Video big data alarm receiving and processing application system

Abstract

The invention relates to data processing, and provides a video big data alarm receiving and processing application system, which comprises an early warning center module used for accessing alarm information, and carrying out classified filtering, scheduling and queuing distribution on the alarm information to an alarm receiving and processing module; the alarm receiving and processing module is used for studying and judging the alarm information sent by the early warning center module; the disposal front-end module is used for recording and following police information related to the alarm information and feeding back result information to the early warning center module through a disposal workbench; and the accident picture uploading module is used for uploading the accident picture and synchronously transmitting the accident picture to the alarm receiving and processing module. Compared with the prior art, the system organically combines all alarm handling processes together, improves the alarm handling efficiency, and effectively analyzes accident pictures and automatically sorts and issues the police in combination with a video big data mode.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a video big data alarm receiving and handling application system, device, equipment and computer-readable storage medium. Background Art

[0002] With the continuous deepening of the application of artificial intelligence, especially deep learning technology in video surveillance, video surveillance has entered a stage of comprehensive intelligent development. Intelligent applications for different target objects and different scenarios such as vehicle recognition (such as vehicle model recognition, window decoration recognition, seat belt recognition, driving and calling recognition, etc.), face recognition, portrait (body) recognition, gait recognition, and cyclist recognition have developed rapidly, playing an increasingly important role in public security practical applications. At the same time, with the continuous enhancement of the processing power of embedded AI chips, the intelligence level of front-end and edge devices is getting higher and higher, and the collaborative intelligent analysis of the front-end and back-end has further promoted the development of video surveillance intelligence. In response to the networking and sharing of video image information under the background of comprehensive intelligent video surveillance, SAC / TC100 organized the preparation of two series of standards, GA / T1400-2017 "Public Security Video Image Information Application System" and GA / T1399-2017 "Public Security Video Image Analysis System", which effectively solved the problems of intelligent equipment interconnection and video image information sharing and application in the process of video surveillance intelligence development, and greatly promoted the development process and practical application results of public security video surveillance intelligence.

[0003] With the development of video surveillance technology, the application mode of video surveillance is also undergoing profound changes. The main application modes of traditional video surveillance are real-time video browsing (manual viewing), historical video retrieval and playback (manual viewing), and cloud mirror control. With the development of intelligent video surveillance, the application mode of video surveillance is also moving towards the video big data application mode: (1) video big data query and retrieval; (2) vehicle big data analysis (various technical tactics); (3) face big data analysis (recognition comparison analysis, etc.); (4) serial and parallel case analysis; (5) feature control (license plate control, face control, etc.). With the continuous development of video combat applications, the application mode of video big data is further developing towards the video big data deep processing application mode: (1) video image cluster analysis: "one car one file", "one person one file", etc.; (2) multi-dimensional data fusion analysis based on video big data: video to find mobile phone, mobile phone to find person, mobile phone to find car, car to find mobile phone, face search car, historical relationship mining, etc.; (3) multi-dimensional data association analysis, etc. Multi-dimensional data fusion analysis based on video big data has become a hot spot in current application development.

[0004] However, in terms of application mode, these applications are still mainly based on post-event retrospective analysis. The video big data application mode has greatly improved the efficiency of post-event retrospective analysis, but it is still in the "passive reaction police" application mode, that is, after receiving the police information and cases, the relevant video image data are searched and retrieved. At present, the real-time applications facing the incident mainly include the following three aspects: (1) major security applications based on manual real-time browsing; (2) deployment of control and alarm, which adopts the mechanism of who deploys the control and who receives the alarm information for handling; (3) comparison and recognition warning, based on library comparison of face / portrait comparison and recognition, vehicle feature comparison, etc., and model comparison based on multi-dimensional data, the warning information can be summarized in real time and can be viewed, queried and statistically analyzed through the video image information comprehensive application platform or video image analysis system. However, there is no unified real-time warning application police mechanism to form a business closed loop of real-time warning signal analysis and judgment and application implementation. As a result, a large number of face checkpoints, vehicle checkpoints, etc. The alarm information is not handled in time, and the effectiveness of real-time video surveillance application is greatly restricted. The two series of standards, GA / T1400-2017 "Public Security Video Image Information Application System" and GA / T1399-2017 "Public Security Video Image Analysis System", only provide a control and alarm mechanism. How to give full play to the role of video big data in real-time warning applications, as well as multi-dimensional data real-time warning applications based on video big data, provide video big data support for "active policing" and "preventive policing", and improve the application effectiveness of face checkpoints, vehicle checkpoints, video analysis systems, etc., which require huge investments, has become an urgent problem that needs to be solved in the in-depth development of current video combat applications.

