Personnel behavior identification method and device, medium and equipment

Abstract

The embodiment of the invention discloses a personnel behavior recognition method and device, a medium and equipment, and relates to the technical field of personnel surveillance, and the method comprises the steps: taking an original image shot by a camera as a recognition basis, firstly extracting the feature information of a target person on the image, obtaining plane feature points under two-dimensional data, and carrying out the recognition of the target person; secondly, the feature points are matched, feature points representing the same feature information are obtained, the feature information on different original images is fused based on the feature points, and due to the fact that different cameras inevitably have the position relation in the space, in the process of fusing the plane feature points, the feature information of different cameras is fused; therefore, the positions of the feature points in the space can be restored according to the spatial position relation, and the obtained spatial feature points can more accurately and completely represent the behaviors of the personnel in the space, so that the accuracy of personnel behavior recognition is improved.

Description

Technical Field

[0001] The present application relates to the technical field of personnel monitoring, and in particular to a method, device, medium and equipment for identifying personnel behavior. Background Art

[0002] Personnel monitoring refers to the act of real-time or regular monitoring, observation and recording of personnel in a specific area. This monitoring can be achieved through technical means, such as cameras, face recognition, fingerprint recognition, etc., or through manual methods, such as patrols and observations. For some important areas, all-weather monitoring is required. The most commonly used method is to achieve this through surveillance cameras. By analyzing the camera images, the personnel in the image are identified, and the specific behavior of the personnel is identified through artificial intelligence algorithms. For example, if a person is identified to be wandering in a certain area, an alarm can be issued to indicate that there is a suspicious person. If a person is identified to be climbing near the fence, it may be an illegal intrusion. If a person is identified to be kicking or kicking in a certain area, it may be an illegal activity. This has a great effect on improving the effectiveness of personnel monitoring.

[0003] At present, the method of recognition based on the image captured by the camera is to first separate the person information on the image through the background subtraction algorithm, and then extract the feature data representing the person's behavior through edge detection or feature point detection, and finally use the artificial intelligence algorithm to complete the recognition of the person's behavior. This method has a disadvantage. Feature extraction and behavior recognition are based on two-dimensional data, and most human behaviors cannot be accurately described by two-dimensional data, which leads to inaccurate recognition of human behavior. Summary of the invention

[0004] The main purpose of this application is to provide a method, device, medium and equipment for personnel behavior recognition, aiming to solve the problem of inaccurate personnel behavior recognition based on images in the prior art.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for identifying human behavior, comprising the following steps:

[0007] Obtain at least two original images; wherein the original images contain a target person and are taken by cameras at different positions;

[0008] Extract the characteristic information of the target person on the original image and obtain the plane feature points;

[0009] Matching the plane feature points to determine the target plane feature points; wherein the target plane feature points are plane feature points that characterize the same feature information as the target person;

[0010] Based on the target plane feature points, the plane feature points are fused, and according to the spatial position relationship of the camera, the spatial position of the plane feature points is adjusted to obtain the spatial feature points;

[0011] Based on spatial feature points, the behavior of the target person is identified.

[0012] In a possible implementation manner of the first aspect, extracting feature information of a target person on an original image to obtain plane feature points includes:

[0013] Extract the feature information of the target person in the original image and obtain multi-scale planar feature points.

[0014] In a possible implementation of the first aspect, extracting feature information of a target person on an original image to obtain multi-scale planar feature points includes:

[0015] Based on the pixel stepping unit, the edge contour of the target person on the original image is gradually blurred, and the feature information of the target person on the original image after each blurring process is extracted to obtain multi-scale planar feature points.

[0016] In a possible implementation manner of the first aspect, before gradually blurring the edge contour of the target person on the original image based on the pixel stepping unit, the method further includes:

[0017] Determine the pixel stepping unit based on the spatial distance between the camera and the target person.

[0018] In a possible implementation manner of the first aspect, before fusing the plane feature points based on the target plane feature points and according to the spatial position relationship of the cameras, the method further includes:

[0019] According to the coordinate information of the camera in the spatial coordinate system, the spatial position relationship of the camera is obtained;

[0020] Adjust the spatial position of the plane feature points to obtain spatial feature points, including:

[0021] Adjust the coordinate parameters of the plane feature points in the spatial coordinate system to obtain the spatial feature points.

[0022] In a possible implementation manner of the first aspect, before obtaining the spatial position relationship of the camera according to the coordinate information of the camera in the spatial coordinate system, the method further includes:

[0023] Based on the principle that the most cameras are on the coordinate plane, a spatial coordinate system is established.

