based on each of the video streams to be evaluated, a preset frequency domain spectrum analysis algorithm and a preset regional average contrast statistics algorithm, it is determined whether a picture of each of the video streams to be evaluated has picture blur.

[0010] In one embodiment, performing weighted sum processing based on the scores of each of the video streams to be evaluated to obtain the quality evaluation result includes: Performing weighted summation processing based on the scores of each of the video streams to be evaluated and the preset weight coefficients corresponding to each of the target cameras to obtain the score of the monitoring area to be evaluated; The score of the monitored area to be evaluated is compared with a preset threshold, and the quality evaluation result is determined based on the comparison result.

[0011] In a second aspect, an embodiment of the present application provides a quality assessment device for a traffic monitoring video, which is applied to a monitoring system, including: A first data acquisition module is used to acquire the element information to be evaluated of the traffic monitoring video, wherein the element information to be evaluated includes the monitoring area to be evaluated, the patrol frequency and the flow collection time limit, the monitoring area to be evaluated includes multiple cameras, and the flow collection time limit represents the maximum time length that the monitoring system waits for the flow collection response; A target camera determination module, used to determine a plurality of target cameras based on the monitoring area to be evaluated, the patrol frequency and the flow limit time; A second data acquisition module is used to acquire the video stream to be evaluated of each target camera; The result generation module is used to evaluate each of the video streams to be evaluated based on a preset evaluation strategy to obtain a quality evaluation result, wherein the quality evaluation result is used to indicate the shooting quality of the camera in the monitoring area to be evaluated.

[0012] In a third aspect, an embodiment of the present application provides a monitoring system, comprising: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor, when running the computer program, executes the steps of the method described in the first aspect of the embodiment of the present application.

[0013] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect of the embodiment of the present application are implemented.

[0014] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect of the present application.

[0015] The technical solution provided in the embodiment of the present application first determines multiple target cameras in the monitoring area to be evaluated based on information such as the monitoring area to be evaluated, the patrol frequency, and the flow collection time limit. Then, the video stream to be evaluated of each target camera is pulled, and each video stream to be evaluated is evaluated based on a preset evaluation strategy to obtain a quality evaluation result. By pulling the video stream and evaluating the quality of the video stream, the true situation of the video quality of the traffic monitoring video can be obtained, thereby improving the accuracy of the quality evaluation of the traffic monitoring video. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a method for evaluating the quality of a traffic surveillance video according to an embodiment of the present application; Figure 2 A flow chart of a method for evaluating the quality of traffic surveillance video according to another embodiment of the present application; Figure 3 A flow chart of a method for evaluating the quality of traffic surveillance video according to another embodiment of the present application; Figure 4 A schematic diagram of the structure of a quality assessment device for traffic monitoring video according to an embodiment of the present application; Figure 5 A schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0019] In the related technologies, during the process of transmitting videos from front-end cameras to municipal, provincial, and ministerial platforms, there are many factors, such as multiple transmission network elements, multiple cascade platforms, unstable networks, and insufficient bandwidth. There is a problem that the video channel status is normal but the video cannot be viewed, and the video quality is usually determined based on the online status of the video. However, although the online status of the video is normal, the quality of the video may not meet the viewing requirements. Therefore, it is difficult to meet the needs of efficient operation of the road network, timely handling of emergencies, and providing high-quality travel services.

[0020] The embodiment of the present application provides a method for evaluating the quality of traffic monitoring videos. The method is applied in a monitoring system, that is, the execution subject is a monitoring system, which is an electronic device including multiple cameras. The electronic device can be any device that can execute the method for evaluating the quality of traffic monitoring videos, for example, it can be a terminal device or a server, etc., and the present application does not make any specific restrictions on this. Figure 1 As shown, the method includes: Step 101, obtaining the element information to be evaluated of the traffic monitoring video, the element information to be evaluated includes the monitoring area to be evaluated, the patrol frequency and the flow collection time limit, and the flow collection time limit represents the maximum time length that the monitoring system waits for the flow collection response.

[0021] Among them, waiting for a stream acquisition response refers to the stage in which the monitoring system waits for the camera to respond and start transmitting the video stream after sending a stream acquisition request during the process of acquiring the video stream from the camera. The time for waiting for a stream acquisition response is the time interval from when the monitoring system sends a stream acquisition request to when the camera starts transmitting video stream data.

