Startup and control ball position identification method and device, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention provides a deploy and control ball position identification method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of computers. According to the method, a monitoring image shot by the monitoring ball is analyzed, a body area of a monitored object is accurately positioned, an upper body area and a lower body area are divided, the compliance of the placement position of the monitoring ball is deduced according to the relative positions of the upper body area and the lower body area in the monitoring image, and intelligent identification of the installation state of the monitoring ball is achieved. Therefore, reliable intelligent support is provided for safety monitoring, manual intervention is reduced, and the method has the remarkable advantages of high monitoring precision, high robustness and low cost and has a wider application prospect.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method, device, electronic device and computer-readable storage medium for identifying the position of a bullet-proof camera ball. Background Art

[0002] As an intelligent monitoring device, the bullet-proof camera ball is widely used in fields such as construction and traffic management to ensure the safety of workers and compliance with construction regulations. However, due to the complex construction site environment, possible negligence of operators or equipment limitations, the bullet-proof camera ball is often placed illegally at a position lower than the standard height or at a non-designated position, resulting in problems such as monitoring blind spots, reduced effectiveness, increased risk of equipment damage, and safety hazards. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method, device, electronic device and computer-readable storage medium for identifying the position of a bullet-proof camera ball, which can improve the efficiency and accuracy of identifying the position of the bullet-proof camera ball.

[0004] To achieve the above purpose, the technical solutions adopted in the embodiments of the present invention are as follows:

[0005] In a first aspect, the present invention provides a method for identifying the position of a bullet-proof camera ball, the method comprising:

[0006] Identifying an upper body bounding box and a lower body bounding box of a monitoring object according to a monitoring image captured by the bullet-proof camera ball;

[0007] Judging whether the position of the bullet-proof camera ball is illegal according to the positions of the upper body bounding box and the lower body bounding box in the monitoring image.

[0008] In an alternative embodiment, the identifying an upper body bounding box and a lower body bounding box of a monitoring object according to a monitoring image captured by the bullet-proof camera ball comprises:

[0009] Performing object detection on the monitoring object according to the monitoring image to obtain a person bounding box;

[0010] Performing key point detection according to the person bounding box to obtain the upper body bounding box and the lower body bounding box; the upper body bounding box is determined by head key points, shoulder key points and hip key points; the lower body bounding box is determined by hip key points and ankle key points.

[0011] In an alternative embodiment, the judging whether the position of the bullet-proof camera ball is illegal according to the positions of the upper body bounding box and the lower body bounding box in the monitoring image comprises:

[0012] Determining whether the upper body constraint frame is valid according to the confidence of the head key point, the confidence of the shoulder key point, the confidence of the hip key point, the head ordinate and the abdomen ordinate;

[0013] If the upper body constraint frame is invalid, the position of the control ball is determined to be illegal;

[0014] If the upper body constraint frame is valid, it is determined whether the position of the control ball is in violation of the rules according to the bottom frame of the upper body constraint frame, the bottom frame of the lower body constraint frame and the bottom of the monitoring image.

[0015] In an optional implementation, judging whether the upper body constraint frame is valid according to the confidence of the head key point, the confidence of the shoulder key point, the confidence of the hip key point, the head ordinate and the abdomen ordinate includes:

[0016] Determine the head ordinate according to the ordinates of the nose key point, the left ear key point and the right ear key point among the head key points;

[0017] Determine the abdominal ordinate according to the ordinates of the left hip key point and the right hip key point among the hip key points;

[0018] If the confidence of the head key point, the confidence of the shoulder key point, and the confidence of the hip key point are all greater than the confidence threshold, and the head ordinate is less than the abdomen ordinate, it is determined that the upper body constraint frame is valid;

[0019] If the confidence of the head key point, the confidence of the shoulder key point or the confidence of the hip key point is not greater than the confidence threshold, or the head ordinate is not less than the abdomen ordinate, the upper body constraint frame is determined to be invalid.

[0020] In an optional implementation, judging whether the position of the control ball is in violation of the rules according to the bottom frame of the upper body constraint frame, the bottom frame of the lower body constraint frame and the bottom of the monitoring image includes:

[0021] Determining whether the lower body constraint frame is valid according to the confidence of the hip key point and the confidence of the ankle key point;

[0022] If the lower body constraint frame is invalid, the position of the control ball is determined to be illegal;

[0023] If the lower body constraint frame is valid, determining whether a ratio of a distance between a bottom frame of the lower body constraint frame and a bottom of the monitoring image to a height of the monitoring image is less than a first threshold;

[0024] If it is less than the first threshold, it is determined that the position of the control ball is compliant;

[0025] If it is not less than the first threshold, determining whether the ratio of the distance between the bottom frame of the upper body constraint frame and the bottom of the monitoring image to the height of the monitoring image is less than a second threshold; the second threshold is greater than the first threshold;

[0026] If it is not less than the second threshold, it is determined that the position of the control ball is illegal;

[0027] If it is less than the second threshold, it is determined that the position of the control ball is compliant.

[0028] In an optional implementation, before identifying the upper body constraint frame and the lower body constraint frame of the monitored object according to the monitoring image taken by the surveillance ball, the method further includes:

[0029] According to the field of view of the control ball, the compliance height of the control ball, the abdomen height of the observed object, and multiple monitoring distances between the control ball and the observed object, a first abdomen proportion and a first ankle proportion corresponding to each of the monitoring distances are obtained;

[0030] According to the field of view of the control ball, the violation height of the control ball, the abdomen height of the observed object, and multiple monitoring distances between the control ball and the observed object, a second abdomen proportion and a second ankle proportion corresponding to each of the monitoring distances are obtained;

[0031] generating a first abdomen curve according to all the first abdomen proportions, and generating a first ankle curve according to all the first ankle proportions;

[0032] generating a second abdomen curve according to all of the second abdomen proportions, and generating a second ankle curve according to all of the second ankle proportions;

[0033] The first threshold and the second threshold are determined according to the first abdomen curve, the first ankle curve, the second abdomen curve, and the second ankle curve.