[0024] In a possible implementation manner of the first aspect, fusing the plane feature points based on the target plane feature points includes:

[0025] Based on the overlap of the target plane feature points, the feature information of the target person on the original image is superimposed to fuse the plane feature points.

[0026] In a second aspect, an embodiment of the present application provides a device for identifying human behavior, including:

[0027] An acquisition module, the acquisition module is used to acquire at least two original images; wherein the original images contain a target person, and the original images are obtained by taking pictures with cameras at different positions;

[0028] Extraction module, the extraction module is used to extract the characteristic information of the target person on the original image and obtain the plane feature points;

[0029] A matching module is used to match the plane feature points to determine the target plane feature points; wherein the target plane feature points are plane feature points that represent the same feature information as the target person;

[0030] A fusion module is used to fuse plane feature points based on target plane feature points, and adjust the spatial positions of the plane feature points according to the spatial position relationship of the camera to obtain spatial feature points;

[0031] Recognition module,The recognition module is used to identify the behavior of the target person based on,spatial feature points.

[0032] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, the method for identifying personnel behavior as provided in any one of the first aspects above is implemented.

[0033] In a fourth aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein:

[0034] The memory is used to store computer programs;

[0035] The processor is used to load and execute a computer program so that the electronic device executes a method for identifying human behavior as provided in any one of the first aspects above.

[0036] Compared with the prior art, the beneficial effects of this application are:

[0037] The embodiments of the present application propose a method, device, medium and equipment for identifying human behavior, the method comprising: obtaining at least two original images; wherein the original images contain a target person, and the original images are obtained by taking pictures with cameras at different positions; extracting feature information of the target person on the original images to obtain plane feature points; matching the plane feature points to determine target plane feature points; wherein the target plane feature points are plane feature points that characterize the same feature information of the target person; fusing the plane feature points based on the target plane feature points, and adjusting the spatial position of the plane feature points according to the spatial position relationship of the cameras to obtain spatial feature points; and identifying the behavior of the target person based on the spatial feature points. This application uses the original image obtained by camera shooting as the basis for recognition. First, the feature information of the target person on the image is extracted to obtain the plane feature points under the two-dimensional data. Secondly, the feature points are matched to obtain the feature points representing the same feature information. Based on these feature points, the feature information on different original images is fused. Since different cameras must have a positional relationship in space, the position of the feature points in space can be restored according to this spatial positional relationship during the fusion of plane feature points. The obtained spatial feature points can more accurately and completely represent the behavior of people in space, thereby improving the accuracy of identifying people's behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of the structure of an electronic device of a hardware operating environment involved in an embodiment of the present application;

[0039] Figure 2 A flowchart of a method for identifying human behavior provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of establishing a spatial coordinate system in the personnel behavior recognition method provided in an embodiment of the present application;

[0041] Figure 4 A schematic diagram of a module of a human behavior recognition device provided in an embodiment of the present application;

[0042] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] See attached Figure 1 , attached Figure 1This is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage; the processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0045] Those skilled in the art will appreciate that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0046] As attached Figure 1 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and a human behavior recognition device.

[0047] In the attached Figure 1 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the personnel behavior recognition device stored in the memory 105 through the processor 101, and executes the personnel behavior recognition method provided in the embodiment of the present application.

[0048] See attached Figure 2 Based on the hardware device of the aforementioned embodiment, the embodiment of the present application provides a method for identifying human behavior, comprising the following steps:

[0049] S10: Acquire at least two original images; wherein the original images contain the target person, and the original images are taken by cameras at different positions.

[0050] In the specific implementation process, the target person is the person whose behavior needs to be recognized in the original image. At least two original images can ensure that the corresponding different cameras have relative position differences in space. The image fed back by the monitoring camera is used as the original image to identify the behavior of the person. Usually the monitoring screen is presented in the form of video. The image can be extracted from the video by intercepting the frame data, but it should be noted that the original images must be taken at the same time.

[0051] S20: Extract feature information of the target person on the original image to obtain plane feature points.

[0052] In the specific implementation process, the recognition of human behavior depends on feature information. By characterizing the behavior of the target person, the edge contour features of the human body and the feature points of the key parts of the human body are extracted for identification. Due to the digitization process, the limbs of the human body can be simplified to a stick figure-like form according to the location of the joints. Compared with the unclear edge contour, this line representation method can more concisely express the human posture. Therefore, the embodiment of the present application adopts a feature point recognition method to extract the feature information on the image to obtain a series of planar feature points that represent the behavior of the person.