[0022] During the t-th execution of the quality assessment method, the monitoring area to be assessed, the patrol frequency and the flow limit time are determined and pre-set before the method is executed, and t is a natural number.

[0023] The monitoring area to be evaluated can be adjusted according to the location / area classification. The patrol frequency is used to determine the number of cameras that the monitoring system uses to obtain traffic each time, and the patrol frequency can be adjusted according to the bandwidth. The time limit for obtaining traffic can be set manually. In this way, before the subsequent t+1th execution of the quality assessment method, the element information to be evaluated of the new traffic monitoring video can be obtained. That is, a new monitoring area to be evaluated, a new patrol frequency and / or a new time limit for obtaining traffic are obtained as the element information to be evaluated.

[0024] The monitoring area can be divided into administrative areas, such as county level, district / city level and provincial level.

[0025] Step 102, based on the monitoring area to be evaluated, the patrol frequency and the flow limit, determine multiple target cameras.

[0026] Specifically, the monitoring system first determines multiple target cameras based on the information of the elements to be evaluated. For example, according to the monitoring area to be evaluated, each camera used to monitor the monitoring area to be evaluated can be determined as the first candidate camera. Then, it is determined whether the flow acquisition time of each first candidate camera is less than the flow acquisition time limit, and the first candidate camera whose flow acquisition time is less than the flow acquisition time limit is determined as the second candidate camera. Finally, multiple cameras are randomly selected from multiple second candidate cameras as target cameras according to the patrol frequency.

[0027] It should be noted that when the bandwidth remains unchanged, the number of cameras that fetch the stream each time at the patrol frequency is fixed, but the cameras selected when fetching the stream are random.

[0028] Step 103: Obtain the video stream to be evaluated of each of the target cameras.

[0029] The monitoring system obtains the video stream to be evaluated of each target camera and also obtains the information of the video stream to be evaluated of each target camera. The information of the video stream to be evaluated includes at least the identification information of the camera, the area classification of the camera, the state signal of the camera and the timestamp information.

[0030] Step 104 , evaluating each video stream to be evaluated based on a preset evaluation strategy to obtain a quality evaluation result, where the quality evaluation result is used to indicate the shooting quality of the camera in the monitoring area to be evaluated.

[0031] The preset evaluation strategy is a preset strategy that can be used to evaluate the quality of the video stream.

[0032] By evaluating the quality of each video stream to be evaluated based on a preset evaluation strategy, a quality evaluation result can be obtained. The quality evaluation result can be used to indicate the shooting quality of the camera in the monitoring area to be evaluated.

[0033] The monitoring system is provided with a front end for users to view and operate. For example, the quality assessment results can be displayed on the front end, so as to instruct the user to take corresponding actions.

[0034] The technical solution provided by the present application obtains information on elements to be evaluated of a traffic monitoring video, wherein the information on elements to be evaluated includes a monitoring area to be evaluated, a patrol frequency, and a flow collection time limit, the monitoring area to be evaluated includes multiple cameras, and the flow collection time limit represents the maximum time that the monitoring system waits for a flow collection response; based on the monitoring area to be evaluated, the patrol frequency, and the flow collection time limit, multiple target cameras are determined; the video stream to be evaluated of each target camera is obtained; and each video stream to be evaluated is evaluated based on a preset evaluation strategy to obtain a quality evaluation result, and the quality evaluation result is used to indicate the shooting quality of the camera in the monitoring area to be evaluated.

[0035] That is, the present application first determines multiple target cameras in the monitoring area to be evaluated based on information such as the monitoring area to be evaluated, patrol frequency, and flow collection time limit. Then, the video stream to be evaluated of each target camera is pulled, and each video stream to be evaluated is evaluated based on a preset evaluation strategy to obtain a quality evaluation result. By pulling the video stream and evaluating the quality of the video stream, the true situation of the video quality of the traffic monitoring video can be obtained, thereby improving the accuracy of the quality evaluation of the traffic monitoring video.

[0036] In one embodiment, Figure 2 As shown, the monitoring system includes a camera, and the camera is communicatively connected with each of the target cameras; after obtaining the video stream to be evaluated of each of the target cameras, the method further includes: Step 201, obtaining status information sent by the camera, and determining the status of each target camera based on the status information, wherein the status information includes information indicating whether the transmission status between the camera and each target camera is normal or abnormal.

