Shooting behavior detection method, device, electronic device and storage medium

Abstract

The present application relates to a shooting behavior detection method, device, electronic device and storage medium, wherein the shooting behavior detection method obtains an image sequence captured by a monitoring device; detects the image acquisition device and the target display device in the image sequence, and respectively determines a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device; determines a first plane corresponding to the display screen of the image acquisition device in the first 3D bounding box, and determines a second plane corresponding to the display screen of the target display device in the second 3D bounding box; based on the positional relationship between the first plane and the second plane, determines whether there is a target shooting behavior. Through this application, the problem of many false detections and false alarms and low detection accuracy in the detection of customer privacy shooting in the related art is solved, and the judgment of shooting behavior is determined according to the positional relationship between the image acquisition device and the target display device.

Description

Technical Field

[0001] The present application relates to the field of computer vision, and in particular to a method, device, electronic device and storage medium for detecting shooting behavior. Background Art

[0002] With the improvement of computer computing power and the development of deep learning technology, artificial intelligence products are increasingly used in people's daily lives. In the relevant technical field, counter service is a common customer service method. During the counter service process, the customer's privacy information is often displayed, and the customer's privacy information needs to be protected. Therefore, it is necessary to check whether the customer's privacy information is photographed to reduce the leakage of customer privacy.

[0003] In the related art, during the teller service process, whether the teller takes private photos of customers is detected only by detecting whether there is a shooting device, which results in many false detections and false alarms and low detection accuracy. At the same time, the related art uses single target detection or artificial intelligence to identify illegal shooting behaviors, and the algorithm has low robustness and accuracy.

[0004] There are many false detections and false alarms in the detection of customer privacy photos in related technologies, and the detection accuracy is low. Currently, no effective solution has been proposed. Summary of the invention

[0005] In this embodiment, a shooting behavior detection method, device, electronic device and storage medium are provided to solve the problem of high number of false detections and false alarms and low detection accuracy in the detection of customer privacy shooting in the related art.

[0006] In a first aspect, a shooting behavior detection method is provided in this embodiment, comprising: acquiring an image sequence captured by a monitoring device; detecting an image acquisition device and a target display device in the image sequence, and respectively determining a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device; determining a first plane of the display screen of the image acquisition device in the first 3D bounding box, and determining a second plane of the display screen of the target display device in the second 3D bounding box; based on the positional relationship between the first plane and the second plane, determining whether there is a target shooting behavior, wherein the target shooting behavior includes using the image acquisition device to shoot the display screen of the target display device.

[0007] In some embodiments, determining whether there is a target shooting behavior based on the positional relationship between the first plane and the second plane includes: determining an angle between the first plane and the second plane; if it is determined that the angle is less than a preset angle threshold, determining that there is the target shooting behavior.

[0008] In some of the embodiments, before determining the angle between the first plane and the second plane, the method further includes: determining that a display screen of the image acquisition device is in use based on the first 3D bounding box; and determining that a display screen of the target display device is in use based on the second 3D bounding box.

[0009] In some of the embodiments, determining that the display screen of the image acquisition device is in use based on the first 3D bounding box includes: determining that the mean of pixels corresponding to the first 3D bounding box is greater than a first pixel threshold; determining that the display screen of the target display device is in use based on the second 3D bounding box includes: determining that the mean of pixels corresponding to the second 3D bounding box is greater than a second pixel threshold.

[0010] In some of the embodiments, after acquiring an image sequence captured by a monitoring device, the detection method further includes: determining a first image frame corresponding to a preset target area from the image sequence, wherein the preset target area is used to characterize an area where a target person in the image sequence is located; determining hand feature points corresponding to the target person from the first image frame; if it is determined that the number of hand feature points that are within the first 3D bounding box is greater than a preset number threshold, detecting an image acquisition device and a target display device in the image sequence.

[0011] In some of the embodiments, after determining the first image frame corresponding to the preset target area from the image sequence, the method further includes: performing human target detection in the first image frame through a target detection algorithm to generate target detection information; if it is determined that the target detection information includes a human target frame, then determining that the human target is detected from the first image frame, wherein the human target frame is used to mark the target person.

[0012] In some embodiments, determining the angle between the first plane and the second plane includes: determining a first normal vector of the first plane in a preset direction, and determining a second normal vector corresponding to the second plane in the preset direction; and determining the angle between the first normal vector and the second normal vector as the angle between the first plane and the second plane.

[0013] In some embodiments, the method also includes: using a preset 3D target detection algorithm to detect a first 3D projection coordinate corresponding to the first plane in the monitoring device coordinate system, and detecting a second 3D projection coordinate corresponding to the second plane in the monitoring device coordinate system; processing the first 3D projection coordinate and the second 3D projection coordinate respectively by a preset posture estimation algorithm to obtain first 3D spatial position information and second 3D spatial position information, wherein the first 3D spatial position information represents the coordinate information of the first plane in the world coordinate system, and the second 3D spatial position information represents the coordinate information of the second plane in the world coordinate system; determining the distance between the first plane and the second plane according to the first 3D spatial position information and the second 3D spatial position information; if it is determined that the distance is less than a preset distance threshold, determining the angle between the first plane and the second plane.

[0014] In some embodiments, if it is determined that the angle is less than a preset angle threshold, determining that the target shooting behavior exists includes: determining a third normal vector corresponding to the first plane based on the first 3D spatial position information, and determining a fourth normal vector corresponding to the second plane based on the second 3D spatial position information; determining the angle between the third normal vector and the fourth normal vector to obtain a second angle, and if it is determined that the second angle is less than the preset angle threshold, determining that the target shooting behavior exists.

