A video stream detection system, method and device in a security cascade scene

Abstract

The application relates to a video stream detection system, method and equipment in a security cascade scene. The system comprises a patrol center, a distributed detection cluster and to-be-detected video channel information; wherein the patrol center comprises at least two patrol nodes, and the distributed detection cluster comprises at least two detection nodes; the patrol node is used for issuing a detection task to the corresponding detection node according to the acquired customer demand; the detection node is used for determining corresponding target to-be-detected video channel information from the to-be-detected video channel information based on the detection task, pulling corresponding to-be-detected video based on the target to-be-detected video channel information and performing detection, and pushing a detection result to the patrol center to generate a corresponding perception video detection result. Through the application, various different application environments can be adapted, the server specification requirement is reduced, and the video detection accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of video detection, in particular to a video stream detection system, method and device in a security cascade scene. BACKGROUND

[0002] A conventional multi-level video convergence monitoring platform video detection analysis composition structure includes a county video access platform 1-N responsible for the access and management capability of the video equipment, which internally contains a streaming media service (or cluster) responsible for forwarding media data streams to multiple clients for pulling video stream viewing or storage, playing a role in relieving the front-end device pressure and saving network access layer bandwidth, a city bureau video convergence platform converging all video points of each county together to shield various complex device interfaces for upper-layer business applications, and an intelligent operation and maintenance platform located at the upper level to make operation and maintenance business such as video detection analysis business with all video points of the city bureau convergence platform. However, if video stream / recording stream detection analysis is performed on the city bureau platform, due to problems such as long link, unstable network, and large network resource occupation, the city bureau platform will be under too much pressure, real-time video cannot be viewed, and the detected results may also be inaccurate, affecting the normal use of upper-layer business functions.

[0003] At present, an effective solution has not been proposed for the problems of high requirement for server resources and poor adaptability to different environments in the prior art. SUMMARY

[0004] Therefore, it is necessary to provide a video stream detection system, method and device in a security cascade scene to solve the above technical problems.

[0005] In a first aspect, the present application provides a video stream detection system in a security cascade scene. The system includes a patrol center, a distributed detection cluster, and to-be-detected video channel information, wherein the patrol center includes at least two patrol nodes, and the distributed detection cluster includes at least two detection nodes.

[0006] The patrol node is configured to issue a detection task to a corresponding detection node according to the acquired customer demand.

[0007] The detection node is configured to determine corresponding target to-be-detected video channel information from the to-be-detected video channel information based on the detection task, pull corresponding to-be-detected video based on the target to-be-detected video channel information, and perform detection, and push the detection result to the patrol center to generate a corresponding perception video detection result.

[0008] In one of the embodiments, the system further includes a dispatch center, wherein the dispatch center is in communication with the patrol center.

[0009] The dispatch center is configured to set a timed video stream detection task.

[0010] The scheduling center is further configured to instruct the corresponding inspection node to start performing the video stream detection task when the timing video stream detection task is triggered.

[0011] In one of the embodiments, the system further comprises a data transfer cluster and a data storage cluster; wherein the inspection center is connected to the data transfer cluster and the data storage cluster respectively;

[0012] The data storage cluster is configured to persistently store the detection rule information for each detection task;

[0013] The data transfer cluster is configured to deliver the detection result.

[0014] In one of the embodiments, the inspection node is further configured to automatically issue a re-inspection task to the corresponding inspection node based on the detection result after generating the detection result;

[0015] The re-inspection task comprises determining an abnormal video result according to the detection result, and performing a loop re-inspection on the abnormal video result until the number of re-inspections reaches a preset re-inspection threshold to obtain a final detection result, wherein the number of video streams for each round of re-inspection decreases successively with the increase of the loop round.

[0016] In one of the embodiments, the inspection center is further configured to obtain platform domain information and IP information of each detection node, and match the to-be-detected video channel information with the detection nodes based on the platform domain information and the IP information, determine a target detection node matched with the to-be-detected video channel information from all the detection nodes, and issue a detection task for the corresponding to-be-detected video channel information to the target detection node.

[0017] In one of the embodiments, the inspection center is further configured to traverse each detection node to determine whether there is an abnormal state in each detection node;

[0018] The inspection center is further configured to, when detecting that there is an abnormal detection node in an abnormal state in the detection nodes, match the to-be-detected video channel information corresponding to the abnormal detection node with the nodes other than the abnormal detection node in the detection nodes, and determine a final detection node.

