Network-based video security inspection system and method thereof

Abstract

The invention discloses a network-based video security inspection system and a method thereof. The system comprises a plurality of video monitoring devices, a plurality of edge controllers, a plurality of inspection devices, a database and a master control center. The video monitoring device collects fixed-point image data; the edge controller performs data exchange and processing; and the inspection device enters a view blind area to obtain mobile image data. And the edge controller and the inspection device are connected through a wireless network. The database stores image data; and the master control center identifies the content and judges abnormity. The inspection device is carried by a person or on a mobile robot, and enters a view blind area to obtain a more comprehensive monitoring view. Under the abnormal condition, the abnormal condition can be quickly fed back to an operator. According to the system, the advantages of mobility and network connection are combined, and the monitoring effect and the security and protection capability are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of patrol inspection and security protection, and in particular relates to a network-based video security patrol inspection system and method thereof. Background Art

[0002] Existing video surveillance systems mainly use high-definition network cameras for monitoring. These cameras have clear image quality and night vision functions, and can transmit high-definition video streams in real time. However, fixed cameras can only provide limited viewing angles and monitoring ranges, and their blind spots can be easily exploited. Fixed cameras cannot perform mobile monitoring of important areas, and there is a problem of insufficient monitoring coverage. Specifically, some hidden corners of important places or facilities may be in the camera's monitoring blind spots, and these blind spots can easily become the activity sites of target personnel. In addition, once the camera's field of view and angle are determined, they cannot be changed, making it difficult to conduct in-depth monitoring of key areas. Due to the vast area, it is difficult to conduct a comprehensive and detailed field of view inspection of all areas with only limited fixed cameras, and there may be monitoring gaps in key parts of important facilities.

[0003] In addition, most existing video surveillance systems use a "one-to-multipoint" network topology. Each camera transmits high-definition video images and data to the video management server in the control center in real time, which requires a large amount of network bandwidth resources. Since the amount of data in high-definition video streams is very large, transmitting all of them to the control center will bring huge network transmission pressure, which may cause problems such as video quality degradation and transmission delay due to network congestion. This not only affects the monitoring effect, but also tests the data processing capacity of the control center. More importantly, it is difficult for the control center to feedback monitoring abnormalities in real time. Usually, a lot of manual verification is required to locate the problem, and the response speed is slow. There is a lack of a mechanism for quickly confirming and handling abnormal events.

[0004] From the above analysis of the existing video surveillance system, it can be seen that the monitoring angle of fixed cameras is limited, and a large number of high-definition video streams will consume a lot of network bandwidth resources, making it difficult for the control center to respond to monitoring anomalies in real time. These problems restrict the monitoring effect of the existing monitoring system. In order to solve these pain points and improve the coverage, initiative and real-time response capabilities of monitoring, this application proposes a network-based video security inspection system and method. Summary of the invention

[0005] In view of the various deficiencies in the prior art, the purpose of this application is to provide a network-based video security inspection system and method thereof, so as to solve the problems that the fixed cameras in the prior art have limited monitoring viewing angles, and a large number of high-definition video streams consume a large amount of network bandwidth resources, making it difficult for the control center to respond to monitoring anomalies in real time. On the basis of the existing monitoring network, the system adds mobile inspection devices. These inspection devices can enter the blind spots of the camera's field of view to obtain a more comprehensive monitoring view. At the same time, edge computing technology is used for local analysis, and only key data is uploaded to reduce the network load. In abnormal situations, feedback can be quickly given to operators to guide them to conduct targeted inspections of important areas. This solution fully combines the advantages of mobile monitoring and edge computing technology to enhance the intelligence and real-time response capabilities of video monitoring. The purpose of applying for this patent is to protect this valuable monitoring system design so that it can better serve the public security field and improve the security level of various important places and facilities.

[0006] To achieve the above purpose or other related purposes, the present application provides a network-based video security inspection system and method. The present application adds a mobile inspection device on the basis of the existing monitoring network. The inspection device can automatically or be carried into the blind spot of the camera's field of view to obtain a more comprehensive monitoring view. At the same time, edge computing technology is used for local analysis, and only key data is uploaded to reduce the network load. In abnormal situations, feedback can be quickly given to operators to guide them to conduct targeted inspections of important areas. The present application scheme fully combines the advantages of mobile monitoring and edge computing technology, which can enhance the intelligence and real-time response capabilities of video surveillance, so that it can better serve the public security field and improve the security level of various important places and facilities.