[0037] Step 202: Obtain the stream acquisition duration of each video stream to be evaluated, and determine the stream acquisition state of the monitoring system based on the stream acquisition duration.

[0038] Specifically, if the status information includes information indicating that the transmission status between the cameras is normal, the camera status is determined to be normal. If the status information includes information indicating that the transmission status between the cameras is abnormal, the camera status is determined to be abnormal.

[0039] The stream acquisition duration here refers to the time taken to pull the video stream to be evaluated, which is determined by the monitoring system during the process of executing the stream acquisition. If it is determined that the stream acquisition duration of the video stream to be evaluated exceeds the stream acquisition time limit, the state of the target camera corresponding to the video stream to be evaluated is determined to be abnormal. No subsequent quality assessment will be performed on the target camera with such an abnormal state. For example, for cameras with abnormal stream acquisition duration, brightness abnormality, video jitter, rolling stripes, screen occlusion, screen freezing, image noise, black screen, and blurred screen assessment will not be performed, and these indicator values ​​can all be set to "-", that is, null values.

[0040] That is, according to the duration of each video stream to be evaluated, it is determined whether to continue the subsequent quality evaluation for each target camera. In addition, the quality evaluation is mainly performed on the target cameras whose streaming duration does not exceed the streaming time limit.

[0041] In one embodiment, determining the status of each of the target cameras based on the status information includes: if it is determined based on the status information that the transmission status between each of the target cameras and the camera is normal, then determining that the status of each of the target cameras is normal.

[0042] The camera may have a built-in status reporting function, and send its own status information to the monitoring system through a network protocol (SNMP - simple network management protocol). The status information includes the network connection status and the data transmission status. During the communication connection between any target camera and the camera, when the report received by the monitoring system shows that the network connection is good and there is no abnormality in the data transmission, it can be determined that the transmission status between the target camera and the camera is normal. Otherwise, it is determined that the transmission status between the target camera and the camera is abnormal. Accordingly, the transmission status between the camera and the target camera is abnormal, indicating that the transmission channel between the camera and the target camera is not smooth. The transmission status between the camera and the target camera is normal, indicating that the transmission channel between the camera and the target camera is smooth.

[0043] The transmission status between the target camera and the camera is normal, indicating that the transmission channel between the target camera and the camera is smooth. It can be seen that the status of the target camera is normal.

[0044] In this embodiment, when it is determined based on the status information that the transmission status between the cameras is normal, the status of the camera is judged to be normal, thereby ensuring the accuracy of the evaluation of the status of the camera.

[0045] In one embodiment, Figure 3As shown, the preset evaluation strategy includes a preset image processing strategy and a preset scoring table; each video stream to be evaluated is evaluated based on the preset evaluation strategy to obtain a quality evaluation result, including: Step 301 : performing image processing on each video stream to be evaluated based on a preset image processing strategy to obtain index information of the picture of each video stream to be evaluated, where the index information is used to indicate multiple indexes of the quality of the picture of the corresponding video stream to be evaluated.

[0046] Among them, by performing image processing on each video stream to be evaluated based on a preset image processing strategy, index information of the picture of each video stream to be evaluated can be obtained. According to the index information, information of multiple indicators of the quality of the picture of the corresponding video stream to be evaluated can be determined. These indicators can be understood as indicators that are highly correlated with the evaluation system of the quality of the video picture (the correlation reaches a set correlation threshold).

[0047] Step 302: Determine the score of the index of each video stream to be evaluated based on the index information of each video stream to be evaluated and a preset scoring table. The preset scoring table includes the score corresponding to when the index of each video stream to be evaluated is normal or abnormal.

[0048] The scoring table is pre-set, including the identification of multiple indicators, and the score corresponding to each indicator when it is normal, and the score corresponding to each indicator when it is abnormal.

[0049] For example, for all indicators, when the indicator is normal, the corresponding score is 100 points, and when the indicator is abnormal, the corresponding score is 0 points.

[0050] According to the information of the multiple indicators indicated by the indicator information and the preset scoring table, the score corresponding to each indicator can be determined.

[0051] Step 303: Determine a quality evaluation result based on the score of the indicator of each video stream to be evaluated.