[0005] The in-depth development of video AI technology and the application of multi-dimensional data model analysis and comparison based on video big data can provide a large amount of real-time warning information for public security prevention and control, crime prevention and public services. However, due to the following problems, a large amount of real-time warning information is difficult to play an effective role in actual combat:

[0006] The real-time warning information generated by video AI and multi-dimensional data model analysis and comparison based on video big data has a high proportion of false alarms and cannot be directly distributed to frontline police for handling. Otherwise, it may cause great interference to frontline police.

[0007] If the same object lingers under the same camera for a long time, repeated warning messages will be generated;

[0008] The movement of the same target object within the video image monitoring area will generate a series of warning information, which needs to be dealt with uniformly;

[0009] If the adjustment data of the control level of key objects cannot be synchronized in time, there will be warning information that does not need to be handled;

[0010] Since early warning information has business attributes and regional attributes, real-time early warning information needs to be distributed to different regions or business police types for on-site handling based on its characteristic attributes;

[0011] Different warning information requires different response methods due to its different urgency and difficulty of handling. It needs to be combined with different police mechanisms to achieve a closed-loop business implementation. Some warning information needs to be handled in a timely manner, so it needs to be combined with the patrol police mechanism. Some warning information is difficult to reflect the warning characteristics of a single piece of information. It is necessary to aggregate and analyze multiple warning information to find out the rules and then make special handling. It needs to be combined with intelligence analysis and special action mechanisms;

[0012] Warning information of the same object at different times and in different geographical locations requires different handling methods;

[0013] The existing public security police call-handling business is mainly based on the "three-in-one" police call-handling system, but this method is mainly based on voice calls, combined with WeChat, text messages and other means. The existing system is difficult to handle real-time warning information based on video big data.

[0014] In view of the above problems, the present invention proposes a video big data alarm receiving and handling application system. Summary of the invention

[0015] The main purpose of the present invention is to provide a video big data alarm reception and handling application system, device, equipment and computer-readable storage medium, which aims to handle the alarm situation in combination with the accident video screen.

[0016] To achieve the above object, the present invention provides a video big data alarm reception and handling application system, comprising:

[0017] The early warning center module is used to access alarm information, classify and filter the alarm information, dispatch and queue it and distribute it to the alarm receiving and handling module;

[0018] The alarm receiving and handling module is used to analyze and judge the alarm information sent by the early warning center module;

[0019] The disposal front-end module is used to record and follow up the relevant alarm information of the alarm information, and the result information is fed back to the early warning center module through the disposal workbench;

[0020] The accident screen upload module is used to upload the accident screen and transmit it to the alarm receiving and handling module synchronously.

[0021] In the video big data alarm receiving and handling application system provided in this application, the warning center module includes:

[0022] The unified access unit for early warning information is used to connect with various early warning sources and access various early warning information;

[0023] The warning information scheduling and queuing unit is used to pre-process the received warning information, wherein the pre-processing includes at least one of the following: classification filtering, aggregation, scheduling, queuing and distribution;

[0024] The command dispatch and handling service unit is used to distribute the handling instructions and manage the handling results of the alarm handling station, forward the subsequent warning information of the combined handling, query, retrieve and push the details of the warning object, and provide instant messaging or multi-party conversation services between the handling workbench and the alarm handling station;

[0025] Intelligence service unit, used for classification, aggregation and analysis of intelligence warning information;

[0026] Early warning database unit, used to store all early warning information, analysis and processing results, disposal results and intelligence analysis results;

[0027] The central cockpit unit is used to display the early warning situation, model analysis statistics, statistical data of the police stations, and early warning disposal statistics;

[0028] The configuration management unit is used to configure and manage rule strategies such as classification filtering, aggregation, scheduling and queuing distribution, as well as the account authority management of police dispatchers.