[0053] In order to improve the quality of feature points, so that it can retain more feature information of the person in the image and improve the ability to understand and analyze the image content, multi-scale feature extraction is performed on the original image, that is, the feature information of the target person in the original image is extracted to obtain plane feature points, including:

[0054] Extract the feature information of the target person in the original image and obtain multi-scale planar feature points.

[0055] In the specific implementation process, multi-scale features refer to features extracted at different spatial scales. In image processing, scale is usually associated with the size of the observed object. Since objects in an image may have different sizes, shapes, and structures, these changes can be better captured by using multi-scale features, thereby improving the understanding and analysis of image content. Multi-scale feature extraction methods include convolutional neural networks, which can extract features of different scales through their different layers. By combining features of different layers, multi-scale feature extraction can be achieved; there are also feature pyramid networks, which can achieve feature extraction and prediction at different scales by fusing features of different scales.

[0056] The embodiment of the present application provides a method of performing different scale scaling on an image to realize multi-scale feature point extraction. Specifically, feature information of a target person on an original image is extracted to obtain multi-scale planar feature points, including:

[0057] Based on the pixel stepping unit, the edge contour of the target person on the original image is gradually blurred, and the feature information of the target person on the original image after each blurring process is extracted to obtain multi-scale planar feature points.

[0058] In the specific implementation process, the original image is scaled to different scales, and the edge contour of the target person on the original image is gradually blurred by adjusting the pixels to gradually highlight the person's features, so as to capture image information at different scales, and obtain a series of image sets with gradually reduced resolutions. Then, the feature information on the original image after each blurring process is extracted to obtain features at different scales. In multi-scale feature extraction, the number of scales into which the feature information should be divided is a key factor. Too few scales will result in unsatisfactory improvement in the quality of feature points, and too many scales will increase a lot of calculations. Considering that there is a relative distance between the person and the camera in the actual space, this is used as the basis for multi-scale division, that is, based on the pixel step unit, before gradually blurring the edge contour of the target person on the original image, the method also includes:

[0059] Determine the pixel stepping unit based on the spatial distance between the camera and the target person.

[0060] The spatial distance between the camera and the target person is used as the basis for setting the pixel step unit. The farther the spatial distance, the larger the corresponding pixel step unit. Conversely, the closer the spatial distance, the smaller the pixel step unit. In this way, the number of times the scale is scaled for different original images can meet the feature extraction requirements without much difference.

[0061] S30: Match the plane feature points to determine the target plane feature points; wherein the target plane feature points are plane feature points that represent the same feature information as the target person.

[0062] In the specific implementation process, after extracting the planar feature points on different original images, in order to realize the fusion of the planar feature points into spatial feature points, it is necessary to determine a fusion benchmark. At this time, the use of feature point extraction comes into play. It can more directly and accurately determine whether the feature points extracted on different original images are the same feature through the characterization of the features of the person, thereby obtaining the target planar feature points.

[0063] S40: fusing the plane feature points based on the target plane feature points, and adjusting the spatial positions of the plane feature points according to the spatial position relationship of the cameras to obtain spatial feature points.

[0064] In the specific implementation process, the spatial feature points are obtained by fusing the plane feature points to more completely and accurately characterize the behavior of the person. The actual position relationship of the camera in space is used to restore the position of the plane feature points in space. Since the target plane feature points are determined, the overlap superposition method can be used in the fusion process, that is, the plane feature points are fused based on the target plane feature points, including: overlap based on the target plane feature points, superimpose the feature information of the target person on the original image, and fuse the plane feature points. First, overlap the target plane feature points, and then superimpose the feature points that represent the feature information, and then adjust the spatial position of the feature points except the target plane feature points according to the position relationship of the camera to achieve the fusion of the plane feature points.

[0065] In one embodiment, before fusing the plane feature points based on the target plane feature points and according to the spatial position relationship of the cameras, the method further includes:

[0066] According to the coordinate information of the camera in the spatial coordinate system, the spatial position relationship of the camera is obtained;

[0067] Adjust the spatial position of the plane feature points to obtain spatial feature points, including:

[0068] Adjust the coordinate parameters of the plane feature points in the spatial coordinate system to obtain the spatial feature points.

