Monitoring and early warning method and system based on big data model, terminal and medium

Abstract

The invention is suitable for the technical field of monitoring and early warning, and provides a monitoring and early warning method and system based on a big data model, a terminal and a medium, and the method comprises the steps: firstly obtaining multi-frame continuous monitoring image information through employing a camera, then accurately generating event analysis result information according to the multi-frame monitoring image information and a preset big data model, and carrying out the early warning of the event. And finally, event alarm information is effectively generated according to event analysis result information. Normal behaviors and potential abnormal behaviors can be identified and distinguished, abnormal events can be automatically detected and responded, the possibility of safety risk increase caused by missing of key events is effectively reduced, alarms of corresponding levels can be given according to different severity degrees, monitoring personnel can more effectively manage a monitoring area, and the monitoring efficiency is improved. And the safety is further improved.

Description

Technical Field

[0001] The present application relates to the technical field of monitoring and early warning, and specifically, to a monitoring and early warning method, system, terminal and medium based on a big data model. Background Art

[0002] With the rapid development of the digital age, webcams, as a commonly used monitoring tool, are widely deployed in homes, commercial places and public areas. Their main function is to monitor the security of a specific area by capturing static images or video streams. Traditional cameras mainly include analog cameras, digital cameras and webcams. These devices help users identify and respond to various situations by recording visual information.

[0003] At present, traditional cameras rely on manual monitoring and lack the ability to automatically detect and respond to abnormal events. They are prone to missing key events and have high security risks, which needs further improvement. Summary of the invention

[0004] Based on this, the embodiments of the present application provide a monitoring and early warning method, system, terminal and medium based on a big data model to solve the problem of high security risks in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a monitoring and early warning method based on a big data model, the method comprising:

[0006] Based on the preset camera, obtain multiple frames of continuous monitoring image information;

[0007] Generate event analysis result information based on the multiple frames of monitoring image information and a preset big data model;

[0008] Event alarm information is generated according to the event analysis result information.

[0009] Compared with the prior art, the beneficial effects are: the monitoring and early warning method based on the big data model provided in the embodiment of the present application, the terminal device can first use the camera to obtain multiple frames of continuous monitoring image information, and then accurately generate event analysis result information based on the multiple frames of monitoring image information and the preset big data model, and finally effectively generate event alarm information based on the event analysis result information, thereby automatically detecting and responding to abnormal events, reducing the possibility of missing key events, reducing security risks, and to a certain extent solving the current problem of high security risks.

[0010] In a second aspect, an embodiment of the present application provides a monitoring and early warning system based on a big data model, the system comprising:

[0011] Monitoring image information acquisition module: used to obtain multiple frames of continuous monitoring image information based on a preset camera;

[0012] An event analysis result information generation module is used to generate event analysis result information based on multiple frames of monitoring image information and a preset big data model;

[0013] Event alarm information generation module: used to generate event alarm information according to the event analysis result information.

[0014] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect described above when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of the first aspect described above are implemented.

[0016] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0018] Figure 1 It is a flowchart of a monitoring and early warning method provided by an embodiment of the present application;

[0019] Figure 2 It is a flowchart of step S200 in the monitoring and early warning method provided in one embodiment of the present application;

[0020] Figure 3 It is a flowchart of step S220 in the monitoring and early warning method provided in one embodiment of the present application;

[0021] Figure 4 This is a first flow chart of step S223 in the monitoring and early warning method provided in one embodiment of the present application;

[0022] Figure 5 This is a first flow chart of step S230 in the monitoring and early warning method provided in one embodiment of the present application;

[0023] Figure 6 This is a second flow diagram of step S223 in the monitoring and early warning method provided in one embodiment of the present application;

[0024] Figure 7 This is a second flow diagram of step S230 in the monitoring and early warning method provided in one embodiment of the present application;

[0025] Figure 8 It is a flowchart of step S300 in the monitoring and early warning method provided in one embodiment of the present application;

[0026] Fig. 9 This is a module block diagram of a monitoring and early warning system provided by an embodiment of the present application;

[0027] Fig.10 It is a schematic diagram of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0028] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0029] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0030] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0031] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0032] See also Figure 1 , Figure 1: is a flow chart of the monitoring and early warning method based on the big data model provided in the embodiment of the present application. In the present embodiment, the execution subject of the monitoring and early warning method is a terminal device. It is understandable that the types of terminal devices include but are not limited to mobile phones, tablet computers, laptop computers, ultra-mobile personal computers (Ultra-Mobile Personal Computer, UMPC), netbooks, personal digital assistants (Personal Digital Assistant, PDA), etc., and the embodiment of the present application does not impose any restrictions on the specific types of terminal devices.