[0029] In the video big data alarm receiving and handling application system provided by this application, the accident screen uploading module includes:

[0030] Network contact unit, used for personnel to upload accident images;

[0031] The sequence unit is used to sort the uploaded accident images according to the time when the accident occurred.

[0032] In the video big data police receiving and handling application system provided in the present application, the police receiving and handling module includes: a video big data intelligence analysis and judgment unit, which is used to extract features from the accident screen, obtain personnel information, and classify the accident personnel according to the personnel information;

[0033] A personnel injury analysis unit, used to determine the number of injured personnel and the degree of injury based on a clustering algorithm and the behavioral characteristics of personnel extracted from the accident scene;

[0034] The degree unit is used to determine the order of police dispatch according to the weight relationship between personnel classification and injury degree.

[0035] In the video big data police receiving and handling application system provided in the present application, the police receiving and handling module also includes a face recognition unit and a motion recognition unit. The face recognition unit is used to recognize facial features and call relevant personnel age information and disease information. The motion recognition unit is used to obtain continuous motion features of personnel in the accident scene.

[0036] In the video big data police receiving and handling application system provided in the present application, the video big data intelligence analysis and judgment unit includes: a classification unit for classifying accident personnel according to pre-set personnel priorities.

[0037] In the video big data police receiving and handling application system provided by the present application, the number of injured persons and the degree of injury are determined based on the clustering algorithm and the behavioral characteristics of the persons in the extracted accident screen, including:

[0038] Based on the clustering algorithm, the continuous behavior characteristics of the people in the extracted accident scenes are identified, and the different features between the identified continuous behavior characteristics of the people and the continuous behavior characteristics of the people under normal circumstances are taken as abnormal features. According to the number of abnormal features and the position information of the people where the characteristics are located, the number of injured people and the degree of injury are determined.

[0039] In the video big data police response application system provided in the present application, the method for calculating the size of the weight relationship between personnel classification and injury degree includes: obtaining the size of the weight relationship between personnel classification and injury degree by summing the product of the weight corresponding to the classification unit's grade and level and the product of the severity level of the personnel's injury degree and the weight of the injury degree.

[0040] The video big data police response application system provided in this application also includes a rescue module, which calls a specified number of ambulances to the scene based on the number of injured people in the accident scene.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also provides a video big data alarm receiving and handling application device, which includes a processor, a memory, and a video big data alarm receiving and handling application program stored in the memory and executable by the processor, wherein when the video big data alarm receiving and handling application program is executed by the processor, the steps of the video big data alarm receiving and handling application system as described above are implemented.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which a video big data alarm receiving and handling application is stored, wherein when the video big data alarm receiving and handling application is executed by a processor, the steps of the video big data alarm receiving and handling application system as described above are implemented.

[0043] The present invention provides a video big data alarm receiving and handling application system, the system includes an early warning center module, which is used to access alarm information, and classify, filter, dispatch and queue the alarm information to distribute it to the alarm receiving and handling module; the alarm receiving and handling module is used to judge the alarm information sent by the early warning center module; the disposal front-end module is used to record and follow up the relevant alarm information of the alarm information, and the result information is fed back to the early warning center module through the disposal workbench; the accident picture uploading module is used to upload the accident picture and synchronously transmit it to the alarm receiving and handling module. Compared with the existing technology, this system organically combines various alarm handling processes together, improves the efficiency of alarm handling, and at the same time combines the video big data method to effectively analyze the accident picture and automatically sort the alarm. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of the hardware structure of a video big data alarm receiving and handling application device involved in an embodiment of the present invention;

[0045] Figure 2 Data processing flow chart of the video big data police response application system.

[0046] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0048] The video big data alarm reception and processing application system involved in the embodiment of the present invention is mainly applied to video big data alarm reception and processing application equipment, which can be a PC, portable computer, mobile terminal and other equipment with display and processing functions.

[0049] With the deepening application of artificial intelligence, especially deep learning technology in video surveillance, video surveillance has entered a stage of comprehensive intelligent development.