[0015] In some of the embodiments, if it is determined that the angle is less than a preset angle threshold, then after determining that the target shooting behavior exists, the method further includes: determining the duration from the start time of the target shooting behavior to the current time, and if it is determined that the duration exceeds the time threshold, issuing a violation alarm for the target shooting behavior.

[0016] In some of the embodiments, after respectively determining the first 3D bounding box of the image acquisition device and the second 3D bounding box of the target display device, the method further includes: determining whether the first 3D bounding box is in a preset violation area in the image sequence; if it is determined that the first 3D bounding box is in the preset violation area in the image sequence, determining a first plane in the first 3D bounding box corresponding to a display screen of the image acquisition device, and determining a second plane in the second 3D bounding box corresponding to a display screen of the target display device.

[0017] According to a second aspect, a shooting behavior detection device is provided in the present embodiment, comprising: an acquisition module for acquiring an image sequence acquired by a monitoring device; a detection module for detecting an image acquisition device and a target display device in the image sequence, and acquiring a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device; a processing module for determining a first plane of the first 3D bounding box corresponding to a display screen of the image acquisition device, and determining a second plane of the second 3D bounding box corresponding to a display screen of the target display device; and a determination module for determining whether there is a target shooting behavior based on a positional relationship between the first plane and the second plane, wherein the target shooting behavior includes using the image acquisition device to shoot the display screen of the target display device.

[0018] In a third aspect, an electronic device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the shooting behavior detection method described in the first aspect when executing the computer program.

[0019] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the shooting behavior detection method described in the first aspect is implemented.

[0020] Compared with the related art, the shooting behavior detection method, device, electronic device and storage medium provided in the present embodiment obtain an image sequence captured by a monitoring device; detect the image acquisition device and the target display device in the image sequence, and respectively determine the first 3D bounding box of the image acquisition device and the second 3D bounding box of the target display device; determine the first plane of the display screen of the image acquisition device in the first 3D bounding box, and determine the second plane of the display screen of the target display device in the second 3D bounding box; based on the positional relationship between the first plane and the second plane, determine whether there is a target shooting behavior, wherein the target shooting behavior includes the behavior of shooting the display screen of the target display device using the image acquisition device, thereby solving the problem of a large number of false detections and false alarms and a low detection accuracy in the detection of customer privacy shooting in the related art, and realizing the judgment of the shooting behavior determined according to the positional relationship between the image acquisition device and the target display device.

[0021] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] Figure 1 is a hardware structure block diagram of a terminal according to a shooting behavior detection method of an embodiment of the present application;

[0024] Figure 2 is a flow chart of a shooting behavior detection method according to an embodiment of the present application;

[0025] Figure 3 is a flow chart of a shooting behavior detection method according to a preferred embodiment of the present application;

[0026] Figure 4 It is a structural block diagram of a shooting behavior detection device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0028] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0029] The various techniques described in this application can be used in various target detection and action state detection systems and devices.

[0030] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 is a hardware structure block diagram of a terminal according to the shooting behavior detection method of an embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0031] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the shooting behavior detection method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0032] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0033] In this embodiment, a shooting behavior detection method is provided. Figure 2is a flow chart of a shooting behavior detection method according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0034] Step S201, acquiring an image sequence captured by a monitoring device.

[0035] In this embodiment, the monitoring device includes but is not limited to a monitoring camera, a common camera or a smart camera.

[0036] In this embodiment, the shooting behavior detection processes whether the teller shoots the customer's private information during the service process in the counter scene. The counter scene includes the teller area and the customer area. The counter area is between the teller area and the customer area, and the target display device is placed in the counter area. The teller is located on the side of the target display device away from the customer area.

[0037] In this embodiment, the monitoring device is installed obliquely and shines from the teller area to the customer area. At least one obliquely installed monitoring device is installed in each teller area.

[0038] Step S202: Detect an image acquisition device and a target display device in an image sequence, and obtain a first three-dimensional (3D) bounding box of the image acquisition device and a second 3D bounding box of the target display device.

[0039] In this embodiment, the image acquisition device includes but is not limited to a camera, a mobile phone, a smart camera or other device with a camera function; in this embodiment, the target display device includes but is not limited to a computer with a display screen, an independent display connected to a computer, a projection device (such as a projector), etc.; at the same time, the present application can be applied not limited to scenarios for counter services, but can also be applied to other scenarios where shooting of content displayed by related devices is not allowed, such as: meetings. In this case, the target display device can be a projection or other display device, and shooting of content displayed by the projection or other display devices is also not allowed.

[0040] The 3D bounding box can represent the posture of an object, that is, the spatial position XYZ of the object in the 3D space, and the rotation angle of the object around the X-axis, Y-axis and Z-axis of the 3D space coordinate system; by determining the six degrees of freedom of the object in the corresponding 3D space, the corresponding posture of the object can be determined. In this embodiment, the 3D space coordinate system corresponds to the coordinate system of the image sequence scene, for example: the coordinate system of the image sequence formed by the surveillance camera.

[0041] In this embodiment, the 3D bounding box is the 3D projection coordinates of the target object corresponding to the monitoring camera coordinate system, including the center point coordinates and 8 corner point coordinates, wherein the center point coordinates and the 8 angle coordinates determine the six degrees of freedom of the target object in the monitoring camera coordinate system and determine the corresponding posture of the target object. The 3D coordinate parameters corresponding to the 3D bounding box in this embodiment can also be converted into the world coordinate system for subsequent position calculation processing.