[0033] See also Figure 1 The monitoring and early warning method provided in the embodiment of the present application includes but is not limited to the following steps:

[0034] In S100, multiple frames of continuous monitoring image information are acquired based on a preset camera.

[0035] Specifically, the terminal device can obtain multiple frames of continuous monitoring image information based on the preset camera, which is suitable for application scenarios such as public safety, traffic management and commercial monitoring. The camera can be a high-definition camera to ensure the clarity of the image and video and provide high-quality input data for big data analysis; the monitoring image information is used to describe the monitoring image taken by the camera in real time.

[0036] In S200, event analysis result information is generated based on multiple frames of monitoring image information and a preset big data model.

[0037] Specifically, after the terminal device obtains multiple frames of continuous surveillance image information, the terminal device can input the multiple frames of surveillance image information into a preset big data model to generate event analysis result information, which is conducive to combining big data analysis technology to realize real-time analysis of the collected image and video data, identify abnormal behaviors or events, and learn historical data to predict possible security incidents. Among them, the big data model integrates a target detection algorithm and a behavior recognition algorithm; the behavior recognition algorithm can identify and distinguish normal behavior from potential abnormal behavior; the target detection algorithm can be a target detection algorithm based on YOLO V5 or a Faster R-CNN algorithm, and the behavior recognition algorithm can be a behavior recognition algorithm based on template matching or a behavior recognition algorithm based on a hidden Markov model.

[0038] In some possible implementations, in order to generate valid event analysis result information, please refer to Figure 2 Step S200 includes but is not limited to the following steps:

[0039] In S210, target detection processing is performed on each frame of monitoring image information based on a target detection algorithm to generate object information to be analyzed corresponding to each frame of monitoring image information and object identification information corresponding to each piece of object information to be analyzed.

[0040] Specifically, the terminal device can perform target detection processing on each frame of monitoring image information based on the target detection algorithm, generate object information to be analyzed corresponding to each frame of monitoring image information, and generate object identification information corresponding to each object information to be analyzed, wherein the object information to be analyzed is used to describe the object of the specific behavior to be analyzed in the monitoring image information, and the object identification information is used to describe the unique identifier corresponding to the object of the specific behavior to be analyzed, thereby facilitating the distinction between different objects in the same frame of monitoring image information, and determining the same object in different frames of monitoring image information.

[0041] In S220, based on the behavior recognition algorithm, behavior recognition processing is performed on the target object information to generate object behavior information.

[0042] Specifically, after the terminal device generates object identification information, the terminal device can perform behavior recognition processing on the target object information based on the behavior recognition algorithm, and quickly generate object behavior information, thereby realizing comprehensive analysis of the behavior of the same object by combining the same objects in different frames of monitoring image information, wherein the target object information is used to describe multiple objects to be analyzed with the same object identification information.

[0043] In S230, event analysis result information is generated based on the object behavior information.

[0044] Specifically, after the terminal device generates the object behavior information, the terminal device can accurately generate event analysis result information based on the object behavior information.

[0045] In some possible implementations, the object behavior information includes fighting behavior information and / or injured behavior information. To effectively generate the object behavior information, refer to Figure 3 Step S220 includes but is not limited to the following steps:

[0046] In S221, multiple target torso skeleton point information is generated according to the behavior recognition algorithm and the target object information.

[0047] Specifically, the terminal device can generate multiple target torso bone point information based on the behavior recognition algorithm and the target object information, wherein the target torso bone point information is used to describe the bone points corresponding to the torso of the target object information, such as the head, neck, chest, shoulders, elbows, wrists, pelvis, knees and ankles.

[0048] In S222, object joint information is generated based on multiple target torso bone point information.

[0049] Specifically, after the terminal device generates multiple target torso bone point information, the terminal device can generate object joint information based on the multiple target torso bone point information, wherein the object joint information is used to describe the joints corresponding to the torso of the target object information, and the object joint information can be a line segment connected by two adjacent target torso bone point information.

[0050] In S223, object behavior information is generated based on the object joint information.