[0050] With the development of video surveillance technology, the application mode of video surveillance is also undergoing profound changes. The main application modes of traditional video surveillance are real-time video browsing (manual viewing), historical video retrieval and playback (manual viewing), and cloud mirror control. With the development of intelligent video surveillance, the application mode of video surveillance is also moving towards the video big data application mode: (1) video big data query and retrieval; (2) vehicle big data analysis (various technical tactics); (3) face big data analysis (recognition comparison analysis, etc.); (4) serial and parallel case analysis; (5) feature control (license plate control, face control, etc.). With the continuous development of video combat applications, the application mode of video big data is further developing towards the video big data deep processing application mode: (1) video image cluster analysis: "one car one file", "one person one file", etc.; (2) multi-dimensional data fusion analysis based on video big data: video to find mobile phone, mobile phone to find person, mobile phone to find car, car to find mobile phone, face search car, historical relationship mining, etc.; (3) multi-dimensional data association analysis, etc. Multi-dimensional data fusion analysis based on video big data has become a hot spot in current application development.

[0051] However, in terms of application mode, these applications are still mainly based on post-event retrospective analysis. The video big data application mode has greatly improved the efficiency of post-event retrospective analysis, but it is still in the "passive reaction police" application mode, that is, after receiving the police information and cases, the relevant video image data are searched and retrieved. At present, the real-time applications facing the incident mainly include the following three aspects: (1) major security applications based on manual real-time browsing; (2) deployment of control and alarm, which adopts the mechanism of who deploys the control and who receives the alarm information for handling; (3) comparison and recognition warning, based on library comparison of face / portrait comparison and recognition, vehicle feature comparison, etc., and model comparison based on multi-dimensional data, the warning information can be summarized in real time and can be viewed, queried and statistically analyzed through the video image information comprehensive application platform or video image analysis system. However, there is no unified real-time warning application police mechanism to form a business closed loop of real-time warning signal analysis and judgment and application implementation. As a result, a large number of face checkpoints, vehicle checkpoints, etc. The alarm information is not handled in time, and the effectiveness of real-time video surveillance applications is greatly restricted. Two series of standards, GA / T1400-2017 "Public Security Video Image Information Application System" and GA / T1399-2017 "Public Security Video Image Analysis System", only provide a control and alarm mechanism. How to give full play to the role of video big data in real-time warning applications, as well as multi-dimensional data real-time warning applications based on video big data, provide video big data support for "active policing" and "preventive policing", and improve the application effectiveness of face checkpoints, vehicle checkpoints, video analysis systems, etc., which require huge investments, has become an urgent problem that needs to be solved in the in-depth development of current video combat applications.

[0052] The in-depth development of video AI technology and the application of multi-dimensional data model analysis and comparison based on video big data can provide a large amount of real-time warning information for public security prevention and control, crime prevention and public services. However, due to the following problems, a large amount of real-time warning information is difficult to play an effective role in actual combat:

[0053] The real-time warning information generated by video AI and multi-dimensional data model analysis and comparison based on video big data has a high proportion of false alarms and cannot be directly distributed to frontline police for handling. Otherwise, it may cause great interference to frontline police.

[0054] If the same object lingers under the same camera for a long time, repeated warning messages will be generated;

[0055] The movement of the same target object within the video image monitoring area will generate a series of warning information, which needs to be dealt with uniformly;

[0056] If the adjustment data of the control level of key objects cannot be synchronized in time, there will be warning information that does not need to be handled;

[0057] Since early warning information has business attributes and regional attributes, real-time early warning information needs to be distributed to different regions or business police types for on-site handling based on its characteristic attributes;

[0058] Different warning information requires different response methods due to its different urgency and difficulty of handling. It needs to be combined with different police mechanisms to achieve a closed-loop business implementation. Some warning information needs to be handled in a timely manner, so it needs to be combined with the patrol police mechanism. Some warning information is difficult to reflect the warning characteristics of a single piece of information. It is necessary to aggregate and analyze multiple warning information to find out the rules and then make special handling. It needs to be combined with intelligence analysis and special action mechanisms;

[0059] Warning information of the same object at different times and in different geographical locations requires different handling methods;

[0060] The existing public security police call-handling business is mainly based on the "three-in-one" police call-handling system, but this method is mainly based on voice calls, combined with WeChat, text messages and other means. The existing system is difficult to handle real-time warning information based on video big data.

