Method for tracking a trajectory of a person, tracking device thereof and tracking system thereof

Abstract

The application provides a tracking method of personnel trajectory, a tracking device thereof and a tracking system thereof. The method comprises the following steps: firstly, obtaining multiple image information and multiple parameter information of multiple preliminary shooting devices in a predetermined space; then, determining predetermined coordinate information of personnel in each image information according to the parameter information and the image information, wherein the predetermined coordinate information is three-dimensional coordinate information of the personnel in the image information; subsequently, obtaining identity information corresponding to the personnel in each image information; then, determining a target shooting device group from the multiple preliminary shooting devices according to the predetermined coordinate information and the identity information, wherein the target shooting device group is a shooting device without failure in the multiple preliminary shooting devices; finally, determining target coordinate information of the personnel in the target shooting device group as the predetermined coordinate information. The accuracy of tracking the personnel trajectory in the predetermined space is high, and the problem of inaccurate positioning of indoor personnel in the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of trajectory tracking, and more specifically, to a method, a tracking device, and a tracking system for tracking the trajectory of persons. Background Technology

[0002] Currently, in coal preparation plant operations, due to the presence of numerous mechanical devices and unsafe factors within the workshop, accurate and effective location of workers is a crucial means of preventing accidents and ensuring worker safety.

[0003] Currently, most methods for locating workers at work sites use GPS (Global Positioning System), BeiDou Navigation Satellite System, and UWB (Ultra Wide Band) positioning systems. However, GPS and BeiDou systems have insufficient positioning accuracy and cannot locate indoors, while UWB systems are expensive and inconvenient to use. Therefore, there is a need to propose a simple and quick method for indoor personnel positioning. Summary of the Invention

[0004] The main objective of this application is to provide a method, a tracking device, and a tracking system for tracking personnel trajectories, so as to at least solve the problem of inaccurate positioning of indoor personnel in the prior art.

[0005] To achieve the above objectives, according to one aspect of this application, a method for tracking personnel trajectories is provided. The method includes: acquiring multiple image information and multiple parameter information from multiple pre-capture devices within a predetermined space, wherein the parameter information is information on various parameters of the pre-capture devices; determining predetermined coordinate information of a person in each of the image information based on the parameter information and the image information, wherein the predetermined coordinate information is three-dimensional coordinate information of the person in the image information; acquiring identity information corresponding to the person in each of the image information; determining a target capture device group among the multiple capture devices based on the predetermined coordinate information and the identity information, wherein the target capture device group is a capture device without malfunction among the multiple pre-capture devices; and determining the predetermined coordinate information corresponding to the person in the target capture device group as target coordinate information.

[0006] Optionally, acquiring parameter information of multiple pre-capture devices within a predetermined space includes: an acquisition step, acquiring intrinsic parameters and distortion parameters of the pre-capture devices; a calibration step, calibrating the distortion parameters using the intrinsic parameters to obtain new distortion parameters; a first determination step, determining new intrinsic parameters based on the new distortion parameters; a looping step, repeatedly executing the calibration step and the first determination step until the values ​​of the new distortion parameters and the new intrinsic parameters converge; and a second determination step, determining the converged new intrinsic parameters as target intrinsic parameters and determining the converged new distortion parameters as target distortion parameters, wherein the target intrinsic parameters and the target distortion parameters constitute the parameter information.

[0007] Optionally, obtaining the identity information corresponding to the person in each of the image information includes: determining the identity information of the person in each of the image information through facial recognition technology.

[0008] Optionally, determining a target shooting device group among multiple shooting devices based on the predetermined coordinate information and the identity information includes: acquiring all the predetermined coordinate information corresponding to the same identity information in multiple image information at the same time; when multiple predetermined coordinate information exists and the difference between the multiple predetermined coordinate information is within a predetermined range, determining that the multiple shooting devices corresponding to the multiple image information form the target shooting device group; when multiple predetermined coordinate information exists and the difference between the multiple predetermined coordinate information is not within the predetermined range, determining the deviation coefficients corresponding to the multiple shooting devices, and determining the target shooting device group based on the multiple deviation coefficients, wherein the deviation coefficients are used to characterize the tracking differences of the personnel trajectories of the multiple shooting devices within the predetermined space, and the deviation coefficients are proportional to the differences of the multiple shooting devices.

[0009] Optionally, determining the target shooting device group based on a plurality of deviation coefficients includes: determining that the shooting device corresponding to the deviation coefficient has not malfunctioned when the deviation coefficient is within a predetermined range; determining that the shooting device corresponding to the deviation coefficient has malfunctioned when the deviation coefficient is not within the predetermined range; and determining that the shooting devices that have not malfunctioned constitute the target shooting device group.

[0010] Optionally, after determining that the shooting device corresponding to the deviation coefficient has malfunctioned, the method further includes: if the deviation coefficient is greater than a predetermined value, determining that multiple shooting devices in the predetermined space have experienced a group malfunction, the predetermined value being greater than the maximum value of the predetermined interval; if the deviation coefficient is not greater than the predetermined value, determining that multiple shooting devices in the predetermined space have experienced a single malfunction.

[0011] Optionally, after determining that multiple shooting devices in the predetermined space have experienced a group failure, the method further includes: obtaining a time interval between two consecutive group failures to obtain a first duration; if the first duration is greater than a predetermined duration, sending a first message to a first terminal device, wherein the first message is used to indicate that the repair result of the group failure is qualified; if the first duration is not greater than the predetermined duration, sending a second message to the first terminal device, wherein the second message is used to indicate that the repair result of the group failure is unqualified.

[0012] Optionally, after determining that a single fault has occurred in one of the multiple shooting devices in the predetermined space, the method further includes: sending the serial number information of the shooting device corresponding to the single fault to a second terminal device.

[0013] According to another aspect of this application, a personnel trajectory tracking device is provided. The device includes a first acquisition unit, a first determination unit, a second acquisition unit, a second determination unit, and a third determination unit. The first acquisition unit is used to acquire multiple image information and multiple parameter information from multiple pre-capture devices within a predetermined space, wherein the parameter information is information about various parameters of the pre-capture devices. The first determination unit is used to determine predetermined coordinate information of a person in each image based on the parameter information and the image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the image. The second acquisition unit is used to acquire identity information corresponding to the person in each image. The second determination unit is used to determine a target capture device group among the multiple capture devices based on the predetermined coordinate information and the identity information, wherein the target capture device group is a capture device without malfunction among the multiple pre-capture devices. The third determination unit is used to determine that the predetermined coordinate information corresponding to the person in the target capture device group is the target coordinate information.

[0014] According to another aspect of this application, a personnel trajectory tracking system is provided, the tracking system comprising multiple imaging devices and a processor, wherein the multiple imaging devices are all located within a predetermined space, the imaging devices being used to provide image information; and the processor being used to execute any of the personnel trajectory tracking methods described above.

[0015] Applying the technical solution of this application, the method for tracking personnel trajectories firstly acquires multiple image information and multiple parameter information from multiple pre-capture devices within a predetermined space, wherein the parameter information comprises information on various parameters of the pre-capture devices; then, based on the parameter information and the image information, predetermined coordinate information of the personnel in each image information is determined, wherein the predetermined coordinate information comprises the three-dimensional coordinate information of the personnel in the image information; subsequently, identity information corresponding to the personnel in each image information is acquired to identify the personnel in the image information; then, based on the predetermined coordinate information and the identity information, a target capture device group among the multiple capture devices is determined, wherein the target capture device group comprises capture devices without malfunctions among the multiple pre-capture devices; finally, the predetermined coordinate information corresponding to the personnel in the target capture device group is determined as the target coordinate information. Compared to the inaccurate positioning of indoor personnel in existing technologies, the personnel trajectory tracking method of this application first acquires the parameter information and image information of multiple pre-capture devices within the predetermined space, enabling the determination of the predetermined coordinate information of the personnel in the image information in three-dimensional space. Then, through the identity information and the predetermined coordinate information, the target capture device group is determined, ensuring that the devices in the target capture device group are not faulty. This ensures a high degree of accuracy in the target coordinate information determined based on the target capture device group, and guarantees a high degree of accuracy in tracking the personnel trajectory within the predetermined space, thus solving the problem of inaccurate positioning of indoor personnel in existing technologies. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for a method of tracking the trajectory of an executor provided in an embodiment of this application is shown.