[0034] In an optional embodiment, determining the first threshold and the second threshold according to the first abdomen curve, the first ankle curve, the second abdomen curve, and the second ankle curve includes:

[0035] Determine a monitoring distance of a preset abdomen proportion in the second abdomen curve as a critical distance;

[0036] determining the first threshold value according to the first ankle curve, the second ankle curve and the critical distance;

[0037] The abdomen proportion corresponding to the first intersection point of the stable interval of the first abdomen curve and the stable interval of the second abdomen curve is determined as the second threshold.

[0038] In a second aspect, the present invention provides a device for identifying the position of a control ball, the device comprising:

[0039] A processing module, used for identifying an upper body constraint frame and a lower body constraint frame of a monitored object according to a monitoring image taken by a surveillance ball;

[0040] A determination module is used to determine whether the position of the control ball is in violation of the rules according to the positions of the upper body constraint frame and the lower body constraint frame in the monitoring image.

[0041] In a third aspect, the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the method for identifying the position of a controlled ball as described in any of the aforementioned embodiments.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for identifying the position of a controlled ball as described in any one of the aforementioned embodiments is implemented.

[0043] Compared with the prior art, the control ball position identification method, device, electronic device and computer-readable storage medium provided in the embodiments of the present invention analyze the monitoring image taken by the control ball, accurately locate the body area of the monitored object, divide it into the upper body area and the lower body area, and infer the compliance of the control ball placement position through the relative positions of the upper body area and the lower body area in the monitoring image, thereby realizing intelligent identification of the installation status of the control ball, thereby providing reliable intelligent support for security monitoring, reducing manual intervention, and having the significant advantages of high monitoring accuracy, strong robustness and low cost, and having broader application prospects.

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 A schematic flow chart of a method for identifying the position of a control ball provided in an embodiment of the present invention is shown.

[0047] Figure 2Shows another schematic flowchart of the method for identifying the position of the mobile surveillance camera provided by the embodiment of the present invention.

[0048] Figure 3 Shows another schematic flowchart of the method for identifying the position of the mobile surveillance camera provided by the embodiment of the present invention.

[0049] Figure 4 Shows an application schematic diagram of the mobile surveillance camera in a compliant position provided by the embodiment of the present invention.

[0050] Figure 5 Shows an application schematic diagram of the mobile surveillance camera in a non-compliant position provided by the embodiment of the present invention.

[0051] Figure 6 Shows the abdominal curve graph and ankle curve graph observed by the mobile surveillance camera in a compliant position provided by the embodiment of the present invention.

[0052] Figure 7 Shows the abdominal curve graph and ankle curve graph observed by the mobile surveillance camera in a non-compliant position provided by the embodiment of the present invention.

[0053] Figure 8 Shows a block schematic diagram of the device for identifying the position of the mobile surveillance camera provided by the embodiment of the present invention.

[0054] Figure 9 Shows a block schematic diagram of the electronic device provided by the embodiment of the present invention.

[0055] Icons: 300 - Device for identifying the position of the mobile surveillance camera; 301 - Processing module; 302 - Determination module; 400 - Electronic device; 410 - Memory; 420 - Processor; 430 - Communication module. Detailed implementation manners

[0056] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Usually, the components of the embodiments of the present invention described and shown in the accompanying drawings here can be arranged and designed in various different configurations.

[0057] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0058] It should be noted that relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0059] A mobile surveillance camera is an intelligent monitoring device integrating components such as a high-definition camera, an infrared sensor, a pan-tilt control system, and a communication module. It usually has the ability to provide 360-degree panoramic monitoring, and can achieve full-range and non-blind-spot coverage of the monitored area by rotating or stitching the images of multiple cameras. Mobile surveillance cameras are widely used in fields such as construction, traffic management, security monitoring, and emergency command, and are mainly used for tasks such as real-time monitoring, data collection, and safety warning.

[0060] When installing a mobile surveillance camera illegally, problems such as monitoring blind spots, increased risk of damage to the mobile surveillance camera, and increased potential safety hazards will occur. Through research by the inventor, it is found that the existing methods for identifying the installation location of a mobile surveillance camera mainly rely on manual inspections and simple analysis of monitoring images, lacking an intelligent feedback mechanism for the operating environment, self-debugging status, and collected information of the mobile surveillance camera.

[0061] The following are the main disadvantages of the existing technologies in identifying the installation location of a mobile surveillance camera:

[0062] (1) Low monitoring efficiency: Due to the lack of real-time analysis of environmental impacts and intelligent regulation, the monitoring efficiency of a mobile surveillance camera is easily interfered by the environment, resulting in monitoring blind spots or a decline in image quality.

[0063] (2) High power consumption: A mobile surveillance camera will consume more energy in an inefficient operating state (such as mismatched focal lengths and unreasonable pan-tilt angles), increasing the power consumption of the device.

[0064] (3) Dependence on manual intervention: It is necessary for operators to frequently check and adjust the position and parameters of the mobile surveillance camera, increasing the labor cost and workload.

[0065] (4) Potential safety hazards: Due to the lack of intelligent analysis of moving objects (such as distribution density and movement speed), it is difficult for the existing technologies to timely detect potential safety hazards during construction, increasing the risk of safety accidents.

[0066] To solve the above problems, it is imperative to develop a method that can automatically detect whether the mobile video surveillance device is illegally placed. Based on this, the method, device, electronic device, and computer-readable storage medium for identifying the position of the mobile video surveillance device provided by the embodiments of the present invention analyze the surveillance images captured by the mobile video surveillance device, accurately locate the body area of the monitored object, divide it into the upper body area and the lower body area, and infer the compliance of the placement position of the mobile video surveillance device through the relative positions of the upper body area and the lower body area in the surveillance image, realizing the intelligent identification of the installation state of the mobile video surveillance device, thereby providing reliable intelligent support for security monitoring, reducing manual intervention, and having the significant advantages of high monitoring accuracy, strong robustness, and low cost, and having a broader application prospect.

[0067] The following will describe each embodiment of the present invention in detail with reference to the accompanying drawings.

[0068] Please refer to Figure 1 , Figure 1 which shows a schematic flowchart of a method for identifying the position of a mobile video surveillance device provided by an embodiment of the present invention. The method includes the following steps:

[0069] Step S10, identifying the upper body bounding box and the lower body bounding box of the monitored object according to the surveillance image captured by the mobile video surveillance device.