[0007] In view of this, the specific solutions disclosed in this application are as follows: A network-based video security patrol system, comprising: a plurality of video monitoring devices, which are distributed in the patrol area and are used to obtain fixed-point image data; a plurality of edge controllers, which are used for network communication, data exchange, preliminary recognition and compression of fixed-point image data; an edge controller communicates with one or more of the video monitoring devices through a LAN network; the edge controller communicates with a WAN network; the edge controller has a wireless network communication function; a plurality of patrol devices, which are mobile and set in the patrol area, the patrol devices are connected to the edge controllers through wireless network signals, and the patrol devices are used to obtain mobile image data and upload it through the edge controllers; a database, which communicates with the edge controllers through a WAN network, and is used to receive and store fixed-point image data and mobile image data; a master control center, which communicates with the database through a LAN network, and communicates with the edge controllers and the patrol devices through a WAN network; Among them, the inspection device includes an image acquisition module, an image display module, an alarm module, a positioning module and an inspection configuration module; the image acquisition module is used to acquire mobile image data, the image display module is used to display images, the alarm module is used to trigger or display alarm information, the positioning module is used to identify location information based on wireless network signals and SSID, and the inspection configuration module is used to set inspection paths and inspection cycles; all modules in the inspection device communicate with the edge controller via a wireless network.

[0008] In one or more embodiments provided in the present application, the master control center includes an image recognition module, which is used to identify the content in the fixed-point image data and the moving image data, including facial information of people, image information of objects, and light intensity information.

[0009] In one or more embodiments provided in the present application, the main control center includes an abnormality identification module, which determines the abnormality of the content in the fixed-point image data and the moving image data based on the historical data stored in the database; the historical data includes fixed-point image data and moving image data in a previous time period, and the content identified therefrom.

[0010] In one or more implementations provided in the present application, the master control center includes an alarm sending module, and the alarm sending module is used to send alarm information to the edge controller through a WAN network.

[0011] In one or more embodiments provided in the present application, the alarm sending module sends abnormal fixed-point image data and / or moving image data to the inspection device through the WAN network while sending the alarm information, and displays it through the image display module of the inspection device.

[0012] In one or more embodiments provided in the present application, the inspection device is any combination of one or more of a handheld device, a wearable device, and a mobile robot.

[0013] In one or more implementations provided in the present application, the inspection configuration module communicates with the positioning module to obtain location information to correct and verify the inspection path.

[0014] The present application provides a network-based video security patrol method, which uses the video security patrol system, including: S1: collect fixed-point image data and mobile image data through the network; S2: Identify the content in the fixed-point impact data and the moving image data; S3: Determine whether there is an abnormality in the content; if there is no abnormality, store the fixed-point image data and the moving image data and their contents; if there is an abnormality, broadcast an alarm message.

[0015] In one or more embodiments provided in the present application, before step S1, it also includes: preliminarily identifying and determining whether an abnormality occurs in the fixed-point image data. If no abnormality occurs, compressing the fixed-point image data and uploading it; if an abnormality occurs, uploading uncompressed fixed-point image data.

[0016] In one or more implementations provided in the present application, step S3 further includes: simultaneously broadcasting the fixed-point image data and the moving image data with the abnormality.

[0017] Beneficial effects of the present invention: This system adds a mobile inspection device that can enter the blind spot of the fixed camera to obtain a more comprehensive monitoring perspective. At the same time, it actively obtains real-time images of important areas, no longer limited to the location of static cameras. Through the edge computing server, local preliminary analysis and processing are performed, and only key information is uploaded to avoid a large number of high-definition videos occupying network bandwidth resources. The introduction of intelligent analysis algorithms can automatically identify image content and judge abnormal situations to achieve intelligent monitoring. In the event of a major abnormality, image information can be sent immediately to the inspection device, and the operator can respond in the first time. The system makes full use of the flexibility of mobile devices and the connectivity with network video surveillance to achieve mobile monitoring and remote linkage. The system can improve the monitoring level of important areas, ensure the safe operation of facilities and emergency response to accidents. It can be applied to security inspections in a variety of important places, such as airports, stations, government facilities, corporate buildings, etc., and has a wide range of market applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a schematic diagram of the network-based video security inspection system of the present invention.