[0051] Specifically, after the terminal device generates the object joint information, the terminal device can accurately generate the object behavior information based on the object joint information.

[0052] In some possible implementations, in order to accurately generate object behavior information, see Figure 4 Step S223 includes but is not limited to the following steps:

[0053] In S2231, motion trajectory information is generated based on the object joint information.

[0054] Specifically, the terminal device may generate motion trajectory information based on object joint information in multiple frames of continuous monitoring image information, wherein the motion trajectory information is used to describe the motion trajectory of the object joint information.

[0055] In S2232, trajectory similarity information is generated according to the motion trajectory information and the preset fighting trajectory information.

[0056] Specifically, after the terminal device generates motion trajectory information, the terminal device can generate trajectory similarity information based on the motion trajectory information and preset fighting trajectory information, wherein the fighting trajectory information is used to describe the joint motion trajectory of a person when he is in a fighting state. For example, the terminal device can calculate the Euclidean distance value between each trajectory point, that is, the point that constitutes the motion trajectory, and then average the Euclidean distance values ​​of all trajectory points to determine the trajectory similarity information.

[0057] In S2233, the trajectory similarity information is compared with a preset similarity threshold.

[0058] Specifically, after the terminal device generates trajectory similarity information, the terminal device can compare the trajectory similarity information with a preset similarity threshold, where the similarity threshold is a preset value, thereby allowing monitoring personnel to customize thresholds and response measures, enabling monitoring personnel to manage the monitoring area more effectively and improve the practicality of the monitoring and early warning method.

[0059] In S2234, if the trajectory similarity information is greater than the similarity threshold, fighting behavior information is generated.

[0060] Specifically, if the trajectory similarity information is greater than a similarity threshold, the terminal device may generate fighting behavior information, wherein the fighting behavior information is used to describe abnormal fighting behavior.

[0061] In S2235, joint angle information is generated based on the object joint information.

[0062] Specifically, after the terminal device generates the fighting behavior information, the terminal device may generate joint angle information according to the object joint information, wherein the joint angle information is used to describe the angle between two adjacent object joint information.

[0063] In S2236, the joint angle information is compared with a preset healthy angle threshold.

[0064] Specifically, after the terminal device generates joint angle information, the terminal device can compare the joint angle information with a preset healthy angle threshold, wherein the healthy angle threshold is a preset value, and the healthy angle threshold can be the valgus angle. For example, for the joint angle information specifically of the elbow angle, the healthy angle threshold can be 10 degrees.

[0065] In S2237, if the joint angle information is greater than the healthy angle threshold, the injury behavior information is generated.

[0066] Specifically, if the joint angle information is greater than the healthy angle threshold, the terminal device can generate injury behavior information, where the injury behavior information is used to describe the abnormal behavior of the injury.

[0067] Accordingly, the event analysis result information includes fighting event information and / or injury event information, wherein the fighting event information is used to describe a fighting event between people, and the injury event information is used to describe an injury event between people; see Figure 5 Step S230 includes but is not limited to the following steps:

[0068] In S231, fighting event information is generated based on the fighting behavior information.

[0069] Specifically, the terminal device can generate fighting event information based on the fighting behavior information, thereby automatically determining the key event of a fight between people at the monitoring scene.

[0070] In S232, injury event information is generated based on the injury behavior information.

[0071] Specifically, after the terminal device generates fighting event information, the terminal device can generate injury event information based on the injury behavior information, thereby automatically determining the key event of personal injury at the monitoring site.

[0072] In some possible implementations, the object behavior information also includes theft behavior information and / or vandalism behavior information; in order to further generate accurate object behavior information, before step S230, the method further includes but is not limited to the following steps:

[0073] In S2301, commodity location information and public facility location information are generated based on the target detection algorithm and monitoring image information.

[0074] Specifically, the terminal device can use the target detection algorithm to detect and process the monitoring image information to generate product location information and public facility location information, where the product location information is used to describe the corresponding location of the products at the monitoring site, and the public facility location information is used to describe the corresponding location of the public facilities at the monitoring site.

[0075] In some possible implementations, to further achieve accurate generation of object behavior information, see Figure 6 Step S223 includes but is not limited to the following steps:

[0076] In S2238, it is determined whether the object joint information overlaps with the product position information.

[0077] Specifically, the terminal device can determine whether the object joint information coincides with the product location information, thereby determining whether a person has touched the product.