[0070] Step S20, judging whether the position of the mobile video surveillance device is illegal according to the positions of the upper body bounding box and the lower body bounding box in the surveillance image.

[0071] In the embodiments of the present invention, a real-time surveillance image captured by the mobile video surveillance device for the monitored object (such as construction workers, people entering the security area, etc.) is obtained, and the surveillance image is detected to obtain the upper body bounding box and the lower body bounding box of the monitored object. The relative positions of the upper body bounding box and the lower body bounding box in the surveillance image are analyzed respectively, and whether the installation position of the mobile video surveillance device is illegal is identified through the relative position analysis, that is, it is judged whether the mobile video surveillance device is illegally placed.

[0072] It should be noted that illegal placement means that the mobile video surveillance device is not placed on a tripod or other fixed bracket as required, but is randomly placed on an unstable surface, a position that does not meet the standard height requirement, a position that does not meet the safety specification, etc. Such illegal placement may cause the instability of the mobile video surveillance device, affect the monitoring effect, and even may cause potential safety hazards.

[0073] In summary, the method for identifying the position of the mobile surveillance camera provided by the embodiment of the present invention analyzes the surveillance image captured by the mobile surveillance camera, accurately locates the body area of the monitored object, divides it into the upper body area and the lower body area, and infers the compliance of the placement position of the mobile surveillance camera based on the relative positions of the upper body area and the lower body area in the surveillance image, realizing the intelligent identification of the installation state of the mobile surveillance camera, thereby providing reliable intelligent support for security surveillance, reducing manual intervention, and having the remarkable advantages of high monitoring accuracy, strong robustness and low cost, and having a broader application prospect.

[0074] Optionally, for how to generate the upper body bounding box and the lower body bounding box, a possible implementation manner is provided below. Please refer to Figure 2 , Figure 1 The sub-steps of step S10 may include:

[0075] Step S101, perform object detection on the monitored object according to the surveillance image to obtain a person bounding box.

[0076] In the embodiment of the present invention, object detection is a technique in the field of computer vision that uses an object detection algorithm to detect and locate the monitored object appearing in the surveillance image to obtain a person bounding box. Among them, the object detection algorithm includes but is not limited to the You Only Look Once (YOLO) series, the Single Shot MultiBox Detector (SSD), etc. The YOLO series includes but is not limited to YOLOv8, YOLO-NAS, etc. The monitored object includes but is not limited to construction workers, people entering the security area, etc. The person bounding box represents the minimum bounding rectangle of the monitored object.

[0077] In order to further improve the recognition accuracy of the monitored object, the object detection model corresponding to the object detection algorithm can be trained with a pre-prepared high-quality labeled data set, and then the object detection model is used to perform object detection on the monitored object in the surveillance image to obtain the person bounding box corresponding to the monitored object.

[0078] Step S102, perform key point detection according to the person bounding box to obtain the upper body bounding box and the lower body bounding box; the upper body bounding box is determined by the head key point, the shoulder key point and the hip key point; the lower body bounding box is determined by the hip key point and the ankle key point.

[0079] In the embodiments of the present invention, a key point detection algorithm is used to perform refined detection on the person bounding box. By identifying key points such as the head, shoulders, hips, and ankles, an upper body bounding box and a lower body bounding box of the monitored object are generated. Among them, the key point detection algorithm includes but is not limited to the High-Resolution Network (HRNet for short), OpenPose, etc. The upper body bounding box is a rectangular area determined by the head key point, shoulder key points, and hip key points, and the lower body bounding box is a rectangular area determined by the hip key point and ankle key points.

[0080] It can be seen that in the embodiments of the present invention, the monitoring object in the monitored object is quickly identified and framed through object detection, and the body parts of the monitored object are accurately located based on the person bounding box, providing a reliable basis for subsequent judgment of whether the position of the ball control camera is illegal, avoiding misjudgment caused by environmental interference or poor image quality, and significantly improving the robustness and accuracy of the judgment of the position of the ball control camera.

[0081] Optionally, for how to judge whether the position of the ball control camera is illegal, a possible implementation method is provided below. Please refer to Figure 2 , Figure 1 The sub-steps of step S20 in can include:

[0082] Step S201, judge whether the upper body bounding box is valid according to the confidence of the head key point, the confidence of the shoulder key points, the confidence of the hip key point, the head ordinate, and the abdominal ordinate.

[0083] In the embodiments of the present invention, a key point detection algorithm is used to identify the key points of the monitored object in the person bounding box, and the coordinates and confidence of each key point are obtained. Among them, the coordinates of the key point include the abscissa and the ordinate. It should be noted that the confidence of each key point corresponding to the monitored object can be initialized, for example, initialized to 0.

[0084] Step S202, if the upper body bounding box is invalid, determine that the position of the ball control camera is illegal.

[0085] Step S203, if the upper body bounding box is valid, judge whether the position of the ball control camera is illegal according to the bottom frame of the upper body bounding box, the bottom frame of the lower body bounding box, and the bottom of the monitoring image.

[0086] In the embodiments of the present invention, when the upper body bounding box is determined to be invalid, it is determined that the ball control camera is placed in an illegal position, such as a position with an unqualified height such as the ground. When the upper body bounding box is determined to be valid, it is necessary to further determine whether the position of the ball control camera is compliant or illegal by using the relative positions of the bottom frame of the upper body bounding box, the bottom frame of the lower body bounding box, and the bottom of the monitoring image. Among them, the bottom of the monitoring image refers to the lower bottom edge of the monitoring image.

[0087] It can be seen that the embodiments of the present invention evaluate the effectiveness of the upper body bounding box by using the confidence and position coordinates of key points, which can avoid misjudgment of the position of the PTZ due to key point detection errors. When the upper body bounding box is effective, the relative positions of the upper body bounding box and the lower body bounding box in the surveillance image are further comprehensively analyzed, and the misjudgment probability is effectively reduced through hierarchical reasoning and judgment, improving the robustness, accuracy and reliability of the PTZ position judgment, and providing key technical support for realizing efficient and intelligent detection of illegal placement of PTZs.