[0018] Figure 2 A flowchart illustrating a method for tracking personnel trajectories according to an embodiment of this application is shown.

[0019] Figure 3 A flowchart of a method for tracking personnel trajectories according to an embodiment of this application is shown;

[0020] Figure 4 A structural block diagram of a personnel trajectory tracking device provided according to an embodiment of this application is shown.

[0021] The above figures include the following reference numerals:

[0022] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0023] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] As described in the background section, the prior art suffers from inaccurate positioning of indoor personnel. To address this issue, embodiments of this application provide a method, a tracking device, and a tracking system for tracking personnel trajectories.

[0027] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0028] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of tracking personnel trajectories according to an embodiment of the present invention. For example... Figure 1 As shown, a mobile terminal may include one or more ( Figure 1Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0029] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the personnel trajectory tracking method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and 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 memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] This embodiment provides a method for tracking the trajectory of personnel running on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] Figure 2 This is a flowchart of a personnel trajectory tracking method according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0032] Step S201: Obtain multiple image information and multiple parameter information of multiple pre-shooting devices within a predetermined space. The parameter information refers to the information of multiple parameters of the pre-shooting devices.

[0033] Specifically, the aforementioned predetermined space includes indoor space; however, outdoor space can also be selected, depending on the actual situation. Furthermore, the aforementioned parameter information includes internal parameters and distortion parameters.

[0034] Step S202: Based on the above parameter information and the above image information, determine the predetermined coordinate information of the person in each of the above image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the above image information.

[0035] Specifically, the aforementioned three-dimensional coordinate information refers to the coordinate information in the three-dimensional space after three-dimensional modeling of the aforementioned predetermined space.

[0036] Step S203: Obtain the identity information corresponding to the personnel in each of the above image information;

[0037] Specifically, the aforementioned identity information includes information that can represent a person's identity, such as name, employee number, or ID card number.

[0038] Step S204: Based on the predetermined coordinate information and the identity information, determine the target shooting device group among the multiple shooting devices. The target shooting device group is the shooting device without faults among the multiple prepared shooting devices.

[0039] Specifically, the aforementioned faults include the condition of inaccurate positioning information. Of course, other conditions can also be used as the standard for fault detection, depending on the actual situation.

[0040] Step S205: Determine the predetermined coordinate information corresponding to the personnel in the target shooting equipment group as the target coordinate information.

[0041] Specifically, the aforementioned target coordinate information was determined based on the target imaging equipment group, which had not experienced any abnormalities and had accurate positioning.

[0042] In the aforementioned method for tracking personnel trajectories, firstly, multiple image information and multiple parameter information from multiple pre-capture devices within a predetermined space are acquired, wherein the parameter information refers to various parameters of the pre-capture devices; then, based on the parameter information and the image information, predetermined coordinate information of the personnel in each of the image information is determined, wherein the predetermined coordinate information is the three-dimensional coordinate information of the personnel in the image information; subsequently, identity information corresponding to the personnel in each of the image information is acquired to identify the personnel in the image information; then, based on the predetermined coordinate information and the identity information, a target capture device group among the multiple capture devices is determined, wherein the target capture device group consists of capture devices without malfunctions among the multiple pre-capture devices; finally, the predetermined coordinate information corresponding to the personnel in the target capture device group is determined as the target coordinate information. Compared to the problem of inaccurate indoor personnel positioning in existing technologies, the personnel trajectory tracking method of this application first acquires the parameter information and image information of multiple pre-capture devices within the predetermined space, enabling the determination of the predetermined coordinate information of the personnel in the image information in three-dimensional space. Then, through the identity information and the predetermined coordinate information, the target capture device group is determined, ensuring that the devices in the target capture device group are not faulty. This ensures a high degree of accuracy in the target coordinate information determined by the target capture device group, and guarantees a high degree of accuracy in tracking the personnel trajectory within the predetermined space, thus solving the problem of inaccurate indoor personnel positioning in existing technologies.

[0043] In the above implementation process, the predetermined space can be an indoor space. For example, in the case of a coal preparation plant workshop, firstly, multiple cameras are installed in the workshop so that the viewing angle corresponding to the installation position of the cameras covers the space where people are active in the workshop. If a single camera cannot cover all the viewing angles in a single workshop, multiple cameras are installed. Then, a three-dimensional model is established to model a single predetermined space. After the cameras are installed in a single predetermined space, each camera has a definite position in the actual physical space of the predetermined space. Based on the physical space information of the cameras, the camera is mapped into a virtual three-dimensional model, and the viewing angle corresponding to each camera is virtually displayed in the three-dimensional model to obtain a correspondence between the viewing angle and the spatial information.

[0044] To further ensure the accuracy of tracking the aforementioned personnel trajectories, step S201 can be implemented through the following steps: Step S2011, acquisition step, acquiring the intrinsic parameters and distortion parameters of the aforementioned pre-capture device; Step S2012, calibration step, using the aforementioned intrinsic parameters to calibrate the aforementioned distortion parameters to obtain new distortion parameters; Step S2013, first determination step, determining new intrinsic parameters based on the new aforementioned distortion parameters; Step S2014, looping step, repeatedly executing the aforementioned calibration step and the aforementioned first determination step until the values ​​of the new aforementioned distortion parameters and the new aforementioned intrinsic parameters converge; Step S2015, second determination step, determining the converged aforementioned new intrinsic parameters as target intrinsic parameters, determining the converged aforementioned new distortion parameters as target distortion parameters, the aforementioned target intrinsic parameters and the aforementioned target distortion parameters constitute the aforementioned parameter information. By first acquiring the intrinsic parameters and distortion parameters of the aforementioned pre-shooting device, and then repeatedly executing the aforementioned calibration steps and the aforementioned first determination steps, new distortion parameters and new intrinsic parameters can be calibrated and determined repeatedly until the new distortion parameters and new intrinsic parameters converge. This ensures that the accuracy of the target intrinsic parameters and target distortion parameters determined according to the aforementioned second determination steps is high, and the accuracy of the target coordinate information determined according to the aforementioned target intrinsic parameters and target distortion parameters is high, further ensuring the high accuracy of tracking the trajectory of the aforementioned personnel within the aforementioned predetermined space.

[0045] In the above implementation process, a linear calibration method for a nonlinear model camera is adopted. By calculating the above image information, the target intrinsic parameters and the target distortion coefficients of the shooting device are obtained. The process of obtaining the target intrinsic parameters and the target distortion coefficients includes: First, using the equation system of the ideal pinhole model, the values ​​of the intrinsic parameters are obtained. Then, the distortion coefficients are calibrated using the intrinsic parameters. Next, the new intrinsic parameters are recalculated using the new distortion coefficients. The new distortion coefficients are obtained using the latest obtained intrinsic parameters. Finally, the above steps are repeated until the values ​​of the new intrinsic parameters and the new distortion coefficients converge. The calculation ends, and the new intrinsic parameters and the new distortion coefficients are output to obtain the target intrinsic parameters and the target distortion parameters. For any point P in three-dimensional space, the corresponding image point p is marked in the image captured by the aforementioned shooting device. The extrinsic parameters are obtained through the projection relationship between the artificially set marker point and its feature point using the aforementioned target intrinsic parameters. Each pixel captured in the view of the aforementioned shooting device corresponds to a positional information in the three-dimensional model. The three-dimensional model is then meshed, where the mesh is a three-dimensional model that contains not only planar information but also height information. After meshing, each pixel in each frame of the image acquired by the aforementioned shooting device corresponds to the corresponding mesh in the three-dimensional model. (Since the conversion from the aforementioned shooting device coordinate system to the image coordinate system is a perspective projection, and perspective projection is a one-to-many relationship, that is, any point on the perspective line corresponds to point p; therefore, if the pixel position of point p in the image is known, it can only be determined that the real three-dimensional space point P is located at a certain position on the ray, but the three-dimensional coordinates of the real space point cannot be obtained; to achieve the conversion from the pixel coordinate system to the boundary coordinate system, the aforementioned target intrinsic parameters and extrinsic parameters of the camera are required.)