[0019] The inspection center is further configured to issue the corresponding to-be-detected video channel information to the final detection node.

[0020] In one of the embodiments, the distributed detection cluster is further configured to traverse each detection node, and end the detection task and return the detection result to the inspection center when detecting that all the detection nodes have completed the detection of the to-be-detected video corresponding to the to-be-detected video channel information.

[0021] In a second aspect, the application further provides a video stream detection method in a security cascade scenario. The method is applied to the system as above, and comprises the following steps:

[0022] The at least two inspection nodes included in the inspection center distribute detection tasks to the detection nodes in the corresponding distributed detection cluster according to the obtained customer demand; wherein the detection nodes determine corresponding target to-be-detected video channel information from the to-be-detected video channel information, pull corresponding to-be-detected videos based on the target to-be-detected video channel information and perform detection, push the detection results to the inspection center, and generate corresponding perception video detection results.

[0023] In a third aspect, the application further provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0024] The at least two inspection nodes included in the inspection center distribute detection tasks to the detection nodes in the corresponding distributed detection cluster according to the obtained customer demand; wherein the detection nodes determine corresponding target to-be-detected video channel information from the to-be-detected video channel information, pull corresponding to-be-detected videos based on the target to-be-detected video channel information and perform detection, push the detection results to the inspection center, and generate corresponding perception video detection results.

[0025] In a fourth aspect, the application further provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0026] The at least two inspection nodes included in the inspection center distribute detection tasks to the detection nodes in the corresponding distributed detection cluster according to the obtained customer demand; wherein the detection nodes determine corresponding target to-be-detected video channel information from the to-be-detected video channel information, pull corresponding to-be-detected videos based on the target to-be-detected video channel information and perform detection, push the detection results to the inspection center, and generate corresponding perception video detection results.

[0027] The aforementioned video stream detection system, method, and device for a security cascading scenario include an inspection center, a distributed detection cluster, and information on video channels to be detected. The inspection center includes multiple inspection nodes, and the distributed detection cluster includes multiple detection nodes. Inspection nodes are used to issue detection tasks to corresponding detection nodes according to customer needs. Detection nodes are used to determine the corresponding target video channel information from the information on video channels to be detected based on the detection tasks, retrieve the corresponding video to be detected based on the target video channel information, perform detection, and push the detection results back to the inspection center to generate corresponding perceived video detection results. This application improves the structure of the video stream detection system, thereby adapting to various application environments. Furthermore, this application has low requirements for the server specifications of the detection and analysis nodes, reducing hardware resource investment. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of the structure of a video stream detection system in one embodiment;

[0029] Figure 2 This is a schematic diagram of the video stream detection system in another embodiment;

[0030] Figure 3 This is a schematic diagram of the re-inspection results in one embodiment;

[0031] Figure 4 This is a schematic diagram of the video stream detection method in a preferred embodiment;

[0032] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0034] In one embodiment, such as Figure 1 As shown, a video stream detection system for a security cascading scenario is provided, including an inspection center, a distributed detection cluster, and information on the video channel to be detected; wherein, the inspection center includes at least two inspection nodes 11, and the distributed detection cluster includes at least two detection nodes 12;

[0035] Inspection node 11 is used to issue inspection tasks to the corresponding inspection node 12 based on the obtained customer requirements;

[0036] The detection node 12 is configured to determine corresponding target video channel information to be detected from the video channel information to be detected based on a detection task, pull corresponding video to be detected based on the target video channel information to be detected, and perform detection, and push the detection result to the inspection center to generate corresponding perception video detection result.