[0088] Optionally, a possible implementation manner is provided below for how to determine the effectiveness of the upper body bounding box. Figure 2 The sub-steps of step S201 in may include:

[0089] Determine the head vertical coordinate according to the vertical coordinates of the nose key point, the left ear key point and the right ear key point among the head key points; determine the abdominal vertical coordinate according to the vertical coordinates of the left hip key point and the right hip key point among the hip key points; if the confidence of the head key point, the confidence of the shoulder key point, and the confidence of the hip key point are all greater than the confidence threshold, and the head vertical coordinate is less than the abdominal vertical coordinate, determine that the upper body bounding box is effective; if the confidence of the head key point, the confidence of the shoulder key point, or the confidence of the hip key point is not greater than the confidence threshold, or the head vertical coordinate is not less than the abdominal vertical coordinate, determine that the upper body bounding box is ineffective.

[0090] In the embodiments of the present invention, the head key points include but are not limited to the nose key point, the left ear key point and the right ear key point. Determine the head vertical coordinate according to the minimum value of the vertical coordinates of the nose key point, the left ear key point and the right ear key point, and the head extension margin. The calculation formula of the head vertical coordinate is as follows:

[0091] y h = min(y0, y1, y2) - δ

[0092] where, y h is the head vertical coordinate; y0 is the vertical coordinate of the nose key point; y1 is the vertical coordinate of the left ear key point; y2 is the vertical coordinate of the right ear key point; δ is the head extension margin.

[0093] Determine the mean value of the vertical coordinates of the left hip key point and the right hip key point as the abdominal vertical coordinate. The calculation formula of the abdominal vertical coordinate is as follows:

[0094] y a = (y5 + y6) / 2

[0095] where, y ay0 is the vertical coordinate of the abdomen; y5 is the vertical coordinate of the left hip key point; y6 is the vertical coordinate of the right hip key point.

[0096] As a possible implementation, assume the confidence threshold is 0.3. When the confidence of the head key point is greater than 0.3, the confidence of the shoulder key point is greater than 0.3, the confidence of the hip key point is greater than 0.3, and it satisfies y a >y h Then it is determined that the upper body bounding box is valid, that is, the upper body of the monitored object can be detected.

[0097] Among them, the confidence of the head key point can be determined according to the confidence of the nose key point, the left ear key point, and the right ear key point respectively. The confidence of the shoulder key point can be determined according to the confidence of the left shoulder key point and the right shoulder key point respectively. The confidence of the hip key point can be determined according to the confidence of the left hip key point and the right hip key point. The determination methods include but are not limited to the mean, median, etc.

[0098] When the upper body bounding box is valid, the upper body bounding box includes the nose key point, the left ear key point, the right ear key point, the left shoulder key point, the right shoulder key point, the left hip key point, and the right hip key point. Determine the minimum abscissa and the maximum abscissa of the upper body bounding box according to the abscissa of the left shoulder key point and the abscissa of the right shoulder key point. At the same time, determine the minimum vertical coordinate of the upper body bounding box as the vertical coordinate of the head, and determine the maximum vertical coordinate of the upper body bounding box as the vertical coordinate of the abdomen. The calculation formulas for the minimum abscissa and the maximum abscissa of the upper body bounding box are as follows:

[0099] x_min upper = min(x3, x4)

[0100] x_max upper = max(x3, x4)

[0101] Among them, x_min upper is the minimum abscissa of the upper body bounding box; x_max upper is the maximum abscissa of the upper body bounding box; x3 is the abscissa of the left shoulder key point; x4 is the abscissa of the right shoulder key point; min(·) is the minimum value function; max(·) is the maximum value function.

[0102] When the confidence of the head key point is not greater than 0.3, the confidence of the shoulder key point is greater than 0.3 or the confidence of the hip key point is greater than 0.3, or it satisfies y a ≤y h Then it is determined that the upper body bounding box is invalid, and the upper body of the monitored object cannot be detected.

[0103] Optionally, a possible implementation method is provided below for determining whether the position of the PTZ camera is illegal by using the bottom frame of the upper body bounding box, the bottom frame of the lower body bounding box, and the bottom of the monitoring image. Figure 2 The sub-steps of step S203 may include:

[0104] Determine whether the lower body bounding box is valid according to the confidence of the hip key point and the confidence of the ankle key point; if the lower body bounding box is invalid, determine that the position of the PTZ camera is illegal; if the lower body bounding box is valid, determine whether the ratio of the distance between the bottom frame of the lower body bounding box and the bottom of the monitoring image to the height of the monitoring image is less than a first threshold; if it is less than the first threshold, determine that the position of the PTZ camera is compliant; if it is not less than the first threshold, determine whether the ratio of the distance between the bottom frame of the upper body bounding box and the bottom frame of the monitoring image to the height of the monitoring image is less than a second threshold; the second threshold is greater than the first threshold; if it is not less than the second threshold, determine that the position of the PTZ camera is illegal; if it is less than the second threshold, determine that the position of the PTZ camera is compliant.

[0105] In an embodiment of the present invention, if the confidence of the hip key point and the confidence of the ankle key point are both greater than the confidence threshold, it is determined that the lower body bounding box is valid. If the confidence of the hip key point or the confidence of the ankle key point is not greater than the confidence threshold, it is determined that the lower body bounding box is invalid, that is, it is determined that the position of the PTZ camera is illegal. Among them, the ankle key points include the left ankle key point and the right ankle key point, and the confidence of the ankle key point can be determined according to the confidence of the left ankle key point and the confidence of the right ankle key point. The determination methods include but are not limited to mean, median, etc.

[0106] In an embodiment of the present invention, the abdominal ordinate is determined as the minimum ordinate of the lower body bounding box; the maximum value of the ordinates of the left ankle key point and the right ankle key point is determined as the maximum ordinate of the lower body bounding box. The calculation formula for the maximum ordinate of the lower body bounding box is as follows:

[0107] y_max lower = max(y7, y8)

[0108] where, y_max lower is the maximum ordinate of the lower body bounding box; y7 is the ordinate of the left ankle key point; y8 is the ordinate of the right ankle key point.