[0046] In specific implementation, step S203 can be achieved through the following steps: Step S2031, using facial recognition technology, the identity information of the persons in each of the aforementioned image information is determined. Determining the identity information of the persons in the aforementioned image information using facial recognition technology further ensures that there are no faults in the target equipment group determined based on the identity information and the predetermined coordinate information, further ensures the high accuracy of the target coordinate information determined based on the target shooting equipment group, and further ensures the high accuracy of tracking the trajectory of the persons within the predetermined space.

[0047] Specifically, experiments were conducted on personnel detection and tracking using the YOLOv5 algorithm and the DeepSORT multi-object tracking algorithm. DeepSORT is a multi-object tracking algorithm based on object detection, and the quality of the object detection algorithm affects the tracking effect of the algorithm. The Eigenface algorithm was used to identify and verify individual faces. EigenFace is a statistical feature-based method that treats face images as random vectors and uses statistical methods to identify different face feature patterns. The basic idea of ​​EigenFace is to find the basic elements of the face image distribution from a statistical point of view, that is, the feature vectors of the covariance matrix of the face image sample set, and use this to approximate the face image. These feature vectors are called feature faces. The basic process is as follows: the above-mentioned shooting device processes the acquired images. The processing is divided into two parts. The first part is face recognition to determine the above-mentioned identity information of the person. The second part is human body detection, which is to determine the position of the human feet in the view of the above-mentioned shooting device. After image processing, through coordinate transformation, the above-mentioned identity information of the person and the coordinate information of the person in three-dimensional space are obtained.

[0048] To further ensure high accuracy in tracking the aforementioned personnel trajectories, step S204 can be implemented through the following steps: Step S2041, acquiring all the predetermined coordinate information corresponding to the same identity information in multiple images at the same time; Step S2042, when multiple predetermined coordinate information exist and the difference between the multiple predetermined coordinate information is within a predetermined range, determining that the multiple shooting devices corresponding to the multiple images form the target shooting device group; Step S2043, when multiple predetermined coordinate information exist and the difference between the multiple predetermined coordinate information is not within the predetermined range, determining the deviation coefficients corresponding to the multiple shooting devices, and determining the target shooting device group based on the multiple deviation coefficients. The deviation coefficients are used to characterize the tracking differences of the personnel trajectories of the multiple shooting devices within the predetermined space, and the deviation coefficients are proportional to the differences of the multiple shooting devices. By acquiring all the predetermined coordinate information corresponding to the same identity information from multiple images taken at the same time, and if the difference between the multiple predetermined coordinate information is within the predetermined range, it indicates that the difference between the multiple predetermined coordinate information determined from the multiple images taken by the multiple shooting devices is small, further ensuring the high accuracy of the multiple three-dimensional coordinates determined from the multiple images. Conversely, if the difference between the multiple predetermined coordinate information is not within the predetermined range, it indicates that the difference between the multiple predetermined coordinate information determined from the multiple images taken by the multiple shooting devices is large, suggesting the presence of a faulty device among the multiple shooting devices. By determining the deviation coefficient corresponding to each shooting device, and then determining the target shooting device group through each deviation coefficient, it is ensured that there are no faulty devices in the target shooting device group, further ensuring the high accuracy of the target coordinate information determined from the target shooting device group, and further ensuring the high accuracy of tracking the trajectory of the person within the predetermined space.

[0049] In the above implementation process, the image information corresponding to multiple shooting devices is collected and then selected and screened. The information of all shooting devices is summarized, and the summarized information is analyzed: if the identity information of the same person is identified at the same time in the same predetermined space, and if the identity information of the same person is in the same spatial location, that is, the difference between multiple predetermined coordinate information is within the predetermined range, then the identity recognition result is determined to meet the requirements; if the identity information of the same person is not in the same spatial location, that is, the difference between multiple predetermined coordinate information is not within the predetermined range, then the identity recognition result is determined to not meet the requirements.

[0050] To further ensure the accuracy of tracking the aforementioned personnel trajectories, step S2043 can be implemented through the following steps: if the deviation coefficient is within a predetermined range, determine that the camera corresponding to the deviation coefficient is not malfunctioning; if the deviation coefficient is not within the predetermined range, determine that the camera corresponding to the deviation coefficient is malfunctioning; determine that the malfunctioning camera devices form the target camera device group. By determining whether the deviation coefficient is within the predetermined range, and determining that the camera corresponding to the deviation coefficient is not malfunctioning when the deviation coefficient is within the predetermined range, and conversely, determining that the camera corresponding to the deviating camera is malfunctioning when the deviation coefficient is not within the predetermined range, it is further ensured that the devices in the determined target camera device group are not malfunctioning. This further ensures the accuracy of the target coordinate information determined based on the target camera device group, and further ensures the accuracy of tracking the aforementioned personnel trajectories within the predetermined space.

[0051] Specifically, to ensure accurate positioning of the shooting equipment within the predetermined space, periodic calibration and analysis of the equipment are required. A detection cycle is set, and the shooting equipment within the predetermined space is designated as detection object i, where i = 1, 2, ..., n, and n is a positive integer. Within the detection cycle, detection object i is precisely detected. When the identity recognition result fails to meet requirements, the spatial position obtained by detection object i is designated as location i. The horizontal, vertical, and axial coordinates of location i in the 3D model are designated as Xi, Yi, and Zi, respectively. A horizontal set is established for all horizontal coordinate values ​​of location i in the 3D model, and a horizontal set is established for all vertical coordinate values ​​of location i in the 3D model. A vertical set is established by setting the vertical coordinate values ​​of all positioning i in the 3D model. Variance calculations are performed on the horizontal set, vertical set, and vertical set to obtain the horizontal deviation value HP, the vertical deviation value ZP, and the vertical deviation value SP. The deviation coefficient PL in the workshop is obtained by the formula PL = a1*HP + a2*ZP + a3*SP. The deviation coefficient is a value that reflects the concentration of the acquisition positions of multiple shooting devices in the predetermined space. The smaller the value of the deviation coefficient, the higher the concentration of the acquisition positions of multiple shooting devices in the predetermined space. Among them, a1, a2, and a3 are proportional coefficients, and a1 > a2 > a3 > 1.

[0052] Specifically, the above formulas are all derived from software simulations using a large amount of data, and are selected to be close to the true values. The coefficients in the formulas are set by relevant technical personnel according to the actual situation. For example, the formula PL = a1*HP + a2*ZP + a3*SP involves collecting multiple sets of sample data and setting corresponding deviation coefficients for each set. Substituting the set deviation coefficients and the collected sample data into the formulas, any three formulas form a system of three linear equations. The calculated coefficients are then filtered and averaged to obtain the specific values ​​of a1, a2, and a3. The magnitude of the coefficients is to quantify each parameter into a specific numerical value for easy comparison later. The magnitude of the coefficients depends on the amount of sample data and the initial deviation coefficients set by relevant personnel for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantified value, it is acceptable. For example, the deviation coefficient is proportional to the value of the horizontal deviation.

[0053] In some embodiments, after determining that the shooting device corresponding to the deviation coefficient has malfunctioned, the method further includes the following step: Step S206, if the deviation coefficient is greater than a predetermined value, determining that multiple shooting devices in the predetermined space have experienced a group malfunction, where the predetermined value is greater than the maximum value of the predetermined interval; if the deviation coefficient is not greater than the predetermined value, determining that multiple shooting devices in the predetermined space have experienced a single malfunction. By determining whether the deviation coefficient of the multiple shooting devices is greater than the predetermined value, it is determined whether multiple shooting devices in the predetermined space have experienced a group malfunction. Furthermore, if the deviation coefficient is greater than the predetermined value, it is determined that the devices in the predetermined space have experienced a group malfunction; conversely, if a single malfunction occurs, it ensures that the type of malfunction can be determined based on the deviation coefficient.