[0037] Specifically, in order to solve the problem of video stream detection and analysis performance of a large number of video devices, the inspection center supports multi-node deployment to improve the reliability and throughput of detection and analysis result processing, and the video detection module also adopts a distributed detection cluster mode to improve the concurrent performance and reliability of video stream pulling and detection analysis. The inspection center is connected with the client to obtain the customer demand issued by the client, and issues a detection task to the corresponding detection node 12 according to the customer demand. In actual application, the customer demand is mostly a video detection and analysis instruction issued by the client, wherein the detection node 12 is mostly a different device for detecting video stream belonging to the distributed detection cluster, and is mostly configured by a related technical personnel with configuration information (such as detection index, detection device information, detection trigger time, etc.) required for video detection and analysis. In actual application, the above detection node 12 is generally deployed in a horizontal multi-node mode to form the above distributed detection cluster, that is, a plurality of servers are concentrated together, each server implements the same business, and the main role is to perform task dispersion to improve detection performance. At the same time, if a detection node fails, the node can also support failover to ensure the reliability of video detection and analysis. The above detection task is mostly issued by the user to detect a batch or a certain collected video stream. Further, in the embodiment, the detection task can be issued to a suitable detection node 12, such as issuing the detection task of a certain region to the detection node 12 closest to the region, or issuing the detection task of a certain region to the detection node 12 with the best performance, etc. In actual application, the allocation of the detection task can be determined by a related technical personnel according to the actual situation. It should be noted that the present application does not directly allocate the video to be detected, but allocates the video channel information to be detected to the detection node 12, wherein the video channel information to be detected includes but is not limited to video acquisition device encoding, video device access domain, video device label, video device IP address, etc. After the detection node 12 obtains the target video channel information to be detected corresponding to the detection task, the detection node 12 pulls the corresponding video resource to be detected from the streaming media cluster according to the above target video channel information to be detected, and performs detection. Finally, the detection result is pushed to the inspection center, and the inspection center generates a corresponding perception video detection result, which can be a standard visual report generated by the inspection center, etc., and is fed back to the client for the user to view. In actual application, a large number of video channel information to be detected needs to be detected, at which time different video channel information to be detected can be allocated to different detection nodes 12 according to actual needs, so as to improve detection efficiency and accuracy.

[0038] Through the application, the inspection center and the detection cluster with multiple nodes are deployed, so that all to-be-detected videos can be avoided from being converged at one point / platform, and the problem of excessive platform pressure can be effectively avoided. In the application, the to-be-detected video channel information is distributed instead of directly distributing the to-be-detected videos, so that the hardware requirements of each node are reduced on the basis of improving the overall video detection efficiency, and the detection efficiency is improved, thereby avoiding affecting the normal use of the upper-layer business functions.

[0039] In one of the embodiments, the system further comprises a dispatch center 21, wherein the dispatch center 21 is in communication with the inspection center;

[0040] The dispatch center 21 is configured to set a timed video stream detection task.

[0041] The dispatch center 21 is further configured to instruct the corresponding inspection node to start performing the video stream detection task when the timed video stream detection task is triggered.

[0042] Specifically, the inspection nodes are all deployed on the server in a micro-service manner, and preferably, the inspection nodes are not different in function. The dispatch center 21 and the inspection center can communicate with each other. In actual application, the inspection center can register the dispatch task to the dispatch center 21 according to the customer demand obtained from the client, and the dispatch center 21 is responsible for setting the detection task. The detection task can be time-set, such as being set to trigger the corresponding task immediately after receiving the video stream detection task, or being set to trigger the video stream detection task at a specific time according to actual needs, such as being configured to execute the video stream detection task at 8:55 every morning, or being configured to execute the video stream detection task at 2:10 next week, etc. When the timed video stream detection task set by the dispatch center 21 is triggered, it is fed back to the corresponding inspection node, instructing the inspection node to start performing the corresponding video stream detection task. Through the cooperation of the dispatch center 21 and the inspection center, flexible detection of a large number of videos can be realized, so that the system can be more flexible to adapt to different application scenarios.

[0043] In one of the embodiments, the system further comprises a data transfer cluster and a data storage cluster; wherein the inspection center is connected with the data transfer cluster and the data storage cluster respectively;

[0044] The data storage cluster is configured to persistently store the detection rule information for each detection task.

[0045] The data transfer cluster is configured to deliver the detection results.