[0069] In the specific implementation process, in order to make the acquisition, fusion and adjustment of feature points more conducive to the execution of the algorithm, they are performed in the spatial coordinate system. The feature point position, camera position and position relationship can all be represented by coordinate information. Adjusting the spatial position of the plane feature point becomes the adjustment of the coordinate parameters in the spatial coordinate system, and this adjustment becomes the addition and subtraction of coordinate values ​​and the rotation of vectors. In order to further improve the computing efficiency, the establishment of the spatial coordinate system is optimized, and the spatial coordinate system is established based on the principle of the largest number of cameras on the coordinate plane. That is: according to the coordinate information of the camera in the spatial coordinate system, before obtaining the spatial position relationship of the camera, the method also includes:

[0070] Based on the principle that the most cameras are on the coordinate plane, a spatial coordinate system is established.

[0071] The principle of having the most cameras on the coordinate plane is to have more camera-represented points located on the X0Y, XOZ, and YOZ planes of the coordinate system, as shown in the following figure. Figure 3 As shown, two cameras are used, and both cameras are located on a coordinate plane. With the above settings, at least one coordinate value in the camera's coordinate representation will be zero, which can reduce the amount of calculation in subsequent processing.

[0072] S50: Identify the behavior of the target person based on the spatial feature points.

[0073] In the specific implementation process, behavior recognition technology identifies and understands human behavior by analyzing human behavior data. In behavior recognition based on feature points, the extracted feature point information of key parts of the human body is mainly used in combination with machine learning or deep learning algorithms to classify and identify human behavior. The basic steps include: data preprocessing, feature extraction, obtaining big data samples, and then using machine learning or deep learning algorithms such as support vector machines (SVM), random forests, convolutional neural networks (CNN), etc. through model training to learn and train the extracted feature information, build a model that can recognize different human behaviors, and input the extracted spatial feature points into the model as the behavior data of the person to be identified. Through calculation and analysis, the recognition result is obtained. This result is usually a label and / or probability distribution representing the category of the person's behavior.

[0074] In this embodiment, the original image obtained by taking a camera is used as the basis for recognition. First, the feature information of the target person on the image is extracted to obtain the plane feature points under the two-dimensional data. Secondly, the feature points are matched to obtain the feature points representing the same feature information. Based on these feature points, the feature information on different original images is fused. Since different cameras must have a positional relationship in space, in the process of fusing the plane feature points, the position of the feature points in space can be restored according to this spatial positional relationship. The obtained spatial feature points can more accurately and completely represent the behavior of people in space, thereby improving the accuracy of identifying people's behavior.

[0075] See attached Figure 4 Based on the same inventive concept as in the above-mentioned embodiment, the embodiment of the present application further provides a device for identifying human behavior, including:

[0076] An acquisition module, the acquisition module is used to acquire at least two original images; wherein the original images contain a target person, and the original images are obtained by taking pictures with cameras at different positions;

[0077] Extraction module, the extraction module is used to extract the characteristic information of the target person on the original image and obtain the plane feature points;

[0078] A matching module is used to match the plane feature points to determine the target plane feature points; wherein the target plane feature points are plane feature points that represent the same feature information as the target person;

[0079] A fusion module is used to fuse plane feature points based on target plane feature points, and adjust the spatial positions of the plane feature points according to the spatial position relationship of the camera to obtain spatial feature points;

[0080] Recognition module,The recognition module is used to identify the behavior of the target person based on,spatial feature points.

[0081] Those skilled in the art should understand that the division of the various modules in the embodiment is merely a division of logical functions, and in actual application, all or part of them can be integrated into one or more actual carriers, and these modules can all be implemented in the form of software called by a processing unit, or all in the form of hardware, or in the form of a combination of software and hardware. It should be noted that each module in the personnel behavior identification device in this embodiment corresponds one-to-one to each step in the personnel behavior identification method in the aforementioned embodiment. Therefore, the specific implementation method of this embodiment can refer to the implementation method of the aforementioned personnel behavior identification method, which will not be repeated here.

[0082] Based on the same inventive concept as in the aforementioned embodiment, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when loaded and executed by a processor, implements a method for identifying personnel behavior as provided in an embodiment of the present application.

[0083] Based on the same inventive concept as in the above-mentioned embodiment, an embodiment of the present application further provides an electronic device, including a processor and a memory, wherein:

[0084] The memory is used to store computer programs;

[0085] The processor is used to load and execute a computer program so that the electronic device executes a method for identifying human behavior as provided in an embodiment of the present application.