[0109] Determine the minimum abscissa and the maximum abscissa of the lower body bounding box according to the abscissas of the left hip key point, the right hip key point, the left ankle key point, and the right ankle key point. The calculation formulas for the minimum abscissa and the maximum abscissa of the lower body bounding box are as follows:

[0110] x_min lower = min(x5, x6, x7, x8)

[0111] x_max lower = max(x5, x6, x7, x8)

[0112] where x_min lower is the minimum abscissa of the lower body bounding box; x_max lower is the maximum abscissa of the lower body bounding box; x5 is the abscissa of the left hip key point; x6 is the abscissa of the right hip key point; x7 is the abscissa of the left ankle key point; x8 is the abscissa of the right ankle key point.

[0113] It should be noted that the ordinate of the bottom frame of the lower body bounding box is the maximum ordinate of the lower body bounding box, and the ordinate of the bottom of the surveillance image is the height of the surveillance image. The calculation formula for the relative height ratio of the bottom frame of the upper body bounding box to the bottom of the surveillance image is as follows:

[0114] d lower = (h i - y_max lower ) / h i

[0115] where d lower is the relative height ratio of the bottom frame of the upper body bounding box to the bottom of the surveillance image; h i is the height of the surveillance image.

[0116] When the ratio d lower of the distance between the bottom frame of the lower body bounding box and the bottom of the surveillance image to the height of the surveillance image is less than the first threshold, the monitored object is completely captured by the PTZ in the surveillance image, and the installation position of the PTZ is compliant.

[0117] When the ratio d lower of the distance between the bottom frame of the lower body bounding box and the bottom of the surveillance image to the height of the surveillance image is not less than the first threshold, it indicates that the ankles of the monitored object are far from the bottom of the surveillance image, and it is necessary to continue to judge the distance between the abdomen of the monitored object and the bottom of the surveillance image, that is, the relative height ratio d upper of the bottom frame of the lower body bounding box to the bottom of the surveillance image, and the calculation formula is as follows:

[0118] d upper = (h i - y a ) / h i

[0119] When the ratio of the distance between the bottom frame of the upper body bounding box and the bottom of the surveillance image to the height of the surveillance image is less than the second threshold, it is determined that the installation position of the PTZ is compliant, otherwise it is determined that the installation position of the PTZ is illegal.

[0120] It can be seen that in the embodiments of the present invention, by setting threshold conditions at different levels and comprehensively considering the distribution characteristics of the upper and lower bodies of the human body in the image, the states of compliant placement and non-compliant placement of the cloth control ball can be effectively distinguished, avoiding misjudgment problems that may be caused by single-condition judgment, thereby significantly improving the accuracy and reliability of the recognition result.

[0121] Optionally, before identifying the position of the cloth control ball, it is necessary to first determine a first threshold and a second threshold. For how to determine the first threshold and the second threshold, a possible implementation method is provided below.

[0122] Please refer to Figure 3 , and the method further includes the following steps:

[0123] Step S30: Obtain the first abdominal ratio and the first ankle ratio corresponding to each monitoring distance according to the field of view angle of the cloth control ball, the compliant height of the cloth control ball, the abdominal height of the observation object, and multiple monitoring distances between the cloth control ball and the observation object.

[0124] In the embodiments of the present invention, the field of view angle refers to the scene range that a camera or optical system can capture, usually expressed in degrees. The size of the field of view angle determines the area range that the monitoring device can cover. A larger field of view angle means that the device can monitor a wider area, while a smaller field of view angle means that the monitoring range is more concentrated. For the cloth control ball, the field of view angle is an important parameter for its panoramic monitoring ability.

[0125] Based on the analysis of the field of view angle of the cloth control ball, a dual-threshold determination model is established, that is, the first threshold and the second threshold. Place the cloth control ball at a compliant position to obtain the compliant height of the cloth control ball, and use the field of view angle, compliant height, and abdominal height of the observation object to calculate the first abdominal ratio and the first ankle ratio corresponding to different monitoring distances through spatial geometric modeling. Among them, the observation object can be the monitored object or a person of any height.

[0126] As a possible implementation method, taking Figure 4 as an example, place the cloth control ball at the compliant position O, for example, place the cloth control ball on a tripod. OA represents the compliant height of the cloth control ball, point B represents the position corresponding to the ankle, point C represents the position corresponding to the abdomen, OD is the horizontal line, point E represents the position corresponding to the head, ∠FOB is the field of view angle of the cloth control ball (assumed to be 50 degrees), and AB represents the horizontal distance between the observation object and the cloth control ball (i.e., the monitoring distance).

[0127] The calculation formulas for the first abdominal ratio and the first ankle ratio are as follows:

[0128]

[0129] Among them, d 11 is the first abdominal ratio; d 12The first ankle ratio; θ is the field of view angle of the camera in the fixed position; h1 is the abdominal height of the observed object; h2 is the compliance height of the camera in the fixed position; x is the monitoring distance.

[0130] Step S40: Based on the field of view angle of the camera in the fixed position, the violation height of the camera in the fixed position, the abdominal height of the observed object, and multiple monitoring distances between the camera in the fixed position and the observed object, obtain the second abdominal ratio and the second ankle ratio corresponding to each monitoring distance.

[0131] As another possible implementation, taking Figure 5 as an example, place the camera in the fixed position at the violation position P, for example, place the camera on the ground. PA represents the violation height of the camera in the fixed position, point B represents the position corresponding to the ankle, point C represents the position corresponding to the abdomen, PD is the horizontal line, point E represents the position corresponding to the head, ∠FPB is the field of view angle of the camera in the fixed position (assumed to be 50 degrees), and AB represents the horizontal distance between the observed object and the camera in the fixed position (i.e., the monitoring distance).

[0132] The calculation formulas for the second abdominal ratio and the second ankle ratio are as follows:

[0133]

[0134] where d 21 is the second abdominal ratio; d 22 is the second ankle ratio; h3 is the violation height of the camera in the fixed position.

[0135] Step S50: Generate a first abdominal curve based on all the first abdominal ratios, and generate a first ankle curve based on all the first ankle ratios.