[0046] Specifically, Figure 2For a schematic diagram of the video stream detection system structure in one embodiment, the inspection center is connected with a data storage cluster and a data transfer cluster respectively. The data storage cluster usually also includes a plurality of data storage nodes 23, and different data storage nodes 23 are used to persistently store configuration information of detection tasks, final video detection results and the like, and in this embodiment, a plurality of data storage nodes 23 are included, and if a faulty node appears, other nodes can take over the work, thereby forming a high-reliability data storage capability to avoid losses caused by single-point failures. The detection rules of the detection task include but are not limited to determining the need for detection of the to-be-detected resource, specifying the detection index item, whether it needs to be rechecked, the rechecking strategy, the triggering time, etc. In some embodiments, the data storage cluster can also be used to realize the persistent storage of data. The above-mentioned data transfer cluster usually also includes a plurality of data transfer nodes 22, and each data transfer node 22 is used to decouple the data interaction between the inspection node and the detection node, and reduce the inter-service dependency. In actual application, the capabilities of each data transfer node 22 are basically the same, and setting multiple data transfer nodes 22 can improve the data transfer capability, and the data transfer cluster can also assist in realizing the transmission of asynchronous messages. Asynchronous message transmission can realize message decoupling between services, improve detection performance and reduce inter-service dependency. After completing the analysis of the to-be-detected video, the detection result is pushed to the intermediate storage medium, i.e. the above-mentioned data transfer cluster, and then the inspection service is responsible for persistently storing the detection result, thereby realizing the message transmission and cooperation capability between multiple services in a video stream detection and analysis process. Through the data transfer cluster, the data is pushed to the inspection center, which can reduce the pressure of the inspection node receiving the detection result generated by the detection node, and also realize the asynchronous processing capability. It can be understood that if the detection node directly pushes the detection result to the inspection node, the inspection node needs to ensure that no exception occurs, which greatly improves the requirements for the inspection node, and if the detection result is directly pushed to the inspection node, the inspection node needs to perform additional logical processing, which will also slow down the performance of the detection node.

[0047] In one embodiment, the inspection node is also used to automatically issue a rechecking task to the corresponding inspection node based on the detection result after generating the detection result.

[0048] The rechecking task includes determining an abnormal video result based on the detection result, and performing cyclic rechecking on the abnormal video result until the number of rechecks reaches a preset rechecking threshold, thereby obtaining a final detection result. With the increase of the cycle number, the number of video streams rechecked in each cycle is gradually reduced.

[0049] Specifically, in actual application, some interference factors may occur, such as network jitter, large streaming media pressure and the like, which may cause false detection with a large probability. In order to improve the detection accuracy, the patrol inspection node in the embodiment also supports an automatic re-inspection function. After each round of detection task is completed, the patrol inspection service can re-issue detection according to the detection result and pre-configured resources, filter out abnormal video results that need to be re-inspected from the detected abnormal results for cyclic re-inspection, until the re-inspection times reach a re-inspection times threshold, and obtain a final detection result. The filtering method for the abnormal video results includes but is not limited to: after obtaining the detection result through the first video detection task, a preset number of video stream data are randomly extracted from the abnormal detection result as the abnormal video results for re-inspection; or the abnormal video results are extracted from the detection result according to a pre-set filtering strategy, which includes but is not limited to: detecting the environment in which the video in the detection result is located, if the environmental factor meets the pre-set environmental requirement, the video is determined as the abnormal video result and is re-inspected, and the like. It can be understood that the filtering method for the abnormal video result in the embodiment is not limited, and all methods that can determine the abnormal video result from the detection result should fall within the protection scope of the present application.

[0050] Further, the re-inspection task in the embodiment usually includes multiple rounds of re-inspection tasks, and with the increase of the cycle times, the number of video streams re-inspected in each round is gradually reduced, that is, after the first round of detection on the video to be detected is completed, the video that needs to be re-inspected in the second round is filtered out from the detection result of the first round, and after the second round of detection result of the second round of re-inspection video is obtained, the video that needs to be re-inspected in the third round is filtered out from the second round of detection result, and the like. The above cyclic re-inspection method is repeated until the number of re-inspections reaches a pre-set re-inspection times threshold (such as 3 times), and it needs to be noted that considering the detection accuracy and detection speed in actual application, the number of re-inspection videos in each round should be less than the number of re-inspection videos in the previous round. For example, 150 abnormal detection results are obtained through the first video detection task, and in the second round, 100 video stream data are randomly extracted from the 150 abnormal detection results for re-inspection, 50 abnormal results are obtained through the second round of re-inspection task, and in the third round, 20 videos are extracted from the 50 abnormal results for re-inspection, and the like, until the number of re-inspections reaches the pre-set re-inspection times threshold. In some preferred embodiments, when the re-inspection task is performed, the re-inspection trigger time (such as 13:00 to start re-inspection, or 2h after the detection result is obtained to perform re-inspection, and the like) is also supported, and the re-inspection resources are also supported, and the like. Through the automatic re-inspection task, the video detection and analysis accuracy can be significantly improved, and the influence of the interference factors on the detection result can be reduced, such as Figure 3For an embodiment, after two rounds of review, the accuracy of the results is shown in the figure, the accuracy rate is increased by nearly one times (the green arrow in the figure is the review of the new normal number). In practical applications, the review object can be selected flexibly according to actual needs, such as selecting the channel that needs to be reviewed, such as all channels, that is, reviewing all channels corresponding to the to-be-detected video after detection, and so on. The abnormal channel is only reviewed after the detection of the abnormal to-be-detected video, and so on. The normal channel is reviewed after the detection of the normal to-be-detected video. Further, the number of reviews can be set by the relevant technical personnel according to actual needs, such as setting to 3 times; further, the review start time can also be set, such as setting to start the review immediately after the task (such as the video detection task in this paper) is completed, or setting to start the review according to the specified time, etc.