[0054] In the above implementation process, if the predetermined value is greater than the maximum value of the predetermined space, that is, if the deviation coefficient is small (within the predetermined interval), multiple shooting devices do not malfunction; if the deviation coefficient is large (not within the predetermined interval), the shooting devices malfunction. In the case of malfunction, there are two scenarios: First, if the deviation coefficient is greater than the maximum value of the predetermined interval (i.e., the deviation coefficient is greater than the predetermined value), then multiple shooting devices experience a group malfunction; second, if the deviation coefficient is not greater than the predetermined value, but is not within the predetermined interval (i.e., the deviation coefficient exceeds the predetermined interval but is not greater than the predetermined value), then some of the multiple shooting devices experience a single malfunction. Specifically, the specific values ​​of the predetermined interval and the predetermined value are determined based on the actual situation and are not limited here.

[0055] Of course, instead of judging whether the above-mentioned shooting equipment has malfunctioned, the process of whether the above-mentioned deviation coefficient is within the above-mentioned predetermined range can be skipped, and the process of directly judging whether the above-mentioned deviation coefficient is greater than the above-mentioned predetermined value can be used to judge the type of malfunction, that is, to judge whether it is the above-mentioned group malfunction or the above-mentioned single malfunction. The shooting equipment can be repaired according to different situations, and then all the above-mentioned shooting equipment after repair can be regarded as the above-mentioned target shooting equipment group.

[0056] In the specific implementation process, after determining that multiple shooting devices in the predetermined space have experienced a group failure, the method further includes the following steps: Step S208, obtaining the time interval between two consecutive group failures to obtain a first duration; Step S209, if the first duration is greater than a predetermined duration, sending a first message to a first terminal device, the first message indicating that the repair result of the group failure is qualified; Step S210, if the first duration is not greater than the predetermined duration, sending a second message to the first terminal device, the second message indicating that the repair result of the group failure is unqualified. By obtaining the first duration by obtaining the time interval between two group failures, it is possible to determine whether the repair structure of the group failure is qualified based on whether the first duration is greater than the predetermined duration. Furthermore, if the group failure is successfully repaired, the first message is sent; otherwise, the second message is sent. This allows the first terminal device to determine whether the repair result of the group failure is qualified based on the different information received.

[0057] In some embodiments, after determining that a single fault has occurred in multiple of the aforementioned shooting devices in the predetermined space, the method further includes the following step: Step S211, sending the serial number information of the shooting device corresponding to the single fault to a second terminal device. By sending the serial number information of the shooting device corresponding to the single fault to the second terminal device, staff can repair the shooting device corresponding to the single fault based on the received serial number information.

[0058] In the above implementation process, the deviation coefficient PL is compared with the preset predetermined value PLmax: if the deviation coefficient PL is not greater than the preset value PLmax, the fault type of the shooting equipment in the predetermined space is determined to be a single fault, the number of detection objects with the same positioning i is marked as standard objects, the detection objects with different positioning i from the standard objects are marked as fault objects, and the equipment serial number of the fault object is sent to the mobile terminal of the administrator; if the deviation coefficient PLmax is greater than the preset value, the fault type of the shooting equipment in the predetermined space is determined to be a group fault, and the third information corresponding to the group fault is sent to the mobile terminal of the administrator; if the fault type of group fault occurs continuously, the time difference of the continuous occurrence of the fault type of group fault is obtained and marked as the interval duration, and the interval duration is compared with the preset value. The above-mentioned predetermined time intervals are compared: if the interval is not greater than the predetermined time interval, the maintenance result of the group fault is deemed unqualified, and a maintenance failure signal is sent to the mobile terminal of the management personnel, i.e., the second information is issued; if the interval is greater than the predetermined time interval, the maintenance result of the group fault is deemed qualified, and a maintenance qualification signal is sent to the mobile terminal of the management personnel, i.e., the first information is issued; the above-mentioned shooting equipment is regularly subjected to precise positioning analysis, and the identification results of the above-mentioned shooting equipment within the above-mentioned predetermined space can be periodically verified. When the identification results do not meet the requirements, the fault type of the above-mentioned shooting equipment is marked, which shortens the maintenance time of the above-mentioned shooting equipment, improves the maintenance efficiency of the camera, and continuously optimizes the positioning accuracy. At the same time, the maintenance results of the above-mentioned shooting equipment are monitored, and it is convenient to hold the maintenance personnel accountable when the maintenance results are unqualified.

[0059] Furthermore, according to a predetermined cycle, the personnel positioning points and personnel information generated by the camera images are recorded periodically. Through the accumulation of time and the periodic recording of points, a complete trajectory is ultimately formed. Compared with the existing personnel trajectory tracking methods that use navigation satellites as carriers, the personnel trajectory tracking method described in this application has the advantage of being applicable to both indoor and outdoor scenes. At the same time, based on video as the data core, the algorithm simplifies the number of hardware devices used in the technical method, highlighting the convenience and deployability of the technical method. The combination of the above-mentioned shooting equipment and corresponding algorithms gives the accuracy of personnel trajectory tracking a three-dimensional advantage. In addition, the method of using a gridded three-dimensional model is more conducive to the collection and processing of personnel positioning information in indoor scenes, which has a significant advantage in improving personnel positioning accuracy. For example, in the personnel trajectory tracking method in the indoor coal preparation plant, the captured images and facial information of the face recognition platform are obtained through SDK (Software Development Kit) interface. First, the personnel's identity is identified, and then information recognition is performed based on the camera and spatial location mapping information.

[0060] Specifically, compared to personnel trajectory tracking methods using navigation satellites, the personnel trajectory tracking method described in this application has the advantage of being applicable to both indoor and outdoor scenarios. Furthermore, based on video as the core data source, the algorithm simplifies the number of hardware devices required, highlighting the convenience and deployability of the method. The combination of camera units and algorithms provides a three-dimensional advantage in personnel trajectory tracking accuracy. The method's use of meshing the 3D model further facilitates the collection and processing of personnel positioning information in indoor scenarios, significantly improving positioning accuracy. This application also involves periodically analyzing camera positioning accuracy, periodically verifying camera identification results within the workshop, and marking camera fault types when results are unsatisfactory. This shortens camera maintenance time, improves maintenance efficiency, and continuously optimizes positioning accuracy. Simultaneously, monitoring camera maintenance results facilitates accountability for maintenance personnel when results are unsatisfactory.

[0061] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the personnel trajectory tracking method of this application will be described in detail below with reference to specific embodiments.

[0062] This embodiment relates to a specific method for tracking personnel trajectories, such as... Figure 3 As shown, it includes the following steps:

[0063] Step S1: Acquire multiple image information and multiple parameter information of multiple pre-capture devices within a predetermined space. The parameter information includes target intrinsic parameters and target distortion parameters.

[0064] Step S2: Based on the above parameter information and the above image information, determine the predetermined coordinate information of the person in each of the above image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the above image information.

[0065] Step S3: Using facial recognition technology, determine the identity information of the individuals in the aforementioned image information;

[0066] Step S4: Obtain all the predetermined coordinate information corresponding to the same identity information in multiple images at the same time.

[0067] Step S5: If there are multiple predetermined coordinate information and the difference between the multiple predetermined coordinate information is within a predetermined range, determine that the multiple shooting devices corresponding to the multiple image information form the target shooting device group.

[0068] Step S6: When there are multiple predetermined coordinate information and the difference between the multiple predetermined coordinate information is not within the predetermined range, determine the deviation coefficient corresponding to each of the above-mentioned shooting devices.

[0069] Step S7: If the deviation coefficient is within a predetermined range, determine that the shooting device corresponding to the deviation coefficient has not malfunctioned.