[0052] Specifically, for each video stream to be evaluated, the weight coefficient of each indicator is preset, the value range of the weight coefficient is [0, 1], and the sum of the weight coefficients of each indicator is 1; the score of each indicator and the preset weight coefficient corresponding to each indicator are weighted and summed to obtain the score of each video stream to be evaluated. The score of each video stream to be evaluated obtained here represents the shooting quality of the corresponding target camera.

[0053] After that, the scores of each video stream to be evaluated are weighted and summed according to the preset weight coefficients of each target camera to obtain the quality evaluation result. Here, the quality evaluation result represents the shooting quality of the camera in the monitoring area to be evaluated.

[0054] In this embodiment, by performing image processing on each video stream to be evaluated, the index information of each video stream to be evaluated is obtained. Based on the index information of each video stream to be evaluated and a preset scoring table, the score of the index of each video stream to be evaluated is determined. Based on the score of the index of each video stream to be evaluated, the quality evaluation result is determined, which can ensure the objectivity and accuracy of the obtained quality evaluation result.

[0055] In one embodiment, before executing the quality assessment method of traffic monitoring video, a quality assessment system of traffic monitoring video can be constructed, including device status, streaming status, brightness abnormality, video jitter, rolling stripes, screen occlusion, screen freeze, image noise, black screen, and blurred screen. For example, set the indicator to 100 points when normal and 0 points when abnormal, and set corresponding weights for each indicator.

[0056] In one embodiment, the indicators of each of the video streams to be evaluated include the brightness of the picture of the video stream to be evaluated, whether there is jitter, rolling stripes, picture occlusion, picture freezing, image noise and picture blur, and whether it is displayed as a black and white image; the image processing of each of the video streams to be evaluated based on the preset image processing strategy to obtain the indicator information of the picture of each of the video streams to be evaluated includes at least one of the following: based on each of the video streams to be evaluated and a preset brightness detection algorithm, determining whether the brightness of the picture of each of the video streams to be evaluated is abnormal or normal; based on each of the video streams to be evaluated, a preset image segmentation algorithm, a preset image matching algorithm and a preset jitter frame judgment algorithm, determining whether there is jitter in the picture of each of the video streams to be evaluated; based on each of the video streams to be evaluated, a preset gradient map generation algorithm and a preset straight line detection algorithm, determining whether there is rolling stripes in the picture of each of the video streams to be evaluated; based on each of the video streams to be evaluated, a preset gradient map generation algorithm and a preset straight line detection algorithm, determining whether there is rolling stripes in the picture of each of the video streams to be evaluated. Based on the frequency stream, the preset background image extraction algorithm, the preset texture map acquisition and feature vector construction algorithm and the preset similarity calculation and occlusion judgment algorithm, determine whether there is screen occlusion in the picture of each of the video streams to be evaluated; based on the video streams to be evaluated, the preset image frame extraction algorithm, the preset histogram calculation algorithm and the preset histogram similarity calculation and analysis algorithm, determine whether there is screen freezing in the picture of each of the video streams to be evaluated; based on the video streams to be evaluated and the preset image noise evaluation algorithm, determine whether there is image noise in the picture of each of the video streams to be evaluated; based on the video streams to be evaluated, the preset color space conversion algorithm and the preset UV component separation degree analysis algorithm, determine whether the picture of each of the video streams to be evaluated is displayed as a black and white image; based on the video streams to be evaluated, the preset frequency domain spectrum analysis algorithm and the preset regional average contrast statistics algorithm, determine whether there is screen blur in the picture of each of the video streams to be evaluated.

[0057] As mentioned above, this embodiment is executed when it is determined that the state of the target camera is normal based on the flow acquisition state.

[0058] (1) Evaluate brightness anomalies. This indicator mainly targets phenomena such as whitish images and dark images that make it difficult to distinguish objects. The detection method is to convert the screenshot image into a grayscale image and calculate the average pixel value of the grayscale image as the image brightness. If the image brightness is lower than 50 or higher than 200, it is evaluated as brightness anomaly, otherwise it is normal. The detection method is the preset brightness detection algorithm.