[0051] In one of the embodiments, the inspection center is also used to obtain platform domain information and IP information of each detection node, and to match the to-be-detected video channel information with the detection node based on the platform domain information and the IP information, to determine the target detection node matched with the to-be-detected video channel information from all detection nodes, and to issue the detection task for the corresponding to-be-detected video channel information to the target detection node.

[0052] In the prior art, for the multi-video access platform cascade scene and the video stream detection analysis in the upper level (such as the city-district-county network deployment architecture in the prior art), only by increasing the video stream detection analysis concurrency will have a great impact on the performance of the video access platform, will affect the video stream preview and the network bandwidth resource occupation, and finally will lead to the increase of the customer site cost.

[0053] In some preferred embodiments, the application can calculate the concurrency of each node according to the specification information of each node, wherein the specification information includes but is not limited to the memory, CPU / GPU parameters, operating system, and residual detection analysis quantity of the node, and the specification information contains the basic parameter information of the corresponding detection node. After matching the to-be-detected video channel information, the concurrency, and the detection node, the target detection node matched with the to-be-detected video channel information is determined from all detection nodes, and the detection task for the corresponding to-be-detected video channel information is issued to the target detection node, wherein the matching processing includes matching processing based on the platform domain information and IP network segment information of the detection node and the to-be-detected video stream. Specifically, the embodiment follows the principle of near matching, and the platform domain information and IP network segment information of the detection node and the to-be-detected video channel information are used to filter the optimal path distribution of the to-be-detected video channel information. Specifically, the matching based on the platform domain information includes grouping the detection nodes by platform domain, and grouping the to-be-detected video channel information by platform domain, and then matching the detection nodes and the to-be-detected video channel information in the same domain. Similarly, the matching based on the IP information includes grouping the detection nodes by IP segment, and grouping the to-be-detected video channel information by platform IP segment, and then matching the detection nodes and the to-be-detected video channel information in the same domain. Through the embodiment, the near matching principle of the to-be-detected video channel information can be realized, the network traffic bandwidth is saved under the premise of meeting the video stream (real-time stream / recording stream) detection analysis in a large scene, the video access platform environment is stable, and in addition, the application requires low detection node server specification, dynamically adapts to the detection capability through the video detection component to identify the server specification, and reduces the hardware resource investment.

[0054] In one of the embodiments, the inspection center is further configured to traverse each detection node to determine whether there is an abnormal state in each detection node.

[0055] The inspection center is further configured to, when detecting that there is an abnormal detection node in an abnormal state in the detection node, match the to-be-detected video channel information corresponding to the abnormal detection node with the nodes other than the abnormal detection node in the detection node to determine a final detection node.

[0056] The inspection center is further configured to issue the corresponding to-be-detected video channel information to the final detection node.

[0057] Specifically, the inspection center traverses each detection node to detect whether there is an abnormal detection node in an abnormal state in each detection node. When a server exception, server restart, network disconnection, power failure, and the like occur, the detection node is abnormal. If an abnormal detection node is detected, the abnormal detection node corresponding to the to-be-detected video channel information is matched with other normal detection nodes, where the matching method is as shown in the detection node and the to-be-detected video channel information described above, and the to-be-detected video channel information is distributed according to the optimal path matched, and the to-be-detected video channel information on the abnormal detection node is distributed to other normal nodes for continuous detection. Through the embodiment, the self-healing capability of fault migration after an abnormality occurs in the video resource detection process can be improved, and high-reliable execution of the video detection task is ensured.