[0136] In the embodiment of the present invention, assume that the camera in the fixed position is placed on a tripod at 1.3 meters to ensure that the camera in the fixed position is in a compliant position. Fit according to the first abdominal ratios at different monitoring distances (such as 1 to 40 meters) to obtain the first abdominal curve; fit according to the first ankle ratios at different monitoring distances to obtain the first ankle curve, as Figure 6 shown.

[0137] Step S60: Generate a second abdominal curve based on all the second abdominal ratios, and generate a second ankle curve based on all the second ankle ratios.

[0138] Step S70: Determine a first threshold and a second threshold based on the first abdominal curve, the first ankle curve, the second abdominal curve, and the second ankle curve.

[0139] In an embodiment of the present invention, it is assumed that the cloth control camera is placed on the ground at a height of 0.2 meters to ensure that the cloth control camera is in a violation position. According to the second abdomen ratio under different monitoring distances (for example, 1 to 40 meters), fitting is performed to obtain the second abdomen curve; according to the second ankle ratio under different monitoring distances, fitting is performed to obtain the second ankle curve, as Figure 7 shown.

[0140] It can be seen that, based on the field of view angle characteristics of the cloth control camera at the compliance height and the violation height, the present invention embodiment generates the ratios of the abdomen and ankles in the image at different monitoring distances, and generates curves based on the ratios. By analyzing the abdomen curve and the ankle curve, the imaging rules under compliance placement and violation placement are obtained, and the first threshold and the second threshold for judging the position state of the cloth control camera are determined according to the imaging rules, realizing the automatic and refined setting of the first threshold and the second threshold, and providing technical guarantee for the intelligent identification of the position of the cloth control camera. By intelligently analyzing the placement position and operation parameters of the cloth control camera, it guides the operator to optimize the deployment of the cloth control camera, so as to timely discover potential safety hazards in the monitoring area and reduce the risk of safety accidents.

[0141] Optionally, for how to determine the first threshold and the second threshold according to the four curves, a possible implementation manner is provided below. Figure 3 The sub-steps of step S70 in

[0142] may include:

[0143] Determine the monitoring distance of the preset abdomen ratio in the second abdomen curve as the critical distance; determine the first threshold according to the first ankle curve, the second ankle curve and the critical distance; determine the abdomen ratio corresponding to the first intersection point of the stable interval of the first abdomen curve and the stable interval of the second abdomen curve as the second threshold.

[0143] In an embodiment of the present invention, it is assumed that the preset abdomen ratio is 100%. When there is an abdomen ratio of 100% in the second abdomen curve, the monitoring distance corresponding to the abdomen ratio of 100% is determined as the critical distance, and the ankle ratio corresponding to the critical distance in the second ankle curve is determined as the critical ankle ratio. When there is a critical ankle ratio in the first ankle curve and the abdomen ratio in the first abdomen curve is less than half of the preset abdomen ratio (for example, 50%), the critical ankle ratio is determined as the first threshold. Among them, the stable interval refers to the interval where the change range of the abdomen ratio is lower than the amplitude threshold (for example, 5%) and tends to be relatively stable, such as Figure 6 and Figure 7 the interval with a monitoring distance of 20 meters to 40 meters in

[0144] From Figure 7It can be seen that when the cloth control camera is placed on the ground and the monitoring distance between the cloth control camera and the observed object is 1 meter, the proportion of the second abdomen is 100%. 1 meter is the critical distance, and the critical ankle proportion (the proportion of the second ankle) is approximately 25%. When the monitoring distance between the cloth control camera and the observed object gets closer and closer (less than 1 meter), the proportion of the second ankle is less than 25%, and the proportion of the second abdomen exceeds 100%. At this time, it has far exceeded the field of view angle range of the cloth control camera, and the upper body of the observed object is not visible. When the monitoring distance between the cloth control camera and the observed object gets farther and farther (more than 1 meter), the proportion of the second ankle is greater than 25%, and the proportion of the second abdomen gradually decreases from 100% and finally approaches 50% (that is, the proportion of the second abdomen is greater than or equal to 50%), and the upper body of the observed object is visible.

[0145] From Figure 6 It can be seen that when the cloth control camera is placed on the tripod, the monitoring distance corresponding to the critical ankle proportion (25%) is obtained in the first ankle curve, that is, the monitoring distance between the cloth control camera and the observed object is approximately 6 meters. When the monitoring distance between the cloth control camera and the observed object gets closer and closer (less than 6 meters), the proportion of the first ankle is less than 25%, and the proportion of the first abdomen is between 20% and 40%, and the upper body of the observed object is visible. When the monitoring distance between the cloth control camera and the observed object gets farther and farther (more than 6 meters), the proportion of the first ankle is greater than 25%, and the proportion of the first abdomen gradually increases from 44% and finally approaches 50% (that is, the proportion of the first abdomen is less than or equal to 50%), and the upper body of the observed object is visible.

[0146] Based on the above content, it can be known that if the upper body of the monitored object cannot be detected, the cloth control camera is installed in an illegal position, which belongs to an abnormal state and can trigger an alarm. If the ankle proportion is less than 25%, that is, the bottom frame of the lower body bounding box is less than 25% of the height of the monitoring image from the bottom of the monitoring image, and the upper body of the monitored object is visible, it indicates that the cloth control camera is arranged in a compliant position (such as on a tripod), which belongs to a normal state. If the upper body of the monitored object is not visible, the cloth control camera is installed in an illegal position (such as on the ground), which belongs to an abnormal state and can trigger an alarm.

[0147] If the ankle proportion is not less than 25%, that is, the bottom frame of the lower body bounding box is not less than 25% of the height of the monitoring image from the bottom of the monitoring image. If the upper body of the monitored object is detected, further calculate the ratio of the distance between the bottom frame of the upper body bounding box and the bottom of the monitoring image to the height of the monitoring image. If the ratio of the distance between the bottom frame of the upper body bounding box and the bottom of the monitoring image to the height of the monitoring image is less than 50%, the cloth control camera is installed in a compliant position, which belongs to a normal state. If the ratio of the distance between the bottom frame of the upper body bounding box and the bottom of the monitoring image to the height of the monitoring image is not less than 50%, the cloth control camera is installed in an illegal position, which belongs to an abnormal state and can trigger an alarm.