[0059] (2) Evaluate video jitter. This indicator mainly targets unexpected, irregular shaking or vibration in the picture. The detection method is to divide two consecutive frames of the video stream into multiple sub-blocks and determine the coverage of the matching window of the source sub-block in the subsequent frame image. The matching window is the area to which the source sub-block may move, and its size can be set according to the expected maximum jitter range. Traverse and search within the matching window, obtain the sub-block that best matches the source sub-block as the target sub-block through similarity measurement, and calculate the motion vector between the source sub-block and the target sub-block. By judging whether there is an abnormal change in the size or direction of the motion vector between consecutive frames, it is judged whether it is a jitter frame and the jitter frame count is performed. If the jitter frame count exceeds the threshold, it is judged that the surveillance video is jittery. The algorithms involved in evaluating video jitter include a preset image segmentation algorithm, a preset image matching algorithm, and a preset jitter frame judgment algorithm.

[0060] (3) Evaluation of rolling stripes. This test targets horizontal stripes, vertical stripes, mesh stripes and other phenomena that appear in the picture. The detection method is to make a gradient map in the x and y directions of the image data to enhance the contrast between the stripe area and other areas in the image, thereby highlighting the stripe characteristics. Then, a straight line detection is performed on the gradient image. If the length, direction and motion information of the straight line meet the typical characteristics of rolling stripes (such as consistent length, same direction, and regular movement in consecutive frames), it is determined that rolling stripes exist in the surveillance video. The algorithms involved in evaluating rolling stripes include a preset gradient map generation algorithm and a preset straight line detection algorithm.

[0061] (4) Evaluate screen occlusion. This test targets the phenomenon that the camera is blocked by foreign objects and affects the monitoring effect. Extract a background image from the unobstructed monitoring video as a reference background image; extract a background image from the monitoring video to be detected as the background image to be detected; obtain the texture map of the reference background image and construct a reference feature vector; obtain the texture map of the background image to be detected and construct a feature vector to be detected; calculate the similarity between the reference feature vector and the feature vector to be detected. If the similarity is lower than the threshold, it is determined that the monitoring video is blocked. The algorithms involved in evaluating screen occlusion include a preset background image extraction algorithm, a preset texture map acquisition and feature vector construction algorithm, and a preset similarity calculation and occlusion judgment algorithm.

[0062] (5) Screen freeze assessment: This test targets the phenomenon where the video stream stops updating. This test extracts an image frame at regular intervals from the video frame and analyzes its color histogram. The histogram similarity between consecutive frames is statistically analyzed. If the similarity exceeds a threshold, the screen is judged to be frozen. The algorithms involved in evaluating screen freeze include a preset image frame extraction algorithm, a preset histogram calculation algorithm, and a preset histogram similarity calculation and analysis algorithm.

[0063] (6) Image noise assessment. This test targets interference phenomena such as random changes in brightness or color information in image data. The detection method is frequency domain characteristic analysis. The image is converted into a grayscale image and Fourier transform is performed to convert it from the spatial domain to the frequency domain. If the energy of the high-frequency component exceeds the threshold, it is considered that image noise exists. The algorithms involved in evaluating image noise include a preset image noise assessment algorithm.

[0064] (7) Evaluate black and white images. This test is aimed at the phenomenon that the screen is displayed as a black and white image (no color information). The algorithm is relatively simple to implement. It can convert the image data into the YUV color space, analyze the separation of the UV component, and compare it with the set empirical threshold to obtain the algorithm detection result. The algorithms involved in evaluating black and white images include the preset color space conversion algorithm and the preset UV component separation analysis algorithm.

[0065] (8) Evaluation of image blur. This test targets the phenomenon of unclear objects in the image, empty space in the image, low image contrast, etc. In terms of algorithm implementation, the image data can be subjected to spectrum analysis in the frequency domain or the image can be divided into N regions of equal size and their average contrast can be calculated. The algorithms involved in evaluating image blur include the preset frequency domain spectrum analysis algorithm and the preset regional average contrast statistical algorithm.

[0066] It should be noted that the above various preset algorithms have been trained and stored in the monitoring system. When evaluating the quality of the video stream, one, multiple or all of the above indicators can be selected as indicators for quality evaluation.

[0067] In this embodiment, by pulling the video stream to be evaluated from the target camera, and using the device status, stream acquisition status, brightness abnormality, video jitter, rolling stripes, screen occlusion, screen freeze, image noise, black and white image, and image blur as quality assessment indicators, the dimensions of quality assessment are enriched, which is conducive to improving the accuracy of quality assessment of traffic monitoring videos.