[0070] Step S8: Determine that the aforementioned shooting devices that have not malfunctioned constitute the aforementioned target shooting device group;

[0071] Step S9: If the deviation coefficient is not within the predetermined range, determine that the shooting device corresponding to the deviation coefficient has malfunctioned.

[0072] Step S10: If the deviation coefficient is greater than a predetermined value, it is determined that multiple shooting devices in the predetermined space have experienced a group failure.

[0073] Step S11: Obtain the time interval between two consecutive group failures mentioned above to obtain the first duration;

[0074] Step S12: If the first duration is longer than the predetermined duration, send the first information to the first terminal device. The first information is used to indicate that the repair result of the group fault is qualified.

[0075] Step S13: If the first duration is not greater than the predetermined duration, send a second message to the first terminal device. The second message is used to indicate that the repair result of the group fault is unqualified.

[0076] Step S14: If the deviation coefficient is not greater than the predetermined value, determine that a single fault has occurred in one of the multiple shooting devices in the predetermined space.

[0077] Step S15: Send the serial number information of the shooting device corresponding to the single fault to the second terminal device.

[0078] This application also provides a personnel trajectory tracking device. It should be noted that the personnel trajectory tracking device of this application can be used to execute the personnel trajectory tracking method provided in this application.

[0079] This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0080] The personnel trajectory tracking device provided in the embodiments of this application will be described below.

[0081] Figure 4 This is a schematic diagram of a personnel trajectory tracking device according to an embodiment of this application. Figure 4 As shown, the device includes a first acquisition unit 10, a first determination unit 20, a second acquisition unit 30, a second determination unit 40, and a third determination unit 50, wherein,

[0082] The first acquisition unit 10 is used to acquire multiple image information and multiple parameter information of multiple pre-shooting devices within a predetermined space, wherein the parameter information is information of multiple parameters of the pre-shooting devices.

[0083] Specifically, the aforementioned predetermined space includes indoor space; however, outdoor space can also be selected, depending on the actual situation. Furthermore, the aforementioned parameter information includes internal parameters and distortion parameters.

[0084] The first determining unit 20 is used to determine the predetermined coordinate information of the person in each of the above image information based on the above parameter information and the above image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the above image information.

[0085] Specifically, the aforementioned three-dimensional coordinate information refers to the coordinate information in the three-dimensional space after three-dimensional modeling of the aforementioned predetermined space.

[0086] The second acquisition unit 30 described above is used to acquire the identity information corresponding to the person in each of the above image information;

[0087] Specifically, the aforementioned identity information includes information that can represent a person's identity, such as name, employee number, or ID card number.

[0088] The second determining unit 40 is used to determine a target shooting device group among the multiple shooting devices based on the predetermined coordinate information and the identity information. The target shooting device group is a shooting device without faults among the multiple prepared shooting devices.

[0089] Specifically, the aforementioned faults include the condition of inaccurate positioning information. Of course, other conditions can also be used as the standard for fault detection, depending on the actual situation.

[0090] The third determining unit 50 is used to determine the predetermined coordinate information corresponding to the personnel in the target shooting equipment group as target coordinate information.

[0091] Specifically, the aforementioned target coordinate information was determined based on the target imaging equipment group, which had not experienced any abnormalities and had accurate positioning.

[0092] In the aforementioned personnel trajectory tracking device, the first acquisition unit acquires multiple image information and multiple parameter information of multiple pre-capture devices within a predetermined space, wherein the parameter information is information on various parameters of the pre-capture devices; the first determination unit determines the predetermined coordinate information of the personnel in each of the aforementioned image information based on the parameter information and the aforementioned image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the personnel in the aforementioned image information; the second acquisition unit acquires the identity information corresponding to the personnel in each of the aforementioned image information; the second determination unit determines the target capture device group among the multiple capture devices based on the predetermined coordinate information and the aforementioned identity information, wherein the target capture device group is the capture device without malfunction among the multiple pre-capture devices; and the third determination unit determines the predetermined coordinate information corresponding to the personnel in the target capture device group as the target coordinate information. Compared to the problem of inaccurate indoor personnel positioning in existing technologies, the personnel trajectory tracking device of this application first acquires the parameter information and image information of multiple pre-capture devices within the predetermined space, enabling the determination of the predetermined coordinate information of the personnel in the image information in three-dimensional space. Then, through the identity information and the predetermined coordinate information, the target capture device group is determined, ensuring that the devices in the target capture device group are not faulty. This ensures a high degree of accuracy in the target coordinate information determined by the target capture device group, and guarantees a high degree of accuracy in tracking the personnel trajectory within the predetermined space, thus solving the problem of inaccurate indoor personnel positioning in existing technologies.

[0093] In the above implementation process, the predetermined space can be an indoor space. For example, in the case of a coal preparation plant workshop, firstly, multiple cameras are installed in the workshop so that the viewing angle corresponding to the installation position of the cameras covers the space where people are active in the workshop. If a single camera cannot cover all the viewing angles in a single workshop, multiple cameras are installed. Then, a three-dimensional model is established to model a single predetermined space. After the cameras are installed in a single predetermined space, each camera has a definite position in the actual physical space of the predetermined space. Based on the physical space information of the cameras, the camera is mapped into a virtual three-dimensional model, and the viewing angle corresponding to each camera is virtually displayed in the three-dimensional model to obtain a correspondence between the viewing angle and the spatial information.

[0094] To further ensure high accuracy in tracking the aforementioned personnel trajectories, the first acquisition unit includes a first acquisition module, a calibration module, a first determination module, a loop module, and a second determination module. Specifically, the first acquisition module acquires the intrinsic parameters and distortion parameters of the pre-capture device in the acquisition step; the calibration module calibrates the distortion parameters using the intrinsic parameters to obtain new distortion parameters; the first determination module determines new intrinsic parameters based on the new distortion parameters in the first determination step; the loop module iterates through the calibration and first determination steps until the values ​​of the new distortion parameters and the new intrinsic parameters converge; and the second determination module determines the converged new intrinsic parameters as target intrinsic parameters and the converged new distortion parameters as target distortion parameters in the second determination step. The target intrinsic parameters and the target distortion parameters constitute the parameter information. By first acquiring the intrinsic parameters and distortion parameters of the aforementioned pre-shooting device, and then repeatedly executing the aforementioned calibration steps and the aforementioned first determination steps, new distortion parameters and new intrinsic parameters can be calibrated and determined repeatedly until the new distortion parameters and new intrinsic parameters converge. This ensures that the accuracy of the target intrinsic parameters and target distortion parameters determined according to the aforementioned second determination steps is high, and the accuracy of the target coordinate information determined according to the aforementioned target intrinsic parameters and target distortion parameters is high, further ensuring the high accuracy of tracking the trajectory of the aforementioned personnel within the aforementioned predetermined space.

[0095] In the above implementation process, a linear calibration device for a nonlinear model camera is used to calculate the target intrinsic parameters and target distortion coefficients of the shooting device by calculating the image information. The process of obtaining the target intrinsic parameters and target distortion coefficients includes: first, using the equations of an ideal pinhole model to obtain the values ​​of the intrinsic parameters; then, using the intrinsic parameters to calibrate the distortion coefficients; second, recalculating the new intrinsic parameters using the new distortion coefficients; and finally, using the latest obtained intrinsic parameters to obtain the new distortion coefficients; and finally, repeating the above steps until the values ​​of the new intrinsic parameters and the new distortion coefficients converge, at which point the calculation ends, and the new intrinsic parameters and the new distortion coefficients are output to obtain the target intrinsic parameters and the target distortion parameters. For any point P in three-dimensional space, the corresponding image point p is marked in the image captured by the aforementioned shooting device. The extrinsic parameters are obtained through the projection relationship between the artificially set marker point and its feature point using the aforementioned target intrinsic parameters. Each pixel captured in the view of the aforementioned shooting device corresponds to a positional information in the three-dimensional model. The three-dimensional model is then meshed, where the mesh is a three-dimensional model that contains not only planar information but also height information. After meshing, each pixel in each frame of the image acquired by the aforementioned shooting device corresponds to the corresponding mesh in the three-dimensional model. (Since the conversion from the aforementioned shooting device coordinate system to the image coordinate system is a perspective projection, and perspective projection is a one-to-many relationship, that is, any point on the perspective line corresponds to point p; therefore, if the pixel position of point p in the image is known, it can only be determined that the real three-dimensional space point P is located at a certain position on the ray, but the three-dimensional coordinates of the real space point cannot be obtained; to achieve the conversion from the pixel coordinate system to the boundary coordinate system, the aforementioned target intrinsic parameters and extrinsic parameters of the camera are required.)