[0042] In this embodiment, the image acquisition device and the target display device are detected in the image sequence by using the first 3D bounding box and the second 3D bounding box obtained by the YOLO-6D detection algorithm.

[0043] Step S203, determining a first plane in the first 3D bounding box corresponding to the display screen of the image acquisition device, and determining a second plane in the second 3D bounding box corresponding to the display screen of the target display device.

[0044] In this embodiment, the 3D bounding box corresponding to the image acquisition device and the target display device in the image sequence has six faces, so the faces corresponding to the display screens of the targets (image acquisition device and target display device) have two planes, and the positions of the image acquisition device and the target display device are determined by selecting one face from the two corresponding planes, thereby completing the inspection of the target shooting behavior. In this embodiment, the corresponding positional relationship between the image acquisition device and the target display device is determined by obtaining the planes where the image acquisition device and the target display device are located. Since the relative positional relationship between the image acquisition device and the target display device will not change due to different coordinate systems, the first plane and the second plane can directly use the planes corresponding to the display screen of the image acquisition device and the display screen of the target display device in the image sequence obtained in the coordinate system corresponding to the monitoring device, and directly calculate the positions corresponding to the image acquisition device and the target display device in the coordinate system corresponding to the monitoring device. Of course, the coordinate system corresponding to the monitoring device can also be converted into a world coordinate system, and then the spatial position information corresponding to the first plane and the second plane is converted into spatial position information under the world coordinate system, and the positional relationship corresponding to the image acquisition device and the target display device is calculated.

[0045] Step S204, based on the positional relationship between the first plane and the second plane, determining whether there is a target shooting behavior, wherein the target shooting behavior includes using an image acquisition device to shoot a display screen of a target display device.

[0046] In this embodiment, after obtaining the first plane and the second plane, it is necessary to determine the relative positions of the first plane and the second plane. When the positional relationship between the first plane and the second plane meets the positional relationship corresponding to the preset violation condition, it indicates that target shooting behavior exists.

[0047] In this embodiment, the positional relationship between the first plane and the second plane is characterized by the angle between the first plane and the second plane. At the same time, in this embodiment, by determining the precise positional relationship between the image acquisition device and the target display device, it is determined whether there is a shooting behavior, thereby reducing false alarms and false detections in the shooting behavior detection process.

[0048] In this embodiment, by judging whether the first plane and the second plane are parallel, it is determined whether the image acquisition device and the target display device are in a parallel state. When the image acquisition device and the target display device are in a parallel state, it indicates that the image acquisition device is in a position directly opposite to the display screen of the target display device, thereby indicating that shooting has occurred.

[0049] It should be noted that when the image acquisition device and the target display device are in a parallel state, but the image acquisition device or the target display device is not in use, at this time, although no actual target shooting behavior has occurred, the shooting conditions have been established for the shooting behavior. By recognizing that shooting behavior exists in this state, the risk of leakage of customer privacy information is reduced.

[0050] Through the above steps S201 to S204, by acquiring an image sequence acquired by a monitoring device; detecting the image acquisition device and the target display device in the image sequence, and respectively determining a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device; determining a first plane of the display screen of the image acquisition device in the first 3D bounding box, and determining a second plane of the display screen of the target display device in the second 3D bounding box; based on the positional relationship between the first plane and the second plane, determining whether there is a target shooting behavior, the problem of a large number of false detections and false alarms and a low detection accuracy in the related art for customer privacy shooting is solved, and the image acquisition device and the target display device are detected based on a 3D target detection algorithm, the positional relationship between the image acquisition device and the target display device is accurately determined, and the accuracy of shooting behavior detection is improved.

[0051] In some of the embodiments, based on the positional relationship between the first plane and the second plane, determining whether there is a target shooting behavior is achieved by the following steps:

[0052] Step 1: Determine the angle between the first plane and the second plane.

[0053] In this embodiment, the positional relationship between the first plane and the second plane is determined based on the angle between the two planes.

[0054] Step 2: If it is determined that the angle is less than a preset angle threshold, it is determined that there is a target shooting behavior.

[0055] In this embodiment, by judging whether the angle between the first plane and the second plane is less than a preset angle threshold, it is judged whether the first plane and the second plane are parallel, thereby determining whether the image acquisition device and the target display device are in a parallel state. When the image acquisition device and the target display device are in a parallel state, it indicates that the image acquisition device is in a position directly opposite to the display screen of the target display device, thereby indicating that target shooting behavior has occurred.

[0056] By determining the angle between the first plane and the second plane in the above steps, if it is determined that the angle is less than the preset angle threshold, it is determined that there is target shooting behavior, thereby realizing the positional relationship between the first plane and the second plane based on the angle, so as to judge whether there is shooting of the display screen of the target display device by using the image acquisition device.

[0057] In some of the embodiments, before determining the angle between the first plane and the second plane, the following steps are further performed:

[0058] Step 1: Based on the first 3D bounding box, determine whether the display screen of the image acquisition device is in use.

[0059] Step 2: Based on the second 3D bounding box, determine whether the display screen of the target display device is in use.

[0060] In this embodiment, by determining whether the image acquisition device and the target display device are in use, it is determined whether the conditions for illegally photographing the display screen of the target display device are met; in this embodiment, if the display screen of the image acquisition device is in use, it means that the device for photographing the display screen of the target display device is running, and if the display screen of the target display device is in use, it means that corresponding information, for example, customer privacy information is displayed. By determining that both the image acquisition device and the target display device are in use, and then checking the positional relationship between the first plane and the second plane, the accuracy of the detected target shooting behavior is ensured.