[0078] In S2239, if the object joint information and the product position information coincide with each other, the moving speed information of the target object information is acquired.

[0079] Specifically, if the object joint information coincides with the commodity position information, the terminal device may obtain the moving speed information of the target object information, wherein the moving speed information is used to describe the moving speed of the target object information.

[0080] In S22391, the moving speed information is compared with a preset normal speed threshold.

[0081] Specifically, after the terminal device obtains the moving speed information, the terminal device can compare the moving speed information with a preset normal speed threshold, wherein the normal speed threshold is used to describe the normal moving speed of a person, and exemplarily, the normal speed threshold can be 7 meters per second.

[0082] In S22392, if the moving speed information is greater than the normal speed threshold, theft behavior information is generated.

[0083] Specifically, if the moving speed information is greater than a regular speed threshold, the terminal device may generate theft behavior information.

[0084] In S22393, it is determined whether the object joint information coincides with the public facility position information.

[0085] Specifically, the terminal device can determine whether the object joint information coincides with the public facility location information, thereby determining whether a person has contact with the public facility.

[0086] In S22394, if the object joint information coincides with the public facility position information, the first public facility outer contour information and the second public facility outer contour information are acquired.

[0087] Specifically, if the object joint information coincides with the public facility location information, the terminal device can obtain first public facility outer contour information and second public facility outer contour information, wherein the first public facility outer contour information is used to describe the outer contour corresponding to the public facility before the object joint information coincides with the public facility location information, and the second public facility outer contour information is used to describe the outer contour corresponding to the public facility after the object joint information coincides with the public facility location information.

[0088] In S22395, it is determined whether the first public facility outer contour information overlaps with the second public facility outer contour information.

[0089] Specifically, after the terminal device obtains the first public facility outer contour information and the second public facility outer contour information, the terminal device may determine whether the first public facility outer contour information coincides with the second public facility outer contour information.

[0090] In S22396, if the first public facility outer contour information does not overlap with the second public facility outer contour information, vandalism information is generated.

[0091] Specifically, if the first public facility outer contour information does not overlap with the second public facility outer contour information, the terminal device may generate vandalism information.

[0092] In some possible implementations, the event analysis result information includes theft event information and / or vandalism event information, wherein the theft event information is used to describe a theft event by a person, and the vandalism event information is used to describe a vandalism event by a person; see Figure 7 Step S230 includes but is not limited to the following steps:

[0093] In S233, theft event information is generated based on the theft behavior information.

[0094] Specifically, the terminal device can accurately generate theft event information based on the theft behavior information, thereby automatically determining the key event of theft at the monitoring site.

[0095] In S234, vandalism event information is generated based on the vandalism behavior information.

[0096] Specifically, the terminal device can accurately generate information about vandalism events based on information about vandalism, thereby automatically determining key events where someone has vandalized public property at the monitoring site.

[0097] In S300, event alarm information is generated according to the event analysis result information.

[0098] Specifically, the terminal device can generate event alarm information based on the event analysis result information, wherein the event alarm information is used to describe the alarm issued to alert monitoring personnel to abnormal events; the event alarm information includes ordinary alarm information and serious alarm information, wherein ordinary alarm information is used to describe ordinary level alarms, and serious alarm information is used to describe serious level alarms, so that once abnormal behavior or events are detected, an alarm is immediately triggered, and it is helpful to distinguish the severity and urgency of the event, ensuring that monitoring personnel can respond in a timely manner.

[0099] In some possible implementations, to generate event alert information, see Figure 8 Step S300 includes but is not limited to the following steps:

[0100] In S310, it is determined whether the event analysis result information includes both fighting behavior information and injury behavior information.

[0101] Specifically, the terminal device can determine whether the event analysis result information includes both fighting behavior information and injury behavior information.

[0102] In S320, if the event analysis result information includes both fighting behavior information and injured behavior information, severe alarm information is generated, otherwise, ordinary alarm information is generated.

[0103] Specifically, if the event analysis result information includes both fighting behavior information and injury behavior information, the terminal device can generate severe alarm information to determine a severe level of abnormal event; otherwise, the terminal device can generate ordinary alarm information to determine an ordinary level of abnormal event.

[0104] In one possible implementation, the terminal device can continuously optimize the deep learning model, that is, the big data model, to improve the recognition accuracy of complex scenarios and behaviors. Through continuous training and learning, the big data model can more accurately distinguish between normal and abnormal behaviors and reduce false alarms and missed alarms.