[0020] Description of Figure Numbers: 1- Video surveillance device, 2- Edge controller, 3- Inspection device, 4- Database, 5- Master control center. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0022] In the description of the present invention, it should be noted that the terms "upper", "lower", "left", "right", "center", "vertical", "horizontal", "inner", "outer", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0023] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installation", "setting", "connection", "connection" and the like should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] Exemplary Embodiments like Figure 1 As shown, this exemplary embodiment provides a network-based video security patrol system, including: a plurality of video monitoring devices 1, which are distributed in the patrol area and are used to obtain fixed-point image data; a plurality of edge controllers 2, which are used for network communication, data exchange, preliminary recognition and compression of fixed-point image data; an edge controller 2 communicates with one or more of the video monitoring devices 1 through a LAN network; the edge controller 2 communicates with a WAN network; the edge controller 2 has a wireless network communication function; a plurality of patrol devices 3, which are mobile and set in the patrol area, the patrol devices 3 are connected to the edge controller 2 through a wireless network signal, and the patrol devices 3 are used to obtain mobile image data and upload it through the edge controller 2; a database 4, which communicates with the edge controller 2 through a WAN network, and is used to receive and store fixed-point image data and mobile image data; a master control center 5, which communicates with the database 4 through a LAN network, and communicates with the edge controller 2 and the patrol device 3 through a WAN network; Exemplarily, when the edge controller 2 obtains the clear fixed-point image data through the LAN network, it performs preliminary recognition and judgment on the fixed-point image data, and the preliminary recognition and judgment includes the sudden change of static objects in the image data, the high-speed movement of dynamic objects, and the sudden change of image brightness. During the preliminary recognition and judgment, if the above sudden change occurs, it is determined that a preliminary abnormality has occurred, and the high-definition fixed-point image data is uploaded through the WAN network for further detailed judgment by the master control center 5, and stored in the database 4; if the preliminary recognition and judgment does not occur abnormally, the high-definition fixed-point image data is compressed, and the compressed fixed-point image data is uploaded through the WAN network to the master control center 5 for monitoring, and stored in the database 4.

[0025] Among them, the inspection device 3 includes an image acquisition module, an image display module, an alarm module, a positioning module and an inspection configuration module; the image acquisition module is used to acquire mobile image data, the image display module is used to display images, the alarm module is used to trigger or display alarm information, the positioning module is used to identify location information based on wireless network signals and SSID, and the inspection configuration module is used to set inspection paths and inspection cycles; all modules in the inspection device 3 communicate with the edge controller 2 via a wireless network.

[0026] Exemplarily, the image acquisition module may use a 4K ultra-high-definition camera module to collect high-definition moving image data. The image display module may use a flexible screen module; the alarm module may use an audio-visual alarm module; the positioning module may use a GPS positioning module or a Beidou positioning module. For a closed indoor environment, the positioning module may also use the SSID obtained by the wireless network module and the wireless network signal strength for indoor auxiliary positioning. If the wireless network signal provided by the edge controller 2 covers the entire indoor environment, the positioning module can read the wireless signal SSID and its strength at its location through software. According to the first three SSIDs and their strength values, the location information of the specific location of the positioning module can be calculated using the three-point positioning principle. The inspection configuration module can set the inspection path and inspection cycle. The setting of the inspection path and inspection cycle can display the inspection path through the image display module, which can facilitate the holder to inspect according to the specified route, or limit the automatic inspection robot to inspect according to the established route.

[0027] In one or more embodiments provided in the present application, the master control center 5 includes an image recognition module, which is used to recognize the content in the fixed-point image data and the moving image data, including facial information of people, image information of objects, and light intensity information.