[0096] In specific implementation, the second acquisition unit includes a third determining module, which is used to determine the identity information of the personnel in each of the aforementioned image information using facial recognition technology. Determining the identity information of the personnel in the aforementioned image information through facial recognition technology further ensures that there are no faults in the target device group determined based on the identity information and the predetermined coordinate information, further ensures the high accuracy of the target coordinate information determined based on the target shooting device group, and further ensures the high accuracy of tracking the trajectory of the personnel within the predetermined space.

[0097] Specifically, experiments were conducted on personnel detection and tracking using the YOLOv5 algorithm and the DeepSORT multi-object tracking algorithm. DeepSORT is a multi-object tracking algorithm based on object detection, and the quality of the object detection algorithm affects the tracking effect of the algorithm. The Eigenface algorithm was used to identify and verify individual faces. EigenFace is a statistical feature-based method that treats face images as random vectors and uses statistical methods to identify different face feature patterns. The basic idea of ​​EigenFace is to find the basic elements of the face image distribution from a statistical point of view, that is, the feature vectors of the covariance matrix of the face image sample set, and use this to approximate the face image. These feature vectors are called feature faces. The basic process is as follows: the above-mentioned shooting device processes the acquired images. The processing is divided into two parts. The first part is face recognition to determine the above-mentioned identity information of the person. The second part is human body detection, which is to determine the position of the human feet in the view of the above-mentioned shooting device. After image processing, through coordinate transformation, the above-mentioned identity information of the person and the coordinate information of the person in three-dimensional space are obtained.

[0098] To further ensure high accuracy in tracking the aforementioned personnel trajectories, the second determining unit includes a second acquisition module, a fourth determining module, and a fifth determining module. The second acquisition module acquires all predetermined coordinate information corresponding to the same identity information from multiple images at the same time. The fourth determining module determines that, when multiple predetermined coordinate information exists and the difference between them is within a predetermined range, the multiple shooting devices corresponding to the multiple images form the target shooting device group. The fifth determining module determines the deviation coefficients corresponding to the multiple shooting devices when multiple predetermined coordinate information exists and the difference between them is not within the predetermined range. Based on these deviation coefficients, the target shooting device group is determined. The deviation coefficients characterize the tracking differences of the personnel trajectories of the multiple shooting devices within the predetermined space, and the deviation coefficients are proportional to the differences among the multiple shooting devices. By acquiring all the predetermined coordinate information corresponding to the same identity information from multiple images taken at the same time, and if the difference between the multiple predetermined coordinate information is within the predetermined range, it indicates that the difference between the multiple predetermined coordinate information determined from the multiple images taken by the multiple shooting devices is small, further ensuring the high accuracy of the multiple three-dimensional coordinates determined from the multiple images. Conversely, if the difference between the multiple predetermined coordinate information is not within the predetermined range, it indicates that the difference between the multiple predetermined coordinate information determined from the multiple images taken by the multiple shooting devices is large, suggesting the presence of a faulty device among the multiple shooting devices. By determining the deviation coefficient corresponding to each shooting device, and then determining the target shooting device group through each deviation coefficient, it is ensured that there are no faulty devices in the target shooting device group, further ensuring the high accuracy of the target coordinate information determined from the target shooting device group, and further ensuring the high accuracy of tracking the trajectory of the person within the predetermined space.

[0099] In the above implementation process, the image information corresponding to multiple shooting devices is collected and then selected and screened. The information of all shooting devices is summarized, and the summarized information is analyzed: if the identity information of the same person is identified at the same time in the same predetermined space, and if the identity information of the same person is in the same spatial location, that is, the difference between multiple predetermined coordinate information is within the predetermined range, then the identity recognition result is determined to meet the requirements; if the identity information of the same person is not in the same spatial location, that is, the difference between multiple predetermined coordinate information is not within the predetermined range, then the identity recognition result is determined to not meet the requirements.

[0100] To further ensure high accuracy in tracking the aforementioned personnel trajectories, the fifth determining module includes a first determining submodule, a second determining submodule, and a third determining submodule. The first determining submodule determines that the camera corresponding to the deviation coefficient is not malfunctioning when the deviation coefficient is within a predetermined range. The second determining submodule determines that the camera corresponding to the deviation coefficient is malfunctioning when the deviation coefficient is not within the predetermined range. The third determining submodule determines that the malfunctioning camera devices constitute the target camera device group. By determining whether the deviation coefficient is within the predetermined range, and determining that the camera corresponding to the deviation coefficient is not malfunctioning when the deviation coefficient is within the predetermined range, and conversely determining that the camera corresponding to the deviating camera is malfunctioning when the deviation coefficient is not within the predetermined range, it is further ensured that the devices in the determined target camera device group are not malfunctioning. This further ensures high accuracy of the target coordinate information determined based on the target camera device group, and further ensures high accuracy in tracking the personnel trajectories within the predetermined space.

[0101] Specifically, to ensure accurate positioning of the shooting equipment within the predetermined space, periodic calibration and analysis of the equipment are required. A detection cycle is set, and the shooting equipment within the predetermined space is designated as detection object i, where i = 1, 2, ..., n, and n is a positive integer. Within the detection cycle, detection object i is precisely detected. When the identity recognition result fails to meet requirements, the spatial position obtained by detection object i is designated as location i. The horizontal, vertical, and axial coordinates of location i in the 3D model are designated as Xi, Yi, and Zi, respectively. A horizontal set is established for all horizontal coordinate values ​​of location i in the 3D model, and a horizontal set is established for all vertical coordinate values ​​of location i in the 3D model. A vertical set is established by setting the vertical coordinate values ​​of all positioning i in the 3D model. Variance calculations are performed on the horizontal set, vertical set, and vertical set to obtain the horizontal deviation value HP, the vertical deviation value ZP, and the vertical deviation value SP. The deviation coefficient PL in the workshop is obtained by the formula PL = a1*HP + a2*ZP + a3*SP. The deviation coefficient is a value that reflects the concentration of the acquisition positions of multiple shooting devices in the predetermined space. The smaller the value of the deviation coefficient, the higher the concentration of the acquisition positions of multiple shooting devices in the predetermined space. Among them, a1, a2, and a3 are proportional coefficients, and a1 > a2 > a3 > 1.

[0102] Specifically, the above formulas are all derived from software simulations using a large amount of data, and are selected to be close to the true values. The coefficients in the formulas are set by relevant technical personnel according to the actual situation. For example, the formula PL = a1*HP + a2*ZP + a3*SP involves collecting multiple sets of sample data and setting corresponding deviation coefficients for each set. Substituting the set deviation coefficients and the collected sample data into the formulas, any three formulas form a system of three linear equations. The calculated coefficients are then filtered and averaged to obtain the specific values ​​of a1, a2, and a3. The magnitude of the coefficients is to quantify each parameter into a specific numerical value for easy comparison later. The magnitude of the coefficients depends on the amount of sample data and the initial deviation coefficients set by relevant personnel for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantified value, it is acceptable. For example, the deviation coefficient is proportional to the value of the horizontal deviation.