[0061] In this embodiment, when it is detected that the display screen of the image acquisition device and the display screen of the target display device are both in use, it is detected whether the angle between the first plane and the second plane is less than a preset angle threshold; when it is detected that the angle between the first plane and the second plane is less than the preset angle threshold, it means that the first plane is parallel to the second plane, which means that the image acquisition device is facing the target display device. At the same time, it is detected that both the image acquisition device and the target display device are in use, which means that an image acquisition device is running at a position facing the display screen of the target display device. In this way, it is determined that there is a shooting behavior.

[0062] In the above steps, based on the first 3D bounding box, it is determined that the display screen of the image acquisition device is in use; based on the second 3D bounding box, it is determined that the display screen of the target display device is in use. By adding judgment conditions for judging the shooting behavior, the accuracy of judging the shooting behavior is improved.

[0063] In some of the embodiments, based on the first 3D bounding box, determining that the display screen of the image acquisition device is in use is achieved by the following steps: determining that a mean value of pixels corresponding to the first 3D bounding box is greater than a first pixel threshold;

[0064] Based on the second 3D bounding box, determining that the display screen of the target display device is in use is achieved by the following steps: determining that the average value of pixels corresponding to the second 3D bounding box is greater than a second pixel threshold.

[0065] In this embodiment, the following steps are further implemented to detect whether the display screen of the image acquisition device and the display screen of the target display device are in use:

[0066] Step 1: Detect the mean values ​​of the pixels corresponding to the first 3D bounding box and the second 3D bounding box respectively.

[0067] In this embodiment, when detecting the mean value of corresponding pixels, the mean value of pixels of the first 3D bounding box corresponding to the first plane and the mean value of pixels of the second 3D bounding box corresponding to the second plane are detected; at the same time, since other surfaces of the first 3D bounding box and the second 3D bounding box also have certain pixels, the corresponding usage (lighting) status of the display screen of the image acquisition device and the display screen of the target display device is determined by respectively detecting the overall pixels of the first 3D bounding box and the second 3D bounding box.

[0068] Step 2: Determine whether the mean value of pixels corresponding to the first 3D bounding box is greater than a first pixel threshold, and determine whether the mean value of pixels corresponding to the second 3D bounding box is greater than a second pixel threshold.

[0069] Step 3: If it is determined that the mean value of the pixels corresponding to the first 3D bounding box is greater than the first pixel threshold, it is determined that the display screen of the image acquisition device is in use; and if it is determined that the mean value of the pixels corresponding to the second 3D bounding box is greater than the second pixel threshold, it is determined that the display screen of the target display device is in use.

[0070] In this embodiment, when it is determined that both the image acquisition device and the target display device are not in use, it means that the conditions for photographing the display screen of the target display device are not met, that is, the image acquisition device is not running and the corresponding information is not displayed on the display screen of the target display device, for example: customer privacy information.

[0071] By respectively detecting the mean values ​​of the pixels corresponding to the first 3D bounding box and the second 3D bounding box in the above steps; judging whether the mean value of the pixels corresponding to the first 3D bounding box is greater than the first pixel threshold, and judging whether the mean value of the pixels corresponding to the second 3D bounding box is greater than the second pixel threshold; if it is judged that the mean value of the pixels corresponding to the first 3D bounding box is greater than the first pixel threshold, determining that the display screen of the image acquisition device is in use, and if it is judged that the mean value of the pixels corresponding to the second 3D bounding box is greater than the second pixel threshold, determining that the display screen of the target display device is in use, it is achieved that the operating state of the display screen of the corresponding device is judged according to the mean value of the pixels, and by judging the use state of the image acquisition device and the target display device, the accuracy of shooting behavior detection is improved.

[0072] In some of the embodiments, after acquiring the image sequence collected by the monitoring device, the following steps are further performed:

[0073] Step 1: Determine a first image frame corresponding to a preset target area from an image sequence, wherein the preset target area is used to represent an area where a target person is located in the image sequence.

[0074] In this embodiment, the target person represents at least one teller appearing in the teller area; by detecting whether there is a person target in the preset target area, when the presence of a person target is detected, it represents the person target, that is, the at least one teller, and the person target is a candidate target person who may operate the image acquisition device to perform shooting behavior.

[0075] Step 2: Detect hand feature points corresponding to the target person from the first image frame.

[0076] In this embodiment, detecting hand feature points corresponding to the target person from the first image frame is to detect multiple hand feature points of the target person; detecting the person target in the image by the YOLOV4 target detection algorithm, and obtaining the human body detection frame corresponding to the person target (corresponding to a 3D bounding box), so as to determine whether there is a teller; in this embodiment, there may be one or more tellers, as long as one target person is determined, and then the hand feature points are detected to detect whether the teller is associated with the image acquisition device. In this application, the teller is associated with the image acquisition device, which means that the teller contacts and operates the image acquisition device.

[0077] In this embodiment, after obtaining the human body detection frame, hand key point detection is performed in the human body detection frame. When the number of hand key points detected in the human body detection frame exceeds a preset threshold, it indicates that the corresponding teller's hand is in the position to operate the image acquisition device.

[0078] Step 3: If the number of hand feature points determined to be within the first 3D bounding box is greater than a preset threshold, an image acquisition device and a target display device are detected in the image sequence.