[0058] In one of the embodiments, the distributed detection cluster is further configured to traverse each detection node, and end the detection task and return the detection result to the inspection center after detecting that all the detection nodes complete the detection of the to-be-detected video corresponding to the to-be-detected video channel information.

[0059] Specifically, the distributed detection cluster traverses each detection node, clears the sub-tasks of each detection node, and exits the detection task and returns the detection result to the inspection center after detecting that all the detection nodes complete the detection of the to-be-detected video.

[0060] Based on the same inventive concept, the embodiments of the present application also provide a video stream detection method for implementing the video stream detection system described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more video stream detection method embodiments provided below can refer to the limitations of the video stream detection system described above, which will not be repeated here.

[0061] In one embodiment, a video stream detection method is provided, which is applied in the video stream detection system described above. The method comprises:

[0062] The detection task is distributed to the detection nodes in the distributed detection cluster according to the customer demand obtained by the at least two inspection nodes included in the inspection center. The detection node determines the target to-be-detected video channel information from the to-be-detected video channel information, pulls the corresponding to-be-detected video based on the target to-be-detected video channel information, and performs detection, pushes the detection result to the inspection center, and generates the corresponding perception video detection result.

[0063] The present application also provides a preferred embodiment of a video stream detection method in a security cascade scenario, Figure 4 A preferred embodiment of a video stream detection method flowchart.

[0064] S510, the distributed detection cluster calculates the concurrency of the to-be-detected video according to the detection node server specifications (such as memory, CPU / GPU, operating system type, remaining detection analysis number, etc.).

[0065] S520, determine the relationship degree of the detection node and the to-be-detected video channel information. Among them, the calculation of the matching relationship can be determined from two aspects. If the detection node and the to-be-detected video channel information have configured platform domain information, the detection node is grouped by platform domain, and the to-be-detected video channel information is grouped by platform domain, and then the detection node and the to-be-detected video channel information in the same domain are matched. If the detection node and the to-be-detected video channel information have not configured platform domain information, the detection node is grouped by IP segment, and the to-be-detected video channel information is grouped by platform IP segment, and then the detection node and the to-be-detected video channel information in the same IP are matched.

[0066] S530, according to the concurrency and the relationship degree, the to-be-detected video channel information is distributed to the corresponding detection node.

[0067] S540, asynchronously trigger all detection nodes.

[0068] S550, detect whether each detection node normally completes the detection task. If it is detected that there is an abnormal detection node, the to-be-detected video channel information corresponding to the abnormal detection node is re-matched with other normal detection nodes, wherein the matching method is as shown in the detection node and the to-be-detected video channel information above, so as to complete the detection of the to-be-detected video by other normal detection nodes. If it is detected that all detection nodes normally complete the detection task, the detection node exits, and the detection result is returned to the inspection center.

[0069] It should be understood that although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise stated herein, the execution of these steps has no strict sequence limitation, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with other steps or steps or stages in other steps.

[0070] Each of the modules in the video stream detection system described above can be implemented wholly or partially by software, hardware, and combinations thereof. The modules described above can be embedded in a processor in a computer device in hardware form or independent of the processor in the computer device, or can be stored in a memory in the computer device in software form to facilitate the processor to call and execute the operations corresponding to each of the modules.

[0071] In an embodiment, a computer device, which can be a server, has an internal structure diagram as shown in Figure 5 The computer device includes a processor, a memory, and a network interface connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store video stream detection algorithm related data. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a video stream detection method.

[0072] Those skilled in the art can understand that Figure 5 The structure shown in the above embodiment is only a block diagram of part of the structure related to the scheme of the present application, and does not limit the computer device to which the scheme of the present application is applied. Specifically, the computer device can include more or fewer components than those shown in the diagram, or combine certain components, or have a different arrangement of components.

[0073] In an embodiment, a computer readable storage medium has a computer program stored thereon. The computer program is executed by a processor to implement the following steps:

[0074] The at least two inspection nodes included in the inspection center are configured to issue a detection task to a detection node in a corresponding distributed detection cluster according to the obtained customer demand. The detection node is configured to determine corresponding target to-be-detected video channel information from to-be-detected video channel information, pull corresponding to-be-detected video based on the target to-be-detected video channel information, perform detection, push a detection result to the inspection center, and generate a corresponding perception video detection result.