[0061] In view of the above problems, the present invention proposes a video big data alarm receiving and handling application system.

[0062] Reference Figure 1 , Figure 1The hardware structure diagram of the video big data alarm receiving and handling application device involved in the embodiment of the present invention is shown in FIG. In the embodiment of the present invention, the video big data alarm receiving and handling application device may include a processor 1001 (such as a CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface); the memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory, and the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0063] Those skilled in the art will understand that Figure 1 The hardware structure shown in the figure does not constitute a limitation on the video big data alarm reception and processing application device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0064] Continue to refer to Figure 1 , Figure 1 The memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, and a video big data alarm receiving and processing application.

[0065] exist Figure 1 In the embodiment, the network communication module is mainly used to connect to the server and perform data communication with the server; and the processor 1001 can call the video big data alarm receiving and handling application program stored in the memory 1005, and execute the video big data alarm receiving and handling application system provided by the embodiment of the present invention.

[0066] The embodiment of the present invention provides a video big data alarm receiving and handling application system, including:

[0067] The early warning center module is used to access alarm information, classify and filter the alarm information, dispatch and queue it and distribute it to the alarm receiving and handling module;

[0068] The alarm receiving and handling module is used to analyze and judge the alarm information sent by the early warning center module;

[0069] The disposal front-end module is used to record and follow up the relevant alarm information of the alarm information, and the result information is fed back to the early warning center module through the disposal workbench;

[0070] The accident screen upload module is used to upload the accident screen and transmit it to the alarm receiving and handling module synchronously.

[0071] The present invention provides a video big data alarm receiving and handling application system, the system includes an early warning center module, which is used to access alarm information, and classify, filter, dispatch and queue the alarm information to distribute it to the alarm receiving and handling module; the alarm receiving and handling module is used to judge the alarm information sent by the early warning center module; the disposal front-end module is used to record and follow up the relevant alarm information of the alarm information, and the result information is fed back to the early warning center module through the disposal workbench; the accident picture uploading module is used to upload the accident picture and synchronously transmit it to the alarm receiving and handling module. Compared with the existing technology, this system organically combines various alarm handling processes together, improves the efficiency of alarm handling, and at the same time combines the video big data method to effectively analyze the accident picture and automatically sort the alarm.

[0072] In some embodiments, the early warning center module includes:

[0073] The unified access unit for early warning information is used to connect with various early warning sources and access various early warning information;

[0074] The warning information scheduling and queuing unit is used to pre-process the received warning information, wherein the pre-processing includes at least one of the following: classification filtering, aggregation, scheduling, queuing and distribution;

[0075] The command dispatch and handling service unit is used to distribute the handling instructions and manage the handling results of the alarm handling station, forward the subsequent warning information of the combined handling, query, retrieve and push the details of the warning object, and provide instant messaging or multi-party conversation services between the handling workbench and the alarm handling station;

[0076] Intelligence service unit, used for classification, aggregation and analysis of intelligence warning information;

[0077] Early warning database unit, used to store all early warning information, analysis and processing results, disposal results and intelligence analysis results;

[0078] The central cockpit unit is used to display the early warning situation, model analysis statistics, statistical data of the police stations, and early warning disposal statistics;

[0079] The configuration management unit is used to configure and manage rule strategies such as classification filtering, aggregation, scheduling and queuing distribution, as well as the account authority management of police dispatchers.