[0068] In one embodiment, a weighted summation process is performed based on the scores of each of the video streams to be evaluated to obtain the quality assessment result, including: performing a weighted summation process based on the scores of each of the video streams to be evaluated and the preset weight coefficients corresponding to each of the target cameras to obtain the score of the monitoring area to be evaluated; comparing the score of the monitoring area to be evaluated with a preset threshold, and determining the quality assessment result based on the comparison result.

[0069] Here, the preset threshold is the lower limit of the quality of the surveillance video that is set to meet the standard. After obtaining the score of the surveillance area to be evaluated, the score of the surveillance area to be evaluated is compared with the preset threshold. If it is determined that the score of the surveillance area to be evaluated is greater than or equal to the preset threshold, the quality evaluation result is determined to be that the shooting quality of the camera of the surveillance area to be evaluated meets the standard. If it is determined that the score of the surveillance area to be evaluated is less than the preset threshold, the quality evaluation result is determined to be that the shooting quality of the camera of the surveillance area to be evaluated does not meet the standard.

[0070] In one embodiment, after the quality assessment result is obtained, the quality assessment result may also be sent to a front end of a monitoring system for display, thereby realizing visualization of the quality assessment result.

[0071] In order to implement the method of the embodiment of the present application, the embodiment of the present application also provides a quality assessment device for traffic monitoring videos. The quality assessment device for traffic monitoring videos corresponds to the above-mentioned quality assessment method for traffic monitoring videos, and each step in the embodiment of the above-mentioned quality assessment method for traffic monitoring videos is also fully applicable to the embodiment of the quality assessment device for traffic monitoring videos.

[0072] like Figure 4 As shown, the traffic monitoring video quality assessment device 400 includes: a first data acquisition module 401, a target camera determination module 402, a second data acquisition module 403 and a result generation module 404.

[0073] Among them, the first data acquisition module 401 is used to obtain the element information to be evaluated of the traffic monitoring video, the element information to be evaluated includes the monitoring area to be evaluated, the patrol frequency and the flow limit, the monitoring area to be evaluated includes multiple cameras, and the flow limit represents the maximum time length that the monitoring system waits for a flow response; the target camera determination module 402 is used to determine multiple target cameras based on the monitoring area to be evaluated, the patrol frequency and the flow limit; the second data acquisition module 403 is used to obtain the video stream to be evaluated of each of the target cameras; the result generation module 404 is used to evaluate each of the video streams to be evaluated based on a preset evaluation strategy to obtain a quality evaluation result, and the quality evaluation result is used to indicate the shooting quality of the camera in the monitoring area to be evaluated.

[0074] In one embodiment, the quality assessment device for traffic monitoring videos also includes: a status determination module, the monitoring system includes a camera, and the camera is communicatively connected with each of the target cameras; after obtaining the video stream to be evaluated of each of the target cameras, the status determination module is used to: obtain the status information sent by the camera, and determine the status of each of the target cameras based on the status information, wherein the status information includes information indicating whether the transmission status between the camera and each of the target cameras is normal or abnormal; obtain the stream acquisition time length of each of the video streams to be evaluated, and determine the stream acquisition status of the monitoring system based on the stream acquisition time length.

[0075] In one embodiment, the status determination module determines the status of each of the target cameras based on the status information, including: if it is determined based on the status information that the transmission status between each of the target cameras and the camera is normal, then determining that the status of each of the target cameras is normal.

[0076] In one embodiment, the preset evaluation strategy includes a preset image processing strategy and a preset scoring table; a result generation module evaluates each of the video streams to be evaluated based on the preset evaluation strategy to obtain a quality evaluation result, including: performing image processing on each of the video streams to be evaluated based on the preset image processing strategy to obtain index information of the picture of each of the video streams to be evaluated, the index information is used to indicate information of multiple indicators of the quality of the picture of the corresponding video stream to be evaluated; determining the score of the index of each of the video streams to be evaluated based on the index information of each of the video streams to be evaluated and the preset scoring table, the preset scoring table including the score corresponding to when the index of each of the video streams to be evaluated is normal or abnormal; determining the quality evaluation result based on the score of the index of each of the video streams to be evaluated.