[0075] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0076] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0077] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0078] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A video stream detection system in a security cascade scene, characterized in that, The system comprises an inspection center, a distributed detection cluster, and to-be-detected video channel information; wherein the inspection center comprises at least two inspection nodes, and the distributed detection cluster comprises at least two detection nodes; The distributed detection cluster is configured to calculate the concurrency of the detection nodes; The inspection center is configured to issue a detection task to a corresponding detection node according to the acquired customer demand; including that the inspection center acquires platform domain information and IP information of each detection node, and performs matching processing on the to-be-detected video channel information and the detection nodes based on the platform domain information, the IP information, and the concurrency of the detection nodes, determines a target detection node matched with the to-be-detected video channel information from all the detection nodes, and issues a detection task for the corresponding to-be-detected video channel information to the target detection node; wherein the concurrency of the detection nodes is calculated according to the specification information of the detection nodes; The target detection node is configured to determine corresponding target to-be-detected video channel information from the to-be-detected video channel information based on the detection task, pull corresponding to-be-detected video based on the target to-be-detected video channel information, and perform detection, and push the detection result to the inspection center to generate a corresponding perception video detection result.

2. The video stream detection system of claim 1, wherein, The system further comprises a scheduling center, wherein the scheduling center communicates with the inspection center; The scheduling center is configured to set a timing video stream detection task; The scheduling center is further configured to instruct the corresponding inspection node to start performing a video stream detection task when the timing video stream detection task is triggered.

3. The video stream detection system of claim 1, wherein, The system further comprises a data relay cluster and a data storage cluster; wherein the inspection center is connected with the data relay cluster and the data storage cluster respectively; The data storage cluster is configured to persistently store detection rule information for each detection task; The data relay cluster is configured to deliver the detection result.

4. The video stream detection system of claim 1, wherein, The inspection node is further configured to automatically issue a re-inspection task to the corresponding inspection node based on the detection result after generating the detection result; The re-inspection task comprises determining an abnormal video result according to the detection result, and performing cyclic re-inspection on the abnormal video result until the number of re-inspections reaches a preset re-inspection threshold, to obtain a final detection result, wherein the number of video streams for each round of re-inspection decreases gradually with the increase of the cycle round.

5. The video stream detection system of claim 1, wherein, The inspection center is further configured to traverse each detection node to determine whether there is an abnormal state in each detection node; The inspection center is further configured to, when detecting that there is an abnormal detection node in an abnormal state in the detection nodes, perform the matching processing on to-be-detected video channel information corresponding to the abnormal detection node and nodes other than the abnormal detection node in the detection nodes, to determine a final detection node; The inspection center is further configured to issue the to-be-detected video channel information corresponding to the final detection node to the final detection node.

6. The video stream detection system of any of claims 1 to 5, wherein, The distributed detection cluster is further configured to traverse each detection node, and after detecting that all the detection nodes complete the detection of the to-be-detected video corresponding to the to-be-detected video channel information, end the detection task and return the detection result to the inspection center.

7. A video stream detection method in a security cascade scene, characterized in that, The method is applied to the system of any one of claims 1-6, and the method comprises: The number of concurrent detection nodes in the distributed detection cluster is calculated by at least two inspection nodes included in the inspection center, and a detection task is issued to a detection node in a corresponding distributed detection cluster according to acquired customer demand, comprising that the inspection center acquires platform domain information and IP information of each detection node, and performs matching processing on the to-be-detected video channel information and the detection node based on the platform domain information, the IP information and the number of concurrent detection nodes, determines a target detection node matched with the to-be-detected video channel information from all the detection nodes, and issues a detection task for corresponding to-be-detected video channel information to the target detection node; wherein the target detection node determines corresponding target to-be-detected video channel information from the to-be-detected video channel information, pulls corresponding to-be-detected video based on the target to-be-detected video channel information and performs detection, pushes the detection result to the inspection center, and generates corresponding perception video detection result, and the number of concurrent detection nodes is calculated according to specification information of the detection node.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to realize the function of the video stream detection system of any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the function of the video stream detection system of any one of claims 1-6.

Images