[0086] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0087] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0088] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0089] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0090] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0091] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0092] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0093] In summary, the present application provides a method, device, medium and equipment for identifying personnel behavior, which method includes: obtaining at least two original images; wherein the original images contain a target person, and the original images are obtained by taking pictures with cameras at different positions; extracting feature information of the target person on the original images to obtain plane feature points; matching the plane feature points to determine the target plane feature points; wherein the target plane feature points are plane feature points that characterize the same feature information of the target person; fusing the plane feature points based on the target plane feature points, and adjusting the spatial position of the plane feature points according to the spatial position relationship of the cameras to obtain spatial feature points; and identifying the behavior of the target person based on the spatial feature points. This application uses the original image obtained by camera shooting as the basis for recognition. First, the feature information of the target person on the image is extracted to obtain the plane feature points under the two-dimensional data. Secondly, the feature points are matched to obtain the feature points representing the same feature information. Based on these feature points, the feature information on different original images is fused. Since different cameras must have a positional relationship in space, the position of the feature points in space can be restored according to this spatial positional relationship during the fusion of plane feature points. The obtained spatial feature points can more accurately and completely represent the behavior of people in space, thereby improving the accuracy of identifying people's behavior.

[0094] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for identifying human behavior, characterized in that: The following steps are involved: Acquire at least two original images; wherein the original images contain a target person and are taken by cameras at different positions; Extracting feature information of the target person on the original image to obtain plane feature points; Matching the plane feature points to determine target plane feature points; wherein the target plane feature points are the plane feature points that characterize the same feature information as the target person; Based on the target plane feature points, the plane feature points are fused, and according to the spatial position relationship of the camera, the spatial positions of the plane feature points are adjusted to obtain spatial feature points; Based on the spatial feature points, the behavior of the target person is identified.

2. The method for identifying human behavior according to claim 1, characterized in that: The step of extracting feature information of the target person on the original image to obtain plane feature points includes: Extract feature information of the target person on the original image to obtain multi-scale planar feature points.

3. The method for identifying human behavior according to claim 2, characterized in that: The step of extracting feature information of the target person on the original image to obtain multi-scale planar feature points includes: Based on the pixel stepping unit, the edge contour of the target person on the original image is gradually blurred, and the feature information of the target person on the original image after each blurring process is extracted to obtain multi-scale planar feature points.

4. The method for identifying human behavior according to claim 3, characterized in that: Before the stepwise blurring of the edge contour of the target person on the original image based on the pixel stepping unit, the method further includes: The pixel stepping unit is determined according to the spatial distance between the camera and the target person.

5. The method for identifying human behavior according to claim 1, characterized in that: Before fusing the plane feature points based on the target plane feature points and according to the spatial position relationship of the cameras, the method further includes: Obtaining the spatial position relationship of the camera according to the coordinate information of the camera in the spatial coordinate system; The adjusting the spatial position of the plane feature point to obtain the spatial feature point includes: The coordinate parameters of the plane feature points in the space coordinate system are adjusted to obtain space feature points.

6. The method for identifying human behavior according to claim 5, characterized in that: Before obtaining the spatial position relationship of the camera according to the coordinate information of the camera in the spatial coordinate system, the method further includes: The space coordinate system is established based on the principle that the number of cameras is the largest on the coordinate plane.

7. The method for identifying human behavior according to claim 1, characterized in that: The fusing the plane feature points based on the target plane feature points comprises: Based on the overlap of the target plane feature points, the feature information of the target person on the original image is superimposed to fuse the plane feature points.

8. A device for identifying human behavior, characterized in that: include: An acquisition module, the acquisition module is used to acquire at least two original images; wherein the original images contain a target person, and the original images are obtained by taking pictures with cameras at different positions; An extraction module, the extraction module is used to extract feature information of the target person on the original image to obtain plane feature points; A matching module, the matching module is used to match the plane feature points to determine the target plane feature points; wherein the target plane feature points are the plane feature points that characterize the same feature information as the target person; A fusion module, the fusion module is used to fuse the plane feature points based on the target plane feature points, and adjust the spatial positions of the plane feature points according to the spatial position relationship of the camera to obtain spatial feature points; A recognition module is used to recognize the behavior of the target person based on the spatial feature points.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is loaded and executed by a processor, the method for identifying human behavior as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: comprising a processor and a memory, wherein: The memory is used to store computer programs; The processor is used to load and execute the computer program so that the electronic device executes the human behavior recognition method according to any one of claims 1 to 7.

Images