[0080] (1a) The warning information is connected to the warning center's (1b) warning information scheduling and queuing module through the unified access module for processing. (1c) The warning information unified access module saves the warning information to the warning database upon receiving it;

[0081] The warning information dispatching and queuing module classifies, filters, aggregates, dispatches, queues and distributes the warning information. (2a) The warning information that needs to be judged and processed is sent to the video big data alarm reception and handling station for manual judgment and analysis, and disposal arrangements are made; (2b) After adding the video big data alarm reception and handling station logo to the warning information, the warning information is synchronously sent to the command dispatching and handling module; (2c) The command dispatching and handling module retrieves the detailed information of the warning object through the video big data business support engine according to the warning object in the received warning information; (2d) After retrieving the detailed information of the warning object, the command dispatching and handling module pushes the detailed information of the warning object to the video big data alarm reception and handling station to provide support for the judgment of the police receiver;

[0082] (3a) The video big data alarm reception and handling station handles the warning information after analysis and judgment, and sends the handling instructions to the command dispatch and handling module; (3b) The command dispatch and handling module saves the handling instructions to the warning database upon receiving them;

[0083] The instruction dispatching and handling module forwards the handling instructions to different handling entities according to the type of handling instructions received. (4a) For warning information that requires real-time handling, it is pushed to the designated police's handling workbench / APP together with the details of the warning object; (4b) For intelligence-related warning information, it is pushed to the intelligence service module; (3b) For warning information such as false alarms and warning information that does not require handling, it can be saved in the warning database; (4c) Warning information can also be sent to a third-party instruction system through the instruction dispatching and handling module for distribution and handling, and the handling results are returned to the instruction dispatching and handling module for storage; (4d) According to the handling needs of the warning information, the warning information and the details of the warning object can be pushed to the relevant personnel of the collaborative unit through the business collaborative governance engine for collaborative handling;

[0084] For subsequent warning information of the same object, the warning information dispatching and queuing module receives it (5a) and sends it to the video big data alarm reception station to be merged with the warning information that has been sent; (5b) the warning information of the same object is sent to the command dispatching and handling module at the same time; (5c) for the warning information of the same object that needs to be handled in real time, the command dispatching and handling module sends it to the designated police handling workbench / APP; (4b) for the warning information of the same object of intelligence type, it is sent to the intelligence service module for merged processing;

[0085] (6a) For real-time handling warning information, after completing the handling, the handling police will send the handling results (including the return of warning information that is not within the handling authority of the designated police) to the command dispatch and handling module through the handling workbench / APP; (6b) After receiving the handling results, the command dispatch and handling module will save the handling results to the warning database; (6c) For the returned warning information that is not within the handling authority of the designated police, the command dispatch and handling module will return it to the originally processed video big data alarm reception and handling station or the duty director alarm reception station for re-distribution;

[0086] (7) For intelligence warning information, it can be analyzed and judged through the video big data intelligence analysis and judgment platform as needed, and the results of the analysis and judgment are stored in the warning database;

[0087] The police officer in charge can send instant messages to the dispatcher or initiate multi-party conversations through the handling workbench / APP, command scheduling and handling module with the support of the business collaborative governance engine.

[0088] The accident screen uploading module includes:

[0089] Network contact unit, used for personnel to upload accident images;

[0090] The sequence unit is used to sort the uploaded accident images according to the time when the accident occurred.

[0091] The alarm receiving and handling module includes: a video big data intelligence analysis and judgment unit, which is used to extract features from the accident screen, obtain personnel information, and classify the accident personnel according to the personnel information;

[0092] A personnel injury analysis unit, used to determine the number of injured personnel and the degree of injury based on a clustering algorithm and the behavioral characteristics of personnel extracted from the accident scene;

[0093] The degree unit is used to determine the order of police dispatch according to the weight relationship between personnel classification and injury degree.

[0094] The alarm receiving and handling module also includes a face recognition unit and a motion recognition unit. The face recognition unit is used to recognize facial features and call relevant personnel age information and disease information. The motion recognition unit is used to obtain continuous motion features of personnel in the accident scene.

[0095] The video big data intelligence analysis and judgment unit includes: a classification unit, which is used to classify accident personnel according to pre-set personnel priorities.

[0096] The method of determining the number of injured persons and the degree of injury based on the clustering algorithm and the behavioral characteristics of the persons in the extracted accident scene includes:

[0097] Based on the clustering algorithm, the continuous behavior characteristics of the people in the extracted accident scenes are identified, and the different features between the identified continuous behavior characteristics of the people and the continuous behavior characteristics of the people under normal circumstances are taken as abnormal features. According to the number of abnormal features and the position information of the people where the characteristics are located, the number of injured people and the degree of injury are determined.