[0077] It should be noted that: the quality assessment device for traffic monitoring videos provided in the above embodiments only uses the division of the above program modules as an example when performing the quality assessment of traffic monitoring videos. In practical applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the quality assessment device for traffic monitoring videos provided in the above embodiments and the quality assessment method embodiment for traffic monitoring videos belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0078] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiment of the present application, the embodiment of the present application also provides a monitoring system. Figure 5 Only an exemplary structure of the monitoring system is shown, not all structures, and can be implemented as needed. Figure 5 Partial or complete structure shown.

[0079] like Figure 5 As shown, the monitoring system 500 provided in the embodiment of the present application includes: at least one processor 501, a memory 502, a user interface 503 and at least one network interface 504. The various components in the monitoring system 500 are coupled together through a bus system 505. It can be understood that the bus system 505 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 505 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 5 In the figure, various buses are labeled as bus system 505. Among them, the user interface 503 may include a display, keyboard, mouse, trackball, click wheel, key, button, touch pad or touch screen. The memory 502 in the embodiment of the present application is used to store various types of data to support the operation of the monitoring system. Examples of these data include: any computer program used to operate on the monitoring system.

[0080] The quality assessment method of traffic monitoring video disclosed in the embodiment of the present application can be applied to the processor 501, or implemented by the processor 501. The processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the quality assessment method of traffic monitoring video can be completed by the hardware integrated logic circuit or software instructions in the processor 501. The above-mentioned processor 501 can be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 501 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiment of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 502. The processor 501 reads the information in the memory 502 and completes the steps of the quality assessment method of traffic monitoring video provided in the embodiment of the present application in combination with its hardware.

[0081] In an exemplary embodiment, the monitoring system may be implemented by one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), general purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0082] It can be understood that the memory 502 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0083] In an exemplary embodiment, the present application also provides a computer storage medium, which can be a computer-readable storage medium, for example, a memory 502 storing a computer program, and the computer program can be executed by a processor 501 of the monitoring system to complete the steps described in the method of the present application embodiment. The computer-readable storage medium can be a memory such as a ROM, a PROM, an EPROM, an EEPROM, a Flash Memory, a magnetic surface memory, an optical disk, or a CD-ROM.

[0084] An embodiment of the present application further provides a computer program product, including a computer program, which implements the steps of any of the above methods when executed by a processor.

[0085] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0086] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0087] The above is only a specific implementation method 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 covered by the protection scope of the present application.

Claims

1. A quality assessment method for traffic monitoring video, applied to a monitoring system; characterized in that: The method comprises: Obtaining the element information to be evaluated of the traffic monitoring video, wherein the element information to be evaluated includes the monitoring area to be evaluated, the patrol frequency, and the flow collection time limit, wherein the monitoring area to be evaluated includes multiple cameras, and the flow collection time limit represents the maximum time length that the monitoring system waits for a flow collection response; Determine a plurality of target cameras based on the monitoring area to be evaluated, the patrol frequency and the flow limit time; Obtaining the video stream to be evaluated of each of the target cameras; Each of the video streams to be evaluated is evaluated based on a preset evaluation strategy to obtain a quality evaluation result, where the quality evaluation result is used to indicate the shooting quality of the camera in the monitoring area to be evaluated.

2. The method according to claim 1, characterized in that The monitoring system includes a camera, and the camera is communicatively connected with each of the target cameras; After obtaining the video stream to be evaluated of each of the target cameras, the method further includes: Acquire status information sent by the camera, and determine the status of each of the target cameras based on the status information, wherein the status information includes information indicating whether the transmission status between the camera and each of the target cameras is normal or abnormal; The stream acquisition duration of each of the video streams to be evaluated is obtained, and the stream acquisition state of the monitoring system is determined based on the stream acquisition duration.

3. The method according to claim 2, characterized in that The determining the state of each of the target cameras based on the state information includes: If it is determined based on the status information that the transmission status between each of the target cameras and the video camera is normal, then it is determined that the status of each of the target cameras is normal.