[0079] In this embodiment, when it is determined that the number of hand feature points within the first 3D bounding box is greater than a preset threshold value, it indicates that the hand of the corresponding target person is associated with the image acquisition device, that is, the image acquisition device is operated; at this time, the positions of the image acquisition device and the target display device are determined by detecting the image acquisition device and the target display device in the image sequence, and then the shooting behavior is accurately judged.

[0080] Step 4: Obtain a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device.

[0081] Step 5: Determine a first plane in the first 3D bounding box that corresponds to the display screen of the image acquisition device, and determine a second plane in the second 3D bounding box that corresponds to the display screen of the target display device.

[0082] Step 6: Determine whether there is a target shooting behavior based on the positional relationship between the first plane and the second plane.

[0083] Through the above steps, a first image frame corresponding to a preset target area is determined from the image sequence, wherein the preset target area is used to characterize the area where the target person in the image sequence is located; hand feature points corresponding to the target person are detected from the first image frame; if the number of hand feature points determined to be in the first 3D bounding box is greater than a preset number threshold, an image acquisition device and a target display device are detected in the image sequence; the first 3D bounding box of the image acquisition device and the second 3D bounding box of the target display device are obtained; a first plane corresponding to the display screen of the image acquisition device in the first 3D bounding box is determined, and a second plane corresponding to the display screen of the target display device in the second 3D bounding box is determined; based on the positional relationship between the first plane and the second plane, it is determined whether there is a target shooting behavior, thereby realizing the determination of whether there is a target shooting behavior based on whether the hand of the target person is in the first 3D bounding box and the positional relationship between the first plane and the second plane, thereby improving the accuracy of shooting behavior detection; at the same time, the combination of key point detection and 3D target detection technology realizes the detection of shooting behavior, thereby improving the robustness of the algorithm and the accuracy of detection.

[0084] In some of the embodiments, detecting a plurality of hand feature points corresponding to the target person in the first image frame is implemented in the following manner: using a preset target detector to detect a plurality of hand feature points corresponding to the target person in the first image frame.

[0085] In this embodiment, after obtaining a first 3D bounding box corresponding to at least one target person, a hand bounding box corresponding to the human hand is detected in the first 3D bounding box, and then the hand bounding box is input into the key point detector to detect 21 hand key points corresponding to the hand. If more than one-third of the hand key points are in the first 3D bounding box, it is determined that the corresponding target person is associated with the image acquisition device, that is, is in contact with or operates the image acquisition device.

[0086] By using the preset target detector in the above steps to detect multiple hand feature points corresponding to the target person in the first image frame, it is possible to determine whether the hand of the target person is associated with the image acquisition device.

[0087] In some of the embodiments, after determining the first image frame corresponding to the preset target area from the image sequence, the following steps are further performed:

[0088] Step 1: Perform human target detection in the first image frame using a target detection algorithm to generate target detection information.

[0089] In this embodiment, human target detection is performed using the YOLOV4 target detection algorithm to obtain a human target frame.

[0090] Step 2: If it is determined that the target detection information includes a human target frame, it is determined that the target person is detected from the first image frame, wherein the human target frame is used to mark the target person.

[0091] In this embodiment, it is determined whether a human target frame is detected, thereby determining whether a human target operating the image acquisition device is detected.

[0092] Through the target detection algorithm in the above steps, human target detection is performed in the first image frame to generate target detection information; if it is determined that the target detection information includes a human target frame, it is determined that the target person is detected from the first image frame, wherein the human target frame is used to mark the target person to achieve human target detection.

[0093] In some embodiments, determining the angle between the first plane and the second plane is achieved by the following steps:

[0094] Step 1: Determine a first normal vector of a first plane in a preset direction, and determine a second normal vector corresponding to a second plane in the preset direction.

[0095] Step 2: Determine the angle between the first normal vector and the second normal vector as the angle between the first plane and the second plane.

[0096] In this embodiment, the angle between the first plane and the second plane is calculated by using the normal vectors corresponding to the first plane and the second plane at the coordinates corresponding to the monitoring device, and whether the first plane and the second plane are parallel is determined by the angle.

[0097] In this embodiment, the first normal vector and the second normal vector correspond to normal vectors of the first plane and the second plane in corresponding directions, respectively, wherein the moduli of the first normal vector and the second normal vector may be equal, for example, both are unit normal vectors, or may be unequal.

[0098] By determining a first normal vector of the first plane in a preset direction and determining a second normal vector corresponding to the second plane in the preset direction in the above steps; determining the angle between the first normal vector and the second normal vector as the angle between the first plane and the second plane, the position angle between the first plane and the second plane in the corresponding coordinate system of the monitoring device is determined.

[0099] In some of the embodiments, after the first plane and the second plane are determined, the following steps are further performed:

[0100] Step 1: Use a preset 3D object detection algorithm to detect the first 3D projection coordinates corresponding to the first plane in the monitoring device coordinate system, and detect the second 3D projection coordinates corresponding to the second plane in the monitoring device coordinate system.

[0101] In this embodiment, the YOLO-6D detection algorithm is used to detect the 3D projection coordinates corresponding to the image acquisition device and the target display device, wherein the 3D projection coordinates include the center point coordinates and 8 corner point coordinates.

[0102] Step 2: Process the first 3D projection coordinates and the second 3D projection coordinates respectively through a preset posture estimation algorithm to obtain first 3D spatial position information and second 3D spatial position information respectively, wherein the first 3D spatial position information represents the coordinate information of the first plane in the world coordinate system, and the second 3D spatial position information represents the coordinate information of the second plane in the world coordinate system.