[0148] Based on the same inventive concept, the basic principle and the technical effects of the device for identifying the position of the mobile video surveillance device provided in the embodiments of the present invention are the same as those in the above embodiments. For the sake of brief description, for the parts not mentioned in this embodiment, reference may be made to the corresponding content in the above embodiments.

[0149] Please refer to Figure 8 , Figure 8 , which is a schematic block diagram of a device 300 for identifying the position of a mobile video surveillance device provided in an embodiment of the present invention. The device 300 for identifying the position of a mobile video surveillance device includes a processing module 301 and a determination module 302.

[0150] The processing module 301 is configured to identify the upper body bounding box and the lower body bounding box of the monitored object according to the surveillance image captured by the mobile video surveillance device;

[0151] The determination module 302 is configured to determine whether the position of the mobile video surveillance device is illegal according to the positions of the upper body bounding box and the lower body bounding box in the surveillance image.

[0152] In summary, the device for identifying the position of a mobile video surveillance device provided in the embodiments of the present invention analyzes the surveillance image captured by the mobile video surveillance device, accurately locates the body area of the monitored object, divides the upper body area and the lower body area, and infers the compliance of the placement position of the mobile video surveillance device through the relative positions of the upper body area and the lower body area in the surveillance image, realizing the intelligent identification of the installation state of the mobile video surveillance device, thereby providing reliable intelligent support for security monitoring, reducing manual intervention, and having the remarkable advantages of high monitoring accuracy, strong robustness and low cost, and having a wider application prospect.

[0153] Optionally, the processing module 301 is specifically configured to perform target detection on the monitored object according to the surveillance image to obtain a person bounding box; perform key point detection on the person bounding box to obtain the upper body bounding box and the lower body bounding box; the upper body bounding box is determined by the head key point, the shoulder key point and the hip key point; the lower body bounding box is determined by the hip key point and the ankle key point.

[0154] Optionally, the determination module 302 is specifically configured to determine whether the upper body bounding box is valid according to the confidence of the head key point, the confidence of the shoulder key point, the confidence of the hip key point, the head vertical coordinate and the abdomen vertical coordinate; if the upper body bounding box is invalid, determine that the position of the mobile video surveillance device is illegal; if the upper body bounding box is valid, determine whether the position of the mobile video surveillance device is illegal according to the bottom frame of the upper body bounding box, the bottom frame of the lower body bounding box and the bottom of the surveillance image.

[0155] Optionally, the determination module 302 is specifically configured to determine the head vertical coordinate according to the vertical coordinates of the nose key point, the left ear key point and the right ear key point in the head key points;

[0156] Determine the abdominal ordinate according to the respective ordinate of the left hip key point and the right hip key point in the hip key points; if the confidence of the head key point, the confidence of the shoulder key point, and the confidence of the hip key point are all greater than the confidence threshold, and the head ordinate is less than the abdominal ordinate, determine that the upper body bounding box is valid; if the confidence of the head key point, the confidence of the shoulder key point, or the confidence of the hip key point is not greater than the confidence threshold, or the head ordinate is not less than the abdominal ordinate, determine that the upper body bounding box is invalid.

[0157] Optionally, the determination module 302 is specifically configured to determine whether the lower body bounding box is valid according to the confidence of the hip key point and the confidence of the ankle key point; if the lower body bounding box is invalid, determine that the position of the ball control camera is illegal; if the lower body bounding box is valid, determine whether the ratio of the distance between the bottom frame of the lower body bounding box and the bottom of the monitoring image to the height of the monitoring image is less than the first threshold; if it is less than the first threshold, determine that the position of the ball control camera is compliant; if it is not less than the first threshold, determine whether the ratio of the distance between the bottom frame of the upper body bounding box and the bottom of the monitoring image to the height of the monitoring image is less than the second threshold; the second threshold is greater than the first threshold; if it is not less than the second threshold, determine that the position of the ball control camera is illegal; if it is less than the second threshold, determine that the position of the ball control camera is compliant.

[0158] Optionally, the processing module 301 is further configured to obtain the first abdominal ratio and the first ankle ratio corresponding to each monitoring distance according to the field of view angle of the ball control camera, the compliant height of the ball control camera, the abdominal height of the observed object, and multiple monitoring distances between the ball control camera and the observed object; obtain the second abdominal ratio and the second ankle ratio corresponding to each monitoring distance according to the field of view angle of the ball control camera, the illegal height of the ball control camera, the abdominal height of the observed object, and multiple monitoring distances between the ball control camera and the observed object; generate a first abdominal curve according to all the first abdominal ratios and generate a first ankle curve according to all the first ankle ratios; generate a second abdominal curve according to all the second abdominal ratios and generate a second ankle curve according to all the second ankle ratios; determine the first threshold and the second threshold according to the first abdominal curve, the first ankle curve, the second abdominal curve, and the second ankle curve.

[0159] Optionally, the processing module 301 is specifically configured to determine the monitoring distance of the preset abdominal ratio in the second abdominal curve as the critical distance; determine the first threshold according to the first ankle curve, the second ankle curve, and the critical distance; determine the abdominal ratio corresponding to the first intersection point of the stable interval of the first abdominal curve and the stable interval of the second abdominal curve as the second threshold.

[0160] Please refer to Figure 9, which is a block diagram of an electronic device 400 provided by an embodiment of the present invention. The electronic device 400 includes a memory 410, a processor 420, and a communication module 430. The components of the memory 410, the processor 420, and the communication module 430 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0161] Among them, the memory 410 is used to store programs or data. The memory 410 can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0162] The processor 420 is used to read / write the data or programs stored in the memory 410 and perform corresponding functions. For example, when the computer program stored in the memory 410 is executed by the processor 420, the position recognition method of the PTZ camera disclosed in the above embodiments can be implemented.

[0163] The communication module 430 is used to establish a communication connection between the electronic device 400 and other communication terminals through a network and is used to transmit and receive data through the network.