4. The method according to claim 2, characterized in that: The preset evaluation strategy includes a preset image processing strategy and a preset scoring table; the step of evaluating each of the video streams to be evaluated based on the preset evaluation strategy to obtain a quality evaluation result includes: Performing image processing on each of the video streams to be evaluated based on the preset image processing strategy to obtain index information of the picture of each of the video streams to be evaluated, wherein the index information is used to indicate information of multiple indicators of the quality of the picture of the corresponding video stream to be evaluated; Determining the score of the index of each video stream to be evaluated based on the index information of each video stream to be evaluated and the preset scoring table, wherein the preset scoring table includes the score corresponding to when the index of each video stream to be evaluated is normal or abnormal; The quality assessment result is determined based on the score of the indicator of each video stream to be assessed.

5. The method according to claim 4, characterized in that The step of determining the quality assessment result based on the score of the indicator of each of the video streams to be assessed includes: Performing weighted sum processing on the scores of the indicators of each of the video streams to be evaluated to obtain a score for each of the video streams to be evaluated; A weighted summation process is performed based on the scores of each of the video streams to be evaluated to obtain the quality evaluation result.

6. The method according to claim 4, characterized in that The indicators of each of the video streams to be evaluated include the brightness of the picture of the video stream to be evaluated, whether there is jitter, rolling stripes, picture occlusion, picture freezing, image noise and picture blur, and whether it is displayed as a black and white image; the image processing of each of the video streams to be evaluated based on the preset image processing strategy to obtain the indicator information of the picture of each of the video streams to be evaluated includes at least one of the following: Based on each of the video streams to be evaluated and a preset brightness detection algorithm, determining whether the brightness of the picture of each of the video streams to be evaluated is abnormal or normal; Based on each of the video streams to be evaluated, a preset image segmentation algorithm, a preset image matching algorithm, and a preset jitter frame judgment algorithm, determining whether a picture of each of the video streams to be evaluated has jitter; Based on each of the video streams to be evaluated, a preset gradient map generation algorithm and a preset straight line detection algorithm, determining whether there are scrolling stripes in the picture of each of the video streams to be evaluated; Based on each of the video streams to be evaluated, a preset background image extraction algorithm, a preset texture map acquisition and feature vector construction algorithm, and a preset similarity calculation and occlusion judgment algorithm, determining whether there is screen occlusion in the screen of each of the video streams to be evaluated; Based on each of the video streams to be evaluated, a preset image frame extraction algorithm, a preset histogram calculation algorithm, and a preset histogram similarity calculation and analysis algorithm, determining whether a picture of each of the video streams to be evaluated is frozen; Based on each of the video streams to be evaluated and a preset image noise evaluation algorithm, determining whether there is image noise in a picture of each of the video streams to be evaluated; Based on each of the video streams to be evaluated, a preset color space conversion algorithm, and a preset UV component separation degree analysis algorithm, determining whether the picture of each of the video streams to be evaluated is displayed as a black and white image; Based on each of the video streams to be evaluated, a preset frequency domain spectrum analysis algorithm and a preset regional average contrast statistics algorithm, it is determined whether a picture of each of the video streams to be evaluated has picture blur.

7. The method according to claim 5, characterized in that The step of performing weighted summation processing based on the scores of each of the video streams to be evaluated to obtain the quality evaluation result includes: Performing weighted summation processing based on the scores of each of the video streams to be evaluated and the preset weight coefficients corresponding to each of the target cameras to obtain the score of the monitoring area to be evaluated; The score of the monitored area to be evaluated is compared with a preset threshold, and the quality evaluation result is determined based on the comparison result.

8. A quality assessment device for traffic monitoring video, applied to a monitoring system, characterized in that: The device comprises: A first data acquisition module is used to acquire the element information to be evaluated of the traffic monitoring video, wherein the element information to be evaluated includes the monitoring area to be evaluated, the patrol frequency and the flow collection time limit, the monitoring area to be evaluated includes multiple cameras, and the flow collection time limit represents the maximum time length that the monitoring system waits for the flow collection response; A target camera determination module, used to determine a plurality of target cameras based on the monitoring area to be evaluated, the patrol frequency and the flow limit time; A second data acquisition module is used to acquire the video stream to be evaluated of each target camera; The result generation module is used to evaluate each of the video streams to be evaluated based on a preset evaluation strategy to obtain a quality evaluation result, wherein the quality evaluation result is used to indicate the shooting quality of the camera in the monitoring area to be evaluated.

9. A monitoring system, characterized in that: The method comprises a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is used to execute the steps of the method according to any one of claims 1 to 7 when running the computer program.

10. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images