[0103] In this embodiment, a PnP algorithm is used to obtain a 3D rotation matrix and a 3D translation vector, and the first 3D spatial position information and the second 3D spatial position information corresponding to the image acquisition device and the target display device are calculated based on the 3D rotation matrix and the 3D translation vector.

[0104] Step 3: Determine the distance between the first plane and the second plane according to the first 3D spatial position information and the second 3D spatial position information.

[0105] In this embodiment, the distance between the first plane and the second plane is judged to verify whether the shooting behavior can be judged based on the distance.

[0106] Step 4: If the distance is determined to be less than a preset distance threshold, determine the angle between the first plane and the second plane.

[0107] In this embodiment, when it is determined that the distance between the first plane and the second plane is less than a preset distance threshold, a determination is made as to whether the first plane and the second plane are parallel, thereby improving the accuracy of detection.

[0108] It should be noted that the location of the image acquisition device that constitutes illegal shooting behavior can be determined by judging the distance between the first plane and the second plane.

[0109] By using the preset 3D target detection algorithm in the above steps to detect the first 3D projection coordinates corresponding to the first plane in the monitoring device coordinate system, and detecting the second 3D projection coordinates corresponding to the second plane in the monitoring device coordinate system; processing the first 3D projection coordinates and the second 3D projection coordinates respectively by the preset posture estimation algorithm to obtain the first 3D spatial position information and the second 3D spatial position information respectively; determining the distance between the first plane and the second plane according to the first 3D spatial position information and the second 3D spatial position information; if the determined distance is less than the preset distance threshold, determining the angle between the first plane and the second plane, thereby realizing the judgment of whether there is a shooting behavior by judging whether the first plane and the second plane are parallel in the world coordinate system.

[0110] In some of the embodiments, if it is determined that the angle is less than a preset angle threshold, determining that there is a target shooting behavior is achieved by the following steps:

[0111] Step 1: Determine a third normal vector corresponding to the first plane according to the first 3D space position information, and determine a fourth normal vector corresponding to the second plane according to the second 3D space position information.

[0112] Step 2: determine the angle between the third normal vector and the fourth normal vector to obtain a second angle. If the second angle is less than a preset angle threshold, it is determined that there is a target shooting behavior.

[0113] In this embodiment, the angle between the first plane and the second plane in the world coordinate system is determined.

[0114] In some of the embodiments, if it is determined that the angle is less than the preset angle threshold, then after it is determined that there is a target shooting behavior, the following steps are further implemented:

[0115] Step 1: Determine the duration from the start time of the target shooting behavior to the current time.

[0116] Step 2: If it is determined that the duration exceeds the time threshold, a violation alarm is issued for the target shooting behavior.

[0117] In this embodiment, when it is determined that the duration exceeds the time threshold, the illegal shooting behavior is displayed and reported, and then a violation alarm is issued.

[0118] In this embodiment, by setting a check on the time when the shooting behavior of the image acquisition device occurs, it is determined whether the corresponding shooting behavior violates the regulations based on the duration of the shooting behavior.

[0119] In some of the embodiments, after respectively determining the first 3D bounding box of the image acquisition device and the second 3D bounding box of the target display device, the following steps are further performed:

[0120] Step 1: Determine whether the first 3D bounding box is in a preset violation area in the image sequence.

[0121] Step 2: If it is determined that the first 3D bounding box is in a preset violation area in the image sequence, determine a first plane in the first 3D bounding box corresponding to the display screen of the image acquisition device, and determine a second plane in the second 3D bounding box corresponding to the display screen of the target display device.

[0122] In this embodiment, by setting whether the image acquisition device is located in the violation area, it is determined whether the corresponding shooting behavior is in violation based on whether the image acquisition device is in the violation area.

[0123] This embodiment also provides a shooting behavior detection method. Figure 3 is a flow chart of a shooting behavior detection method according to a preferred embodiment of the present application. Figure 3 As shown, the process includes the following steps:

[0124] Step S301, using a 3D target detection algorithm to detect an image acquisition device and a target display device, and then executing step S302.

[0125] Step S302, generating 3D spatial position information corresponding to the image acquisition device and the target display device, and then executing step S303.

[0126] Step S303, determine the third normal vector corresponding to the image acquisition device and the fourth normal vector corresponding to the target display device, and determine whether the angle between the third normal vector and the fourth normal vector is less than a threshold, then execute step S307.

[0127] Step S304: human target detection.

[0128] In this embodiment, steps S304 to S305 and steps S301 to S303 belong to two parallel logic execution processes, and therefore, there is no order of precedence for the two parallel logic execution processes.

[0129] Step S305: hand feature point detection, then execute step S306.

[0130] Step S306: determine whether the hand feature points are associated with the image acquisition device, and then execute step S307.

[0131] Step S307: Violation detection logic judgment.

[0132] Step S308: Output a violation alarm.

[0133] In this embodiment, a shooting behavior detection device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware of predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0134] Figure 4 is a structural block diagram of a shooting behavior detection device according to an embodiment of the present application, such as Figure 4 As shown, the device comprises:

[0135] An acquisition module 41 is used to acquire an image sequence collected by a monitoring device;

[0136] A detection module 42, coupled to the acquisition module 41, is used to detect the image acquisition device and the target display device in the image sequence, and respectively determine a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device;

[0137] The processing module 43 is coupled to the detection module 42 and configured to determine a first plane in the first 3D bounding box corresponding to the display screen of the image acquisition device, and determine a second plane in the second 3D bounding box corresponding to the display screen of the target display device;

[0138] The determination module 44 is coupled to the processing module 43 and is used to determine whether there is a target shooting behavior based on the positional relationship between the first plane and the second plane, wherein the target shooting behavior includes using an image acquisition device to shoot the display screen of the target display device.