[0103] In some embodiments, the above-described apparatus further includes a fourth determining unit and a fifth determining unit. The fourth determining unit is configured to, after determining that the shooting device corresponding to the deviation coefficient has malfunctioned, determine that multiple shooting devices in the predetermined space have experienced a group malfunction if the deviation coefficient is greater than a predetermined value, where the predetermined value is greater than the maximum value of the predetermined interval; and determine that multiple shooting devices in the predetermined space have experienced a single malfunction if the deviation coefficient is not greater than the predetermined value. By determining whether the deviation coefficient of the multiple shooting devices is greater than the predetermined value, it is determined whether multiple shooting devices in the predetermined space have experienced a group malfunction. If the deviation coefficient is greater than the predetermined value, it is determined that the devices in the predetermined space have experienced a group malfunction; conversely, if a single malfunction occurs, it ensures that the type of malfunction can be determined based on the deviation coefficient.

[0104] In the above implementation process, if the predetermined value is greater than the maximum value of the predetermined space, that is, if the deviation coefficient is small (within the predetermined interval), multiple shooting devices do not malfunction; if the deviation coefficient is large (not within the predetermined interval), the shooting devices malfunction. In the case of malfunction, there are two scenarios: First, if the deviation coefficient is greater than the maximum value of the predetermined interval (i.e., the deviation coefficient is greater than the predetermined value), then multiple shooting devices experience a group malfunction; second, if the deviation coefficient is not greater than the predetermined value, but is not within the predetermined interval (i.e., the deviation coefficient exceeds the predetermined interval but is not greater than the predetermined value), then some of the multiple shooting devices experience a single malfunction. Specifically, the specific values ​​of the predetermined interval and the predetermined value are determined based on the actual situation and are not limited here.

[0105] Of course, instead of judging whether the above-mentioned shooting equipment has malfunctioned, the process of whether the above-mentioned deviation coefficient is within the above-mentioned predetermined range can be skipped, and the process of directly judging whether the above-mentioned deviation coefficient is greater than the above-mentioned predetermined value can be used to judge the type of malfunction, that is, to judge whether it is the above-mentioned group malfunction or the above-mentioned single malfunction. The shooting equipment can be repaired according to different situations, and then all the above-mentioned shooting equipment after repair can be regarded as the above-mentioned target shooting equipment group.

[0106] In its specific implementation, the device further includes a third acquisition unit, a first transmission unit, and a second transmission unit. The third acquisition unit, after determining that multiple shooting devices in the predetermined space have experienced a group failure, acquires the time interval between two consecutive group failures to obtain a first duration. The first transmission unit, if the first duration exceeds a predetermined duration, transmits first information to a first terminal device, indicating that the repair result of the group failure is satisfactory. The second transmission unit, if the first duration is not greater than the predetermined duration, transmits second information to the first terminal device, indicating that the repair result of the group failure is unsatisfactory. By acquiring the first duration through the time interval between two group failures, the device can determine whether the repair structure of the group failure is satisfactory based on whether the first duration exceeds the predetermined duration. If the group failure is satisfactory, the first information is transmitted; otherwise, the second information is transmitted. This allows the device to determine whether the repair result of the group failure is satisfactory based on the different information received.

[0107] In some embodiments, the device further includes a transmitting unit, which, after determining that a single fault has occurred in one of the multiple shooting devices in the predetermined space, transmits the serial number information of the shooting device corresponding to the single fault to a second terminal device. By transmitting the serial number information of the shooting device corresponding to the single fault to the second terminal device, staff can repair the shooting device corresponding to the single fault based on the received serial number information.

[0108] In the above implementation process, the deviation coefficient PL is compared with the preset predetermined value PLmax: if the deviation coefficient PL is not greater than the preset value PLmax, the fault type of the shooting equipment in the predetermined space is determined to be a single fault, the number of detection objects with the same positioning i is marked as standard objects, the detection objects with different positioning i from the standard objects are marked as fault objects, and the equipment serial number of the fault object is sent to the mobile terminal of the administrator; if the deviation coefficient PLmax is greater than the preset value, the fault type of the shooting equipment in the predetermined space is determined to be a group fault, and the third information corresponding to the group fault is sent to the mobile terminal of the administrator; if the fault type of group fault occurs continuously, the time difference of the continuous occurrence of the fault type of group fault is obtained and marked as the interval duration, and the interval duration is compared with the preset value. The above-mentioned predetermined time intervals are compared: if the interval is not greater than the predetermined time interval, the maintenance result of the group fault is deemed unqualified, and a maintenance failure signal is sent to the mobile terminal of the management personnel, i.e., the second information is issued; if the interval is greater than the predetermined time interval, the maintenance result of the group fault is deemed qualified, and a maintenance qualification signal is sent to the mobile terminal of the management personnel, i.e., the first information is issued; the above-mentioned shooting equipment is regularly subjected to precise positioning analysis, and the identification results of the above-mentioned shooting equipment within the above-mentioned predetermined space can be periodically verified. When the identification results do not meet the requirements, the fault type of the above-mentioned shooting equipment is marked, which shortens the maintenance time of the above-mentioned shooting equipment, improves the maintenance efficiency of the camera, and continuously optimizes the positioning accuracy. At the same time, the maintenance results of the above-mentioned shooting equipment are monitored, and it is convenient to hold the maintenance personnel accountable when the maintenance results are unqualified.

[0109] Furthermore, according to a predetermined cycle, the personnel positioning points and personnel information generated by the camera images are recorded periodically. Through the accumulation of time and the periodic recording of points, a complete trajectory is ultimately formed. Compared with the personnel trajectory tracking methods based on navigation satellites in the prior art, the personnel trajectory tracking device of this application has the advantage of being applicable to both indoor and outdoor scenes. At the same time, based on video as the data core, the algorithm simplifies the number of hardware devices used in the technical method, highlighting the convenience and deployability of the technical method. The combination of the above-mentioned shooting equipment and corresponding algorithms gives the accuracy of personnel trajectory tracking a three-dimensional advantage. In addition, the method of using a gridded three-dimensional model is more conducive to the collection and processing of personnel positioning information in indoor scenes, which has a great advantage in improving personnel positioning accuracy. For example, in the personnel trajectory tracking method corresponding to the indoor environment of a coal preparation plant, the person's identity is first identified by obtaining the captured images and facial information from the face recognition platform through the SDK (Software Development Kit) interface, and then information recognition is performed based on the camera and spatial location mapping information.

[0110] Specifically, compared to personnel trajectory tracking methods using navigation satellites, the personnel trajectory tracking method described in this application has the advantage of being applicable to both indoor and outdoor scenarios. Furthermore, based on video as the core data source, the algorithm simplifies the number of hardware devices required, highlighting the convenience and deployability of the method. The combination of camera units and algorithms provides a three-dimensional advantage in personnel trajectory tracking accuracy. The method's use of meshing the 3D model further facilitates the collection and processing of personnel positioning information in indoor scenarios, significantly improving positioning accuracy. This application also involves periodically analyzing camera positioning accuracy, periodically verifying camera identification results within the workshop, and marking camera fault types when results are unsatisfactory. This shortens camera maintenance time, improves maintenance efficiency, and continuously optimizes positioning accuracy. Simultaneously, monitoring camera maintenance results facilitates accountability for maintenance personnel when results are unsatisfactory.

[0111] The aforementioned personnel trajectory tracking device includes a processor and a memory. The first acquisition unit, the first determination unit, the second acquisition unit, the second determination unit, and the third determination unit are all stored as program units in the memory. The processor executes these program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.

[0112] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and adjusting kernel parameters can address the problem of inaccurate indoor personnel positioning in existing technologies.

[0113] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0114] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the personnel trajectory tracking method.

[0115] Specifically, methods for tracking personnel movements include:

[0116] Step S201: Obtain multiple image information and multiple parameter information of multiple pre-shooting devices within a predetermined space. The parameter information refers to the information of multiple parameters of the pre-shooting devices.

[0117] Step S202: Based on the above parameter information and the above image information, determine the predetermined coordinate information of the person in each of the above image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the above image information.

[0118] Step S203: Obtain the identity information corresponding to the personnel in each of the above image information;

[0119] Step S204: Based on the predetermined coordinate information and the identity information, determine the target shooting device group among the multiple shooting devices. The target shooting device group is the shooting device without faults among the multiple prepared shooting devices.