[0028] In one or more embodiments provided in the present application, the main control center 5 includes an abnormality identification module, which determines the abnormality of the content in the fixed-point image data and the moving image data based on the historical data stored in the database 4; the historical data includes fixed-point image data and moving image data in previous time periods, and the content identified therefrom.

[0029] Exemplarily, the anomaly recognition module can use the fixed-point image data and moving image data content within the past 24 hours, 48 ​​hours or a week as the read historical data, and by comparing the historical data with the current image data, more accurate changes in the image anomalies of static objects can be obtained.

[0030] The judgment logic and basis of the abnormality identification module are slightly different from those of the edge controller 2. The edge controller 2 uses the changes in the previous and next frames and the static threshold as the judgment basis. For example, when the image brightness exceeds a fixed threshold, a fire alarm is prompted. The edge controller 2 reflects more instantaneous changes before and after, and then uploads the instantaneous high-definition fixed-point image data before and after the abnormality occurs to the abnormality identification module of the master control center 5 for further judgment.

[0031] The inspection device 3 can directly send high-definition moving image data to the main control center 5 through the WAN network. Since the inspection device 3 can be held or worn by a person, or carried on a mobile robot, compared with the video monitoring device 1, the inspection device 3 has a higher alarm authority and inspection priority. Therefore, the moving image data obtained by the inspection device 3 is directly uploaded to the main control center 5 through the WAN network, and the main control center 5 directly identifies and judges according to the content of the moving image data during the previous inspection.

[0032] In one or more implementations provided in the present application, the master control center 5 includes an alarm sending module, and the alarm sending module is used to send alarm information to the edge controller 2 through a WAN network.

[0033] In one or more embodiments provided in the present application, the alarm sending module sends abnormal fixed-point image data and / or moving image data to the inspection device 3 through the WAN network while sending the alarm information, and displays it through the image display module of the inspection device 3.

[0034] In one or more embodiments provided in the present application, the inspection device 3 is any combination of one or more of a handheld device, a wearable device, and a mobile robot.

[0035] In one or more implementations provided in the present application, the inspection configuration module communicates with the positioning module to obtain location information to correct and verify the inspection path.

[0036] like Figure 1 As shown, the present application provides a network-based video security inspection method, which uses the video security inspection system, including: S1: collect fixed-point image data and mobile image data through the network; S2: Identify the content in the fixed-point impact data and the moving image data; S3: Determine whether there is an abnormality in the content; if there is no abnormality, store the fixed-point image data and the moving image data and their contents; if there is an abnormality, broadcast an alarm message.

[0037] In one or more embodiments provided in the present application, before step S1, it also includes: preliminarily identifying and determining whether an abnormality occurs in the fixed-point image data. If no abnormality occurs, compressing the fixed-point image data and uploading it; if an abnormality occurs, uploading uncompressed fixed-point image data.

[0038] In one or more implementations provided in the present application, step S3 further includes: simultaneously broadcasting the fixed-point image data and the moving image data with the abnormality.

[0039] In this embodiment, the video security patrol system is applied to the external wall area and internal workshop area of ​​Factory A. The factory covers an area of ​​10,000 square meters, and the workshop is a closed space. The system includes: 20 4K ultra-high-definition network cameras are used as video surveillance devices 1, 10 of which are set around the fence and 10 are set on the roof of the workshop; the cameras collect high-definition video images of the peripheral and internal areas in real time as fixed-point image data.

[0040] Two edge controllers 2 are set up in the monitoring center room. Each server is connected to five cameras for preliminary identification and judgment of fixed-point image data. If it is judged that there is no abnormality, the image is compressed and encoded with H.265 to reduce the transmission bandwidth occupation; if it is judged that there is an abnormality, the original high-definition image is retained and transmitted to the main control center 5 in real time.

[0041] The edge controller 2 also provides wireless network function, and the signal covers the entire monitoring area.

[0042] One server is used as database 4 to store fixed-point image data. Database 4 has a redundant backup function to ensure that monitoring data is not lost.

[0043] 1 master control center 5, including content recognition module and abnormality recognition module. It can intelligently analyze pictures and videos, identify content elements such as personnel information, object information, and lighting changes; and can compare historical data to accurately determine abnormal situations. The master control center 5 is also connected to the alarm system, which can automatically trigger sound and light alarms after determining abnormalities.