[0139] In some of the embodiments, the determination module 44 is used to determine the angle between the first plane and the second plane; if the determined angle is less than a preset angle threshold, it is determined that the target shooting behavior exists.

[0140] In some of the embodiments, the apparatus is further configured to determine, based on the first 3D bounding box, that a display screen of the image acquisition device is in use; and based on the second 3D bounding box, determine that a display screen of the target display device is in use.

[0141] In some of the embodiments, the device is also used to respectively detect whether the display screen of the image acquisition device and the display screen of the target display device are in use; when it is detected that the display screen of the image acquisition device and the display screen of the target display device are both in use, detect whether the angle between the first plane and the second plane is less than a preset angle threshold.

[0142] In some of the embodiments, the apparatus is further configured to determine that an average value of pixels corresponding to the first 3D bounding box is greater than a first pixel threshold; and determine that an average value of pixels corresponding to the second 3D bounding box is greater than a second pixel threshold.

[0143] In some of the embodiments, the device is also used to detect the mean values ​​of pixels corresponding to the first 3D bounding box and the second 3D bounding box, respectively; determine whether the mean value of pixels corresponding to the first 3D bounding box is greater than a first pixel threshold, and determine whether the mean value of pixels corresponding to the second 3D bounding box is greater than a second pixel threshold; if it is determined that the mean value of pixels corresponding to the first 3D bounding box is greater than the first pixel threshold, it is determined that the display screen of the image acquisition device is in use, and if it is determined that the mean value of pixels corresponding to the second 3D bounding box is greater than the second pixel threshold, it is determined that the display screen of the target display device is in use.

[0144] In some of the embodiments, after acquiring an image sequence captured by a monitoring device, the apparatus is further used to segment a first image frame corresponding to a preset target area from the image sequence, wherein the preset target area is used to characterize an area where a target person in the image sequence is located; detect hand feature points corresponding to the target person from the first image frame; and detect an image acquisition device and a target display device in the image sequence if the number of hand feature points determined to be within a first 3D bounding box is greater than a preset number threshold.

[0145] In some of the embodiments, the device is further configured to detect hand feature points corresponding to the target person in the first image frame using a preset target detector.

[0146] In some of the embodiments, the device is also used to determine, from the image sequence, a first image frame corresponding to a preset target area, and then perform human target detection in the first image frame through a target detection algorithm to generate target detection information; if it is determined that the target detection information includes a human target frame, it is determined that the target person is detected from the first image frame, wherein the human target frame is used to mark the target person.

[0147] In some of the embodiments, the determination module 44 is also used to determine a first normal vector of the first plane in a preset direction, and to determine a second normal vector corresponding to the second plane in the preset direction; and to determine the angle between the first normal vector and the second normal vector as the angle between the first plane and the second plane.

[0148] In some of the embodiments, the device is also used to detect the first 3D projection coordinates corresponding to the first plane in the monitoring device coordinate system using a preset 3D target detection algorithm, and to detect the second 3D projection coordinates corresponding to the second plane in the monitoring device coordinate system; the first 3D projection coordinates and the second 3D projection coordinates are processed respectively by a preset posture estimation algorithm to obtain first 3D spatial position information and second 3D spatial position information respectively, wherein the first 3D spatial position information represents the coordinate information of the first plane in the world coordinate system, and the second 3D spatial position information represents the coordinate information of the second plane in the world coordinate system; the distance between the first plane and the second plane is determined according to the first 3D spatial position information and the second 3D spatial position information; if the determined distance is less than a preset distance threshold, the angle between the first plane and the second plane is determined.

[0149] In some of the embodiments, the determination module 44 is used to determine a third normal vector corresponding to the first plane based on the first 3D spatial position information, and to determine a fourth normal vector corresponding to the second plane based on the second 3D spatial position information; determine the angle between the third normal vector and the fourth normal vector to obtain a second angle, and if the second angle is less than a preset angle threshold, it is determined that target shooting behavior exists.

[0150] In some of the embodiments, if it is determined that the angle is less than a preset angle threshold, then it is determined that there is a target shooting behavior, and the device is also used to determine the duration from the start time of the target shooting behavior to the current time; if it is determined that the duration exceeds the time threshold, an illegal alarm is issued for the target shooting behavior.

[0151] In some of the embodiments, after respectively determining a first 3D bounding box of an image acquisition device and a second 3D bounding box of a target display device, the apparatus is further configured to determine whether the first 3D bounding box is located in a preset violation area in an image sequence; if it is determined that the first 3D bounding box is located in a preset violation area in an image sequence, then determining a first plane in the first 3D bounding box corresponding to a display screen of the image acquisition device, and determining a second plane in the second 3D bounding box corresponding to a display screen of the target display device.

[0152] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0153] In this embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0154] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0155] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0156] S1, obtaining an image sequence collected by a monitoring device.

[0157] S2, detecting an image acquisition device and a target display device in an image sequence, and determining a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device respectively.

[0158] S3, determining a first plane in the first 3D bounding box corresponding to the display screen of the image acquisition device, and determining a second plane in the second 3D bounding box corresponding to the display screen of the target display device.

[0159] S4. Determine whether there is a target shooting behavior based on the positional relationship between the first plane and the second plane.

[0160] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0161] In addition, in combination with the shooting behavior detection method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the shooting behavior detection method. The storage medium stores a computer program; when the computer program is executed by a processor, any shooting behavior detection method in the above embodiments is implemented.