[0164] It should be understood that Figure 9 The structure shown is only a schematic diagram of the structure of the electronic device 400, and the electronic device 400 may further include more or fewer components than those shown Figure 9 in the figure, or have a different configuration from that shown Figure 9 in the figure. Figure 9 Each component shown in the figure can be implemented by hardware, software, or a combination thereof.

[0165] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor 420, the position recognition method of the PTZ camera disclosed in the above embodiments is implemented.

[0166] An embodiment of the present invention also provides a program product. When the program product is executed by the processor 420, the position recognition method of the PTZ camera disclosed in the above embodiments is implemented.

[0167] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0168] In addition, in each embodiment of the present invention, the various functional modules can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0169] If the above functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0170] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying the position of a mobile video surveillance device, characterized in that, The method includes: Identifying an upper body bounding box and a lower body bounding box of a monitoring object based on a monitoring image captured by a PTZ camera; Judging whether the position of the PTZ camera is illegal according to the positions of the upper body bounding box and the lower body bounding box in the monitoring image.

2. The method for identifying the position of a cloth control ball according to claim 1, wherein The identifying of the upper body bounding box and the lower body bounding box of the monitoring object based on the monitoring image captured by the PTZ camera includes: Performing object detection on the monitoring object according to the monitoring image to obtain a person bounding box; Performing key point detection according to the person bounding box to obtain the upper body bounding box and the lower body bounding box; the upper body bounding box is determined by head key points, shoulder key points and hip key points; the lower body bounding box is determined by hip key points and ankle key points.

3. The method for identifying the position of the cloth control ball according to claim 2, wherein The judging of whether the position of the PTZ camera is illegal according to the positions of the upper body bounding box and the lower body bounding box in the monitoring image includes: Judging whether the upper body bounding box is valid according to the confidence of the head key points, the confidence of the shoulder key points, the confidence of the hip key points, the head vertical coordinate and the abdomen vertical coordinate; If the upper body bounding box is invalid, determining that the position of the PTZ camera is illegal; If the upper body bounding box is valid, judging whether the position of the PTZ camera is illegal according to the bottom frame of the upper body bounding box, the bottom frame of the lower body bounding box and the bottom of the monitoring image.

4. The method for identifying the position of the panoramic camera according to claim 3, wherein The judging of whether the upper body bounding box is valid according to the confidence of the head key points, the confidence of the shoulder key points, the confidence of the hip key points, the head vertical coordinate and the abdomen vertical coordinate includes: Determining the head vertical coordinate according to the vertical coordinates of the nose key point, the left ear key point and the right ear key point in the head key points; Determining the abdomen vertical coordinate according to the vertical coordinates of the left hip key point and the right hip key point in the hip key points; If the confidence of the head key points, the confidence of the shoulder key points and the confidence of the hip key points are all greater than a confidence threshold, and the head vertical coordinate is less than the abdomen vertical coordinate, determining that the upper body bounding box is valid; If the confidence of the head key points, the confidence of the shoulder key points or the confidence of the hip key points is not greater than the confidence threshold, or the head vertical coordinate is not less than the abdomen vertical coordinate, determining that the upper body bounding box is invalid.

5. The method for identifying the position of the camera ball according to claim 3, wherein The judging of whether the position of the PTZ camera is illegal according to the bottom frame of the upper body bounding box, the bottom frame of the lower body bounding box and the bottom of the monitoring image includes: Judging whether the lower body bounding box is valid according to the confidence of the hip key points and the confidence of the ankle key points; If the lower body bounding box is invalid, determining that the position of the PTZ camera is illegal; If the lower body bounding box is valid, judging whether the ratio of the distance between the bottom frame of the lower body bounding box and the bottom of the monitoring image to the height of the monitoring image is less than a first threshold; If it is less than the first threshold, determining that the position of the PTZ camera is compliant; If it is not less than the first threshold, determining whether the ratio of the distance between the bottom frame of the upper body constraint frame and the bottom of the monitoring image to the height of the monitoring image is less than a second threshold; the second threshold is greater than the first threshold; If it is not less than the second threshold, it is determined that the position of the control ball is illegal; If it is less than the second threshold, it is determined that the position of the control ball is compliant.

6. The method for identifying the position of the cloth control ball according to claim 5, wherein, Before identifying the upper body constraint frame and the lower body constraint frame of the monitored object according to the monitoring image taken by the surveillance ball, the method further includes: According to the field of view of the control ball, the compliance height of the control ball, the abdomen height of the observed object, and multiple monitoring distances between the control ball and the observed object, a first abdomen proportion and a first ankle proportion corresponding to each of the monitoring distances are obtained; According to the field of view angle of the control ball, the violation height of the control ball, the abdomen height of the observed object, and multiple monitoring distances between the control ball and the observed object, a second abdomen proportion and a second ankle proportion corresponding to each of the monitoring distances are obtained; generating a first abdomen curve according to all the first abdomen proportions, and generating a first ankle curve according to all the first ankle proportions; generating a second abdomen curve according to all of the second abdomen proportions, and generating a second ankle curve according to all of the second ankle proportions; The first threshold and the second threshold are determined according to the first abdomen curve, the first ankle curve, the second abdomen curve, and the second ankle curve.

7. The method for identifying the position of the panoramic camera according to claim 6, wherein, The determining the first threshold and the second threshold according to the first abdomen curve, the first ankle curve, the second abdomen curve and the second ankle curve comprises: Determine a monitoring distance of a preset abdomen proportion in the second abdomen curve as a critical distance; determining the first threshold value according to the first ankle curve, the second ankle curve and the critical distance; The abdomen proportion corresponding to the first intersection point of the stable interval of the first abdomen curve and the stable interval of the second abdomen curve is determined as the second threshold.

8. A cloth control ball position recognition device, characterized in that, The device comprises: A processing module, used for identifying an upper body constraint frame and a lower body constraint frame of a monitored object according to a monitoring image taken by a surveillance ball; A determination module is used to determine whether the position of the control ball is in violation of the rules according to the positions of the upper body constraint frame and the lower body constraint frame in the monitoring image.

9. An electronic device, characterized in that, It comprises a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the method for identifying the position of a controlled ball as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the method for identifying the position of a controlled ball as described in any one of claims 1 to 7 is implemented.

Images