[0044] Three handheld inspection devices 3 are carried by factory security personnel. They include 4K cameras, alarm modules, flexible display screens, WIFI positioning modules, and path configuration software. Security personnel conduct inspections in important areas at regular intervals according to the inspection routes set by the software. The images and videos collected by the handheld devices are directly transmitted to the master control center 5 for content analysis after being transferred by the edge controller 2.

[0045] During the night shift, a security guard begins patrolling the outside of the fence along the route set by the patrol software. The camera of the handheld device collects clear images in real time and displays them on the portable screen. The software of the master control center 5 analyzes the images at any time to determine whether there are any abnormalities.

[0046] When the security personnel walked to the vicinity of the main gate, the camera captured two suspicious persons wandering around the eaves. The main control center 5 quickly compared the facial features and indicated that the two persons were on the blacklist of the monitoring system. The center determined that it was an abnormal situation and immediately sent an alarm to the edge controller 2. The edge controller 2 pushed the alarm to the handheld device and popped up a voice alarm. At the same time, the real-time images collected by the regional camera were also transmitted to the handheld device. The security personnel understood the situation based on the video and quickly organized personnel to check the two suspicious persons.

[0047] After the perimeter inspection, the security personnel entered the workshop to continue the inspection. The handheld device determines the location based on the change in WIFI signal strength to ensure that each work area is inspected according to the prescribed route. When passing through the warehouse, the device camera captured an employee carrying a large amount of materials to be shipped out of the warehouse. The system determined that the facial features of the person did not match the identity of the warehouse personnel, and no corresponding outbound documents were captured, identifying it as an abnormal situation. The main control center 5 issued an alarm, and the security personnel immediately stepped forward to inquire after receiving the video footage.

[0048] With the help of the handheld inspection device 3, security personnel can fully monitor important areas and detect sudden abnormal situations in real time. The system ensures the safe operation of the factory.

[0049] In this embodiment, the video security patrol system is applied to the exterior wall, access control area and internal floor area of ​​Building B. The total area of ​​the building is 20,000 square meters, with 20 floors above ground. The system includes: 30 8K high-definition cameras are used as video surveillance devices1 to monitor the surroundings of the building, each entrance and each floor corridor. The peripheral and indoor corridor images are transmitted in real time as fixed-point image data. The cameras are equipped with autofocus and gain control functions.

[0050] 3 edge controllers 2, each server is connected to 10 cameras, and performs preliminary analysis on the images. If there is no abnormality, the images are compressed and encoded before transmission. If there is an abnormality, high-definition images are transmitted in real time. WIFI network signals are also provided for the entire building.

[0051] One server is used as a database 4 to store fixed-point image information and has redundancy to ensure that monitoring data is not lost.

[0052] A master control center 5, with content recognition module and abnormality recognition module, can accurately identify various types of image information and compare with historical data to determine abnormal situations. The center can perform speech synthesis and issue warning broadcasts in the event of abnormalities.

[0053] Five patrol robots equipped with 4K cameras are dispatched by the central control center 5 to conduct automatic patrols in important areas and floors. The robots have flexible screen displays, voice alarm modules, GPS / Beidou combined positioning modules, and patrol route planning modules. The images uploaded by the robots are directly transmitted to the central control center 5.

[0054] During the night shift, the control center 5 instructs the robot to patrol the perimeter according to the preset route. The robot uses GPS and Beidou combined positioning to determine its own position, and the surrounding cameras send back clear images in real time. The center software continuously analyzes images and monitors the condition of the exterior wall.

[0055] When the robot drove to the main gate, the camera captured a car parked in the prohibited parking area. The system automatically identified the license plate information and matched the database 4 without finding the corresponding access application record, judging it as an abnormal situation. The main control center 5 immediately sent an alarm to the security personnel and also transmitted the real-time image of the robot. After seeing the surveillance video, the security personnel quickly went to the scene to deal with it. After inspection, the car was driven by an unlicensed driver and had been intercepted by the security personnel.