[0162] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0163] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0164] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0165] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A shooting behavior detection method, characterized in that: include: Acquire an image sequence collected by a monitoring device; Detecting an image acquisition device and a target display device in the image sequence, and determining a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device, respectively; determining a first plane corresponding to a display screen of the image acquisition device in the first 3D bounding box, and determining a second plane corresponding to a display screen of the target display device in the second 3D bounding box; Based on the positional relationship between the first plane and the second plane, determining whether there is a target shooting behavior, wherein the target shooting behavior includes using the image acquisition device to shoot a display screen of the target display device; Determining whether there is a target shooting behavior based on a positional relationship between the first plane and the second plane includes: determining an angle between the first plane and the second plane; If it is determined that the angle is less than a preset angle threshold, it is determined that the target shooting behavior exists.

2. The method according to claim 1, characterized in that Before determining the angle between the first plane and the second plane, the method further includes: Based on the first 3D bounding box, determining that the display screen of the image acquisition device is in use; Based on the second 3D bounding box, it is determined that the display screen of the target display device is in use.

3. The method according to claim 2, characterized in that The determining, based on the first 3D bounding box, that the display screen of the image acquisition device is in use includes: Determining that a mean value of pixels corresponding to the first 3D bounding box is greater than a first pixel threshold; The determining, based on the second 3D bounding box, that the display screen of the target display device is in use includes: It is determined that a mean value of pixels corresponding to the second 3D bounding box is greater than a second pixel threshold.

4. The method according to any one of claims 1 to 3, characterized in that: After acquiring the image sequence collected by the monitoring device, the method further includes: Determining a first image frame corresponding to a preset target area from the image sequence, wherein the preset target area is used to represent an area where a target person in the image sequence is located; Determining hand feature points corresponding to the target person from the first image frame; If the number of the determined hand feature points that are within the first 3D bounding box is greater than a preset number threshold, an image acquisition device and a target display device are detected in the image sequence.

5. The method according to claim 4, characterized in that After determining the first image frame corresponding to the preset target area from the image sequence, the method further includes: Performing human target detection in the first image frame by using a target detection algorithm to generate target detection information; If it is determined that the target detection information includes a human target frame, it is determined that the target person is detected from the first image frame, wherein the human target frame is used to mark the target person.

6. The method according to claim 1, characterized in that The determining the angle between the first plane and the second plane includes: Determine a first normal vector of the first plane in a preset direction, and determine a second normal vector corresponding to the second plane in the preset direction; The angle between the first normal vector and the second normal vector is determined as the angle between the first plane and the second plane.

7. The method according to claim 1, characterized in that The method further comprises: Using a preset 3D object detection algorithm to detect first 3D projection coordinates corresponding to the first plane in the monitoring device coordinate system, and to detect second 3D projection coordinates corresponding to the second plane in the monitoring device coordinate system; The first 3D projection coordinates and the second 3D projection coordinates are processed respectively by a preset posture estimation algorithm to obtain first 3D spatial position information and second 3D spatial position information, wherein the first 3D spatial position information represents the coordinate information of the first plane in a world coordinate system, and the second 3D spatial position information represents the coordinate information of the second plane in the world coordinate system; determining a distance between the first plane and the second plane according to the first 3D spatial position information and the second 3D spatial position information; If it is determined that the distance is less than a preset distance threshold, an angle between the first plane and the second plane is determined.

8. The method according to claim 7, characterized in that If it is determined that the angle is less than the preset angle threshold, then it is determined that the target shooting behavior exists, including: determining a third normal vector corresponding to the first plane according to the first 3D spatial position information, and determining a fourth normal vector corresponding to the second plane according to the second 3D spatial position information; An angle between the third normal vector and the fourth normal vector is determined to obtain a second angle. If it is determined that the second angle is less than the preset angle threshold, it is determined that the target shooting behavior exists.

9. The method according to claim 1, characterized in that If it is determined that the angle is less than the preset angle threshold, then after determining that the target shooting behavior exists, the method further includes: Determine the duration from the start time of the target shooting behavior to the current time; If it is determined that the duration exceeds the time threshold, a violation alarm is issued for the target shooting behavior.

10. The method according to claim 1, characterized in that After respectively determining the first 3D bounding box of the image acquisition device and the second 3D bounding box of the target display device, the method further includes: determining whether the first 3D bounding box is in a preset violation area in the image sequence; If it is determined that the first 3D bounding box is in a preset violation area in the image sequence, a first plane in the first 3D bounding box corresponding to a display screen of the image acquisition device is determined, and a second plane in the second 3D bounding box corresponding to a display screen of the target display device is determined.

11. A shooting behavior detection device, characterized in that: include: An acquisition module, used to acquire an image sequence collected by a monitoring device; A detection module, configured to detect an image acquisition device and a target display device in the image sequence, and to determine a first 3D bounding box of the image acquisition device and a second 3D bounding box of the target display device, respectively; a processing module, configured to determine a first plane in the first 3D bounding box corresponding to a display screen of the image acquisition device, and to determine a second plane in the second 3D bounding box corresponding to a display screen of the target display device; A determination module is used to determine whether there is a target shooting behavior based on the positional relationship between the first plane and the second plane, wherein the target shooting behavior includes using the image acquisition device to shoot the display screen of the target display device; specifically, determine the angle between the first plane and the second plane; if it is determined that the angle is less than a preset angle threshold, it is determined that the target shooting behavior exists.

12. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the shooting behavior detection method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the shooting behavior detection method according to any one of claims 1 to 10 are implemented.

Images