[0105] Without loss of generality, the user interface of the monitoring terminal corresponding to the monitoring personnel can include real-time video streams, alarm logs and event statistics at the same time, and its operation interface can also be relatively simple, so as to facilitate the monitoring personnel to quickly view the alarm details and take corresponding measures, such as ensuring that the operation interface can automatically adjust the layout and display method according to the user's device and preferences, thereby providing a more personalized user experience and adapting to the specific needs of different users.

[0106] In one possible implementation, the terminal device can store the processed data in a secure database for analysis and auditing. At the same time, the terminal device can regularly conduct in-depth analysis of the stored data and optimize the recognition algorithm to improve the accuracy and efficiency of the system; each execution step of the monitoring and early warning method can adopt encryption technology and security protocols to prevent data leakage and unauthorized access; the monitoring and early warning method can run stably on different hardware and software platforms to meet the needs of different users.

[0107] Without loss of generality, monitoring personnel can implement redundant system design for terminal devices to ensure that key components such as servers and storage devices are backed up to prevent data loss or service interruption caused by system failures; terminal devices can provide open API interfaces, allowing third-party developers and service providers to easily integrate and expand the functions of the monitoring and early warning system, thereby enhancing the compatibility and scalability of the monitoring and early warning system.

[0108] The implementation principle of the monitoring and early warning method based on the big data model in the embodiment of the present application is: the terminal device can first use the camera to obtain multiple frames of continuous monitoring image information, and then accurately generate event analysis result information based on the multiple frames of monitoring image information and the preset big data model. Finally, based on the event analysis result information, effectively generate event alarm information, thereby automatically detecting and responding to abnormal events, reducing the possibility of missing key events, reducing security risks, and improving safety.

[0109] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0110] The embodiment of the present application also provides a monitoring and early warning system based on a big data model. For ease of description, only the parts related to the present application are shown, such as Fig. 9 As shown, the system 90 includes:

[0111] Monitoring image information acquisition module 91: used to acquire multiple frames of continuous monitoring image information based on a preset camera;

[0112] The event analysis result information generating module 92 is used to generate event analysis result information according to the multi-frame monitoring image information and the preset big data model;

[0113] Event alarm information generating module 93: used to generate event alarm information according to event analysis result information.

[0114] Optionally, the big data model integrates a target detection algorithm and a behavior recognition algorithm; the event analysis result information generation module 92 includes:

[0115] The submodule for generating information of the object to be analyzed is used to perform target detection processing on each frame of monitoring image information based on the target detection algorithm, and generate the information of the object to be analyzed corresponding to each frame of monitoring image information and the object identification information corresponding to each piece of information of the object to be analyzed;

[0116] The object behavior information generation submodule is used to perform behavior recognition processing on the target object information based on the behavior recognition algorithm to generate object behavior information, wherein the target object information is used to describe multiple objects to be analyzed with the same object identification information;

[0117] Event analysis result information generation submodule: used to generate event analysis result information based on object behavior information.

[0118] Optionally, the object behavior information includes fighting behavior information and / or injury behavior information; the object behavior information generation submodule includes:

[0119] Target trunk skeleton point information generation unit: used to generate multiple target trunk skeleton point information according to the behavior recognition algorithm and target object information;

[0120] Object joint information generating unit: used for generating object joint information according to multiple target trunk bone point information;

[0121] An object behavior information generating unit: used for generating object behavior information based on object joint information;

[0122] Optionally, the object behavior information generating unit includes:

[0123] Motion trajectory information generation subunit: used to generate motion trajectory information according to object joint information;

[0124] The trajectory similarity information generating subunit is used to generate trajectory similarity information according to the motion trajectory information and the preset fighting trajectory information;

[0125] Trajectory similarity information comparison subunit: used to compare trajectory similarity information with a preset similarity threshold;

[0126] A fighting behavior information generating subunit: used for generating fighting behavior information if the trajectory similarity information is greater than a similarity threshold;

[0127] Joint angle information generating subunit: used for generating joint angle information according to object joint information;

[0128] Joint angle information comparison subunit: used to compare joint angle information with a preset healthy angle threshold;

[0129] Injury behavior information generating subunit: used to generate injury behavior information if the joint angle information is greater than the healthy angle threshold;

[0130] Accordingly, the event analysis result information includes fighting event information and / or injury event information; the above-mentioned event analysis result information generation submodule includes:

[0131] A fighting event information generating unit: used to generate fighting event information according to fighting behavior information;

[0132] Injury event information generating unit: used to generate injury event information according to injury behavior information.