[0056] After the perimeter patrol is over, the robot enters the building and continues patrolling along the planned route. WIFI positioning and route planning functions are used to ensure full coverage of each floor. When patrolling the floor at night, the camera captured an unidentified person appearing in the corridor. The center could not recognize the facial information and did not match any employee information, so it was judged as an abnormal situation. The main control center 5 uniformly dispatched the cameras in the area, obtained multi-angle image information, and sent video images and voice alarms to the security personnel. After receiving the complete image information, the security personnel went to the floor to intercept the suspicious person. After verification, the person was a friend of the owner, and the false alarm was caused because he was not registered.

[0057] With the help of robots, security personnel can fully understand the situation in the building and respond quickly to various abnormal events. The system improves the security level of the building area.

[0058] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, improvements, equivalent substitutions, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A network-based video security inspection system, characterized in that: include: Multiple video surveillance devices, which are distributed in the inspected area and are used to obtain fixed-point image data; Multiple edge controllers, which are used for network communication, data exchange, preliminary recognition and compression of fixed-point image data; one edge controller communicates with one or more of the video surveillance devices via a LAN network; the edge controller communicates with a WAN network; the edge controller has a wireless network communication function; A plurality of inspection devices, which are movably arranged in the inspected area, the inspection devices are connected to the edge controller via wireless network signals, and the inspection devices are used to obtain moving image data and upload it via the edge controller; A database, which communicates with the edge controller via a WAN network and is used to receive and store fixed-point image data and mobile image data; A master control center, which communicates with the database via a LAN network, and communicates with the edge controller and the inspection device via a WAN network; The inspection device includes an image acquisition module, an image display module, an alarm module, a positioning module and an inspection configuration module; the image acquisition module is used to acquire mobile image data, the image display module is used to display images, the alarm module is used to trigger or display alarm information, the positioning module is used to identify location information based on wireless network signals and SSIDs, and the inspection configuration module is used to set inspection paths and inspection cycles; The modules in the inspection device all communicate with the edge controller via a wireless network.

2. According to claim 1, the network-based video security inspection system is characterized in that: The master control center includes an image recognition module, which is used to recognize the content in the fixed-point image data and the moving image data, including personnel facial information, object image information and light intensity information.

3. According to claim 2, the network-based video security inspection system is characterized in that: The main control center includes an abnormality identification module, which determines the abnormality of the content in the fixed-point image data and the moving image data based on the historical data stored in the database; the historical data includes the fixed-point image data and the moving image data in the past time period, and the content identified therefrom.

4. The network-based video security inspection system according to claim 3 is characterized in that: The master control center includes an alarm sending module, and the alarm sending module is used to send alarm information to the edge controller through a WAN network.

5. The network-based video security inspection system according to claim 4, characterized in that: The alarm sending module sends the abnormal fixed-point image data and / or moving image data to the inspection device through the WAN network while sending the alarm information, and displays it through the image display module of the inspection device.

6. The network-based video security inspection system according to claim 1, characterized in that: The inspection device is any combination of one or more of a handheld device, a wearable device, and a mobile robot.

7. The network-based video security inspection system according to claim 1, characterized in that: The inspection configuration module communicates with the positioning module to obtain location information to correct and verify the inspection path.

8. A network-based video security patrol method, using the video security patrol system according to any one of claims 1 to 7, characterized in that: include: S1: collect fixed-point image data and mobile image data through the network; S2: Identify the content in the fixed-point impact data and the moving image data; S3: Determine whether there is an abnormality in the content; if there is no abnormality, store the fixed-point image data and the moving image data and their contents; If there is an abnormality, an alarm message will be broadcast.

9. The network-based video security inspection method according to claim 8, characterized in that: Before step S1, the method also includes: preliminarily identifying and determining whether an abnormality occurs in the fixed-point image data. If no abnormality occurs, the fixed-point image data is compressed and then uploaded; if an abnormality occurs, the uncompressed fixed-point image data is uploaded.

10. The network-based video security inspection method according to claim 8, characterized in that: Step S3 also includes: The fixed-point image data and the moving image data with abnormalities are broadcast simultaneously.

Images