Claims

1. A video big data alarm reception and handling application system, characterized in that: include: The early warning center module is used to access alarm information, classify and filter the alarm information, dispatch and queue it and distribute it to the alarm receiving and handling module; The alarm receiving and handling module is used to analyze and judge the alarm information sent by the early warning center module; The disposal front-end module is used to record and follow up the relevant alarm information of the alarm information, and the result information is fed back to the early warning center module through the disposal workbench; The accident screen upload module is used to upload the accident screen and transmit it to the alarm receiving and handling module synchronously.

2. The video big data alarm receiving and handling application system according to claim 1 is characterized in that: The early warning center module includes: The unified access unit for early warning information is used to connect with various early warning sources and access various early warning information; The warning information scheduling and queuing unit is used to pre-process the received warning information, wherein the pre-processing includes at least one of the following: classification filtering, aggregation, scheduling, queuing and distribution; The command dispatch and handling service unit is used to distribute the handling instructions and manage the handling results of the alarm handling station, forward the subsequent warning information of the combined handling, query, retrieve and push the details of the warning object, and provide instant messaging or multi-party conversation services between the handling workbench and the alarm handling station; Intelligence service unit, used for classification, aggregation and analysis of intelligence warning information; Early warning database unit, used to store all early warning information, analysis and processing results, disposal results and intelligence analysis results; The central cockpit unit is used to display the early warning situation, model analysis statistics, statistical data of the police stations, and early warning disposal statistics; The configuration management unit is used to configure and manage rule strategies such as classification filtering, aggregation, scheduling and queuing distribution, as well as the account authority management of police dispatchers.

3. The video big data alarm receiving and handling application system according to claim 1 is characterized in that: The accident screen uploading module includes: Network contact unit, used for personnel to upload accident images; The sequence unit is used to sort the uploaded accident images according to the time when the accident occurred.

4. The video big data alarm receiving and handling application system according to claim 3 is characterized in that: The alarm receiving and handling module includes: a video big data intelligence analysis and judgment unit, which is used to extract features from the accident screen, obtain personnel information, and classify the accident personnel according to the personnel information; A personnel injury analysis unit, used to determine the number of injured personnel and the degree of injury based on a clustering algorithm and the behavioral characteristics of personnel extracted from the accident scene; The degree unit is used to determine the order of police dispatch according to the weight relationship between personnel classification and injury degree.

5. The video big data alarm receiving and handling application system according to claim 4 is characterized in that: The alarm receiving and handling module also includes a face recognition unit and a motion recognition unit. The face recognition unit is used to recognize facial features and call relevant personnel age information and disease information. The motion recognition unit is used to obtain continuous motion features of personnel in the accident scene.

6. The video big data alarm receiving and handling application system according to claim 5 is characterized in that: The video big data intelligence analysis and judgment unit includes: a classification unit, which is used to classify accident personnel according to pre-set personnel priorities.

7. The video big data alarm receiving and handling application system according to claim 6 is characterized in that: The method of determining the number of injured persons and the degree of injury based on the clustering algorithm and the behavioral characteristics of the persons in the extracted accident scene includes: Based on the clustering algorithm, the continuous behavior characteristics of the people in the extracted accident scenes are identified, and the different features between the identified continuous behavior characteristics of the people and the continuous behavior characteristics of the people under normal circumstances are taken as abnormal features. According to the number of abnormal features and the position information of the people where the characteristics are located, the number of injured people and the degree of injury are determined.

8. The video big data alarm receiving and handling application system according to claim 7 is characterized in that: The calculation method for the size of the weight relationship between personnel classification and injury degree includes: obtaining the size of the weight relationship between personnel classification and injury degree by summing the product of the weight corresponding to the classification unit's grade and level and the product of the severity level of the personnel's injury degree and the weight of the injury degree.

9. The video big data alarm receiving and handling application system according to claim 1 is characterized in that: It also includes a rescue module, which calls a specified number of ambulances to the scene based on the number of injured people in the accident scene.

Images