[0133] Optionally, the object behavior information also includes theft behavior information and / or vandalism behavior information; the system 90 also includes:

[0134] Commodity location information generation module: used to generate commodity location information and public facility location information based on target detection algorithm and monitoring image information;

[0135] Optionally, the object behavior information generating unit includes:

[0136] Object joint information judgment subunit: used to judge whether the object joint information coincides with the commodity position information;

[0137] The moving speed information acquisition subunit is used to acquire the moving speed information of the target object information if the object joint information coincides with the commodity position information;

[0138] Moving speed information comparison subunit: used to compare the moving speed information with a preset conventional speed threshold;

[0139] Theft behavior information generating subunit: used for generating theft behavior information if the moving speed information is greater than the normal speed threshold;

[0140] Object joint information judgment subunit: used to judge whether the object joint information coincides with the public facility location information;

[0141] A public facility outer contour information acquisition subunit: used for acquiring first public facility outer contour information and second public facility outer contour information if the object joint information coincides with the public facility position information, wherein the first public facility outer contour information is used to describe the outer contour corresponding to the public facility before the object joint information coincides with the public facility position information, and the second public facility outer contour information is used to describe the outer contour corresponding to the public facility after the object joint information coincides with the public facility position information;

[0142] A public facility outer contour information determination subunit: used to determine whether the first public facility outer contour information coincides with the second public facility outer contour information;

[0143] A vandalism information generating subunit: used for generating vandalism information if the first public facility outer contour information does not overlap with the second public facility outer contour information;

[0144] Accordingly, the event analysis result information includes theft event information and / or vandalism event information; the event analysis result information generation submodule includes:

[0145] Theft event information generating unit: used to generate theft event information according to theft behavior information;

[0146] The vandalism event information generating unit is used to generate vandalism event information according to the vandalism behavior information.

[0147] Optionally, the event alarm information includes common alarm information and serious alarm information; the event alarm information generating module 93 includes:

[0148] The event analysis result information judgment submodule is used to judge whether the event analysis result information includes both fighting behavior information and injury behavior information;

[0149] Severe alarm information generation submodule: used to generate severe alarm information if the event analysis result information includes both fighting behavior information and injury behavior information, otherwise generate ordinary alarm information.

[0150] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0151] The present application also provides a terminal device, such as Fig.10As shown, the terminal device 100 of this embodiment includes: a processor 101, a memory 102, and a computer program 103 stored in the memory 102 and executable on the processor 101. When the processor 101 executes the computer program 103, the steps in the above-mentioned monitoring and early warning method embodiment are implemented, for example Figure 1 Steps S100 to S300 shown; or, when the processor 101 executes the computer program 103, the functions of each module in the above device are implemented, for example Fig. 9 The functions of modules 91 to 93 are shown.

[0152] The terminal device 100 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device 100 includes but is not limited to a processor 101 and a memory 102. Those skilled in the art will appreciate that Fig.10 It is only an example of the terminal device 100 and does not constitute a limitation of the terminal device 100. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 100 may also include input and output devices, network access devices, buses, etc.

[0153] Among them, the processor 101 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0154] The memory 102 may be an internal storage unit of the terminal device 100, such as a hard disk or memory of the terminal device 100, or an external storage device of the terminal device 100, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the terminal device 100; further, the memory 102 may also include both an internal storage unit and an external storage device of the terminal device 100, and the memory 102 may also store the computer program 103 and other programs and data required by the terminal device 100, and the memory 102 may also be used to temporarily store data that has been output or is to be output.

[0155] One embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of each of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.; the computer-readable medium may include: any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0156] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, all equivalent changes made according to the methods, principles, and structures of the present application should be included in the protection scope of the present application.

Claims

1. A monitoring and early warning method based on a big data model, characterized in that: The method comprises: Based on the preset camera, obtain multiple frames of continuous monitoring image information; Generate event analysis result information based on the multiple frames of monitoring image information and a preset big data model; Event alarm information is generated according to the event analysis result information.

2. The method according to claim 1, characterized in that: The big data model integrates a target detection algorithm and a behavior recognition algorithm; the event analysis result information is generated according to the multiple frames of monitoring image information and the preset big data model, including: Based on the target detection algorithm, target detection processing is performed on each frame of the monitoring image information to generate the object information to be analyzed corresponding to each frame of the monitoring image information and the object identification information corresponding to each piece of the object information to be analyzed; Based on the behavior recognition algorithm, the target object information is subjected to behavior recognition processing to generate object behavior information, wherein the target object information is used to describe a plurality of the to-be-analyzed object information having the same object identification information; Based on the object behavior information, event analysis result information is generated.

3. The method according to claim 2, characterized in that The object behavior information includes fighting behavior information and / or injured behavior information; the target object information is subjected to behavior recognition processing based on the behavior recognition algorithm to generate the object behavior information, including: Generate multiple target torso skeleton point information according to the behavior recognition algorithm and the target object information; Generating object joint information according to the plurality of target torso bone point information; Based on the object joint information, generating the object behavior information; Wherein, generating the object behavior information based on the object joint information includes: Generate motion trajectory information according to the object joint information; Generate trajectory similarity information according to the motion trajectory information and preset fighting trajectory information; Comparing the trajectory similarity information with a preset similarity threshold; If the trajectory similarity information is greater than the similarity threshold, generating fighting behavior information; Generate joint angle information according to the object joint information; Comparing the joint angle information with a preset healthy angle threshold; If the joint angle information is greater than the healthy angle threshold, generating injury behavior information; Accordingly, the event analysis result information includes fighting event information and / or injury event information; and generating the event analysis result information based on the object behavior information includes: generating the fighting event information according to the fighting behavior information; The injury event information is generated according to the injury behavior information.

4. The method according to claim 3, characterized in that The object behavior information also includes theft behavior information and / or vandalism behavior information; before generating event analysis result information based on the object behavior information, the method also includes: Generate commodity location information and public facility location information according to the target detection algorithm and the monitoring image information; The generating of the object behavior information based on the object joint information includes: Determining whether the object joint information coincides with the commodity position information; If the object joint information coincides with the commodity position information, obtaining the moving speed information of the target object information; Comparing the moving speed information with a preset conventional speed threshold; If the moving speed information is greater than the normal speed threshold, generating theft behavior information; Determining whether the object joint information coincides with the public facility location information; If the object joint information coincides with the public facility location information, first public facility outer contour information and second public facility outer contour information are obtained, wherein the first public facility outer contour information is used to describe the outer contour corresponding to the public facility before the object joint information coincides with the public facility location information, and the second public facility outer contour information is used to describe the outer contour corresponding to the public facility after the object joint information coincides with the public facility location information; Determining whether the first public facility outer contour information coincides with the second public facility outer contour information; If the first public facility outer contour information does not overlap with the second public facility outer contour information, generating vandalism information; Accordingly, the event analysis result information includes theft event information and / or vandalism event information; the generating of the event analysis result information based on the object behavior information includes: Generating theft event information according to the theft behavior information; The vandalism event information is generated according to the vandalism behavior information.

5. The method according to claim 3, characterized in that: The event alarm information includes common alarm information and serious alarm information; Generating event alarm information according to the event analysis result information includes: Determining whether the event analysis result information includes both the fighting behavior information and the injury behavior information; If the event analysis result information includes both the fighting behavior information and the injured behavior information, the severe alarm information is generated; otherwise, the ordinary alarm information is generated.

6. A monitoring and early warning system based on a big data model, characterized in that: The system comprises: Monitoring image information acquisition module: used to obtain multiple frames of continuous monitoring image information based on a preset camera; An event analysis result information generation module is used to generate event analysis result information based on multiple frames of monitoring image information and a preset big data model; Event alarm information generation module: used to generate event alarm information according to the event analysis result information.

7. The system according to claim 6, characterized in that The big data model integrates a target detection algorithm and a behavior recognition algorithm; the event analysis result information generation module includes: The submodule for generating information of the object to be analyzed is used to perform target detection processing on each frame of the monitoring image information based on the target detection algorithm, and generate the information of the object to be analyzed corresponding to each frame of the monitoring image information and the object identification information corresponding to each piece of the information of the object to be analyzed; The object behavior information generation submodule is used to perform behavior recognition processing on the target object information based on the behavior recognition algorithm to generate object behavior information, wherein the target object information is used to describe a plurality of the object information to be analyzed having the same object identification information; Event analysis result information generation submodule: used to generate event analysis result information based on the object behavior information.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images