[0120] Step S205: Determine the predetermined coordinate information corresponding to the personnel in the target shooting equipment group as the target coordinate information.

[0121] This invention provides a processor for running a program, wherein the program executes the personnel trajectory tracking method during runtime.

[0122] Specifically, methods for tracking personnel movements include:

[0123] Step S201: Obtain multiple image information and multiple parameter information of multiple pre-shooting devices within a predetermined space. The parameter information refers to the information of multiple parameters of the pre-shooting devices.

[0124] Step S202: Based on the above parameter information and the above image information, determine the predetermined coordinate information of the person in each of the above image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the above image information.

[0125] Step S203: Obtain the identity information corresponding to the personnel in each of the above image information;

[0126] Step S204: Based on the predetermined coordinate information and the identity information, determine the target shooting device group among the multiple shooting devices. The target shooting device group is the shooting device without faults among the multiple prepared shooting devices.

[0127] Step S205: Determine the predetermined coordinate information corresponding to the personnel in the target shooting equipment group as the target coordinate information.

[0128] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0129] Step S201: Obtain multiple image information and multiple parameter information of multiple pre-shooting devices within a predetermined space. The parameter information refers to the information of multiple parameters of the pre-shooting devices.

[0130] Step S202: Based on the above parameter information and the above image information, determine the predetermined coordinate information of the person in each of the above image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the above image information.

[0131] Step S203: Obtain the identity information corresponding to the personnel in each of the above image information;

[0132] Step S204: Based on the predetermined coordinate information and the identity information, determine the target shooting device group among the multiple shooting devices. The target shooting device group is the shooting device without faults among the multiple prepared shooting devices.

[0133] Step S205: Determine the predetermined coordinate information corresponding to the personnel in the target shooting equipment group as the target coordinate information.

[0134] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0135] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0136] Step S201: Obtain multiple image information and multiple parameter information of multiple pre-shooting devices within a predetermined space. The parameter information refers to the information of multiple parameters of the pre-shooting devices.

[0137] Step S202: Based on the above parameter information and the above image information, determine the predetermined coordinate information of the person in each of the above image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the above image information.

[0138] Step S203: Obtain the identity information corresponding to the personnel in each of the above image information;

[0139] Step S204: Based on the predetermined coordinate information and the identity information, determine the target shooting device group among the multiple shooting devices. The target shooting device group is the shooting device without faults among the multiple prepared shooting devices.

[0140] Step S205: Determine the predetermined coordinate information corresponding to the personnel in the target shooting equipment group as the target coordinate information.

[0141] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0142] According to another embodiment of this application, a personnel trajectory tracking system is also provided. The tracking system includes multiple imaging devices and a processor, wherein the multiple imaging devices are all located in a predetermined space, and the imaging devices are used to provide image information; the processor is used to execute any of the above-described personnel trajectory tracking methods.

[0143] The aforementioned personnel trajectory tracking system includes multiple imaging devices and a processor. The imaging devices are all located within a predetermined space and are used to provide image information. The processor is used to execute any of the aforementioned personnel trajectory tracking methods. Compared to the problem of inaccurate indoor personnel positioning in existing technologies, the personnel trajectory tracking system of this application, by first acquiring the parameter information and image information of multiple pre-embedded imaging devices within the predetermined space, can determine the predetermined coordinate information of the personnel in the image information in three-dimensional space. Then, through the identity information and the predetermined coordinate information, the target imaging device group is determined, ensuring that the devices in the target imaging device group are not faulty. This ensures high accuracy of the target coordinate information determined based on the target imaging device group, guaranteeing high accuracy in tracking the personnel trajectory within the predetermined space, and solving the problem of inaccurate indoor personnel positioning in existing technologies.

[0144] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0146] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0147] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0148] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0149] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0150] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0151] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0152] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0153] 1) In the personnel trajectory tracking method of this application, firstly, multiple image information and multiple parameter information of multiple pre-capture devices within a predetermined space are acquired, wherein the parameter information is information on various parameters of the pre-capture devices; then, based on the parameter information and the image information, predetermined coordinate information of the personnel in each of the image information is determined, wherein the predetermined coordinate information is the three-dimensional coordinate information of the personnel in the image information; subsequently, identity information corresponding to the personnel in each of the image information is acquired to identify the personnel in the image information; subsequently, based on the predetermined coordinate information and the identity information, a target capture device group among the multiple capture devices is determined, wherein the target capture device group is the capture device without malfunction among the multiple pre-capture devices; finally, the predetermined coordinate information corresponding to the personnel in the target capture device group is determined as the target coordinate information. Compared to the problem of inaccurate indoor personnel positioning in existing technologies, the personnel trajectory tracking method of this application first acquires the parameter information and image information of multiple pre-capture devices within the predetermined space, enabling the determination of the predetermined coordinate information of the personnel in the image information in three-dimensional space. Then, through the identity information and the predetermined coordinate information, the target capture device group is determined, ensuring that the devices in the target capture device group are not faulty. This ensures a high degree of accuracy in the target coordinate information determined by the target capture device group, and guarantees a high degree of accuracy in tracking the personnel trajectory within the predetermined space, thus solving the problem of inaccurate indoor personnel positioning in existing technologies.

[0154] 2) In the personnel trajectory tracking device of this application, the first acquisition unit acquires multiple image information and multiple parameter information of multiple pre-shooting devices within a predetermined space, wherein the parameter information is information on multiple parameters of the pre-shooting devices; the first determination unit determines the predetermined coordinate information of the personnel in each of the above image information based on the parameter information and the image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the personnel in the above image information; the second acquisition unit acquires the identity information corresponding to the personnel in each of the above image information; the second determination unit determines the target shooting device group among the multiple shooting devices based on the predetermined coordinate information and the identity information, wherein the target shooting device group is the shooting device without faults among the multiple pre-shooting devices; and the third determination unit determines the predetermined coordinate information corresponding to the personnel in the target shooting device group as the target coordinate information. Compared to the problem of inaccurate indoor personnel positioning in existing technologies, the personnel trajectory tracking device of this application first acquires the parameter information and image information of multiple pre-capture devices within the predetermined space, enabling the determination of the predetermined coordinate information of the personnel in the image information in three-dimensional space. Then, through the identity information and the predetermined coordinate information, the target capture device group is determined, ensuring that the devices in the target capture device group are not faulty. This ensures a high degree of accuracy in the target coordinate information determined by the target capture device group, and guarantees a high degree of accuracy in tracking the personnel trajectory within the predetermined space, thus solving the problem of inaccurate indoor personnel positioning in existing technologies.

[0155] 3) The personnel trajectory tracking system of this application includes multiple imaging devices and a processor. The multiple imaging devices are all located within a predetermined space, and the imaging devices are used to provide image information. The processor is used to execute any of the aforementioned personnel trajectory tracking methods. Compared to the problem of inaccurate indoor personnel positioning in the prior art, the personnel trajectory tracking system of this application, by first acquiring the parameter information and image information of multiple pre-imaging devices within the predetermined space, can determine the predetermined coordinate information of the personnel in the image information in three-dimensional space. Then, through the identity information and the predetermined coordinate information, the target imaging device group is determined, ensuring that the devices in the target imaging device group are not faulty. This ensures high accuracy of the target coordinate information determined based on the target imaging device group, and guarantees high accuracy in tracking the personnel trajectory within the predetermined space, thus solving the problem of inaccurate indoor personnel positioning in the prior art.

[0156] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for tracking personnel trajectories, characterized in that, The method includes: Acquire multiple image information and multiple parameter information from multiple pre-shooting devices within a predetermined space, wherein the parameter information is information on multiple parameters of the pre-shooting devices; Based on the parameter information and the image information, the predetermined coordinate information of the person in each of the image information is determined, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the image information; Obtain the identity information corresponding to the personnel in each of the aforementioned image information; Based on the predetermined coordinate information and the identity information, a target shooting device group is determined among the multiple shooting devices. The target shooting device group consists of shooting devices without malfunctions among the multiple reserve shooting devices. The predetermined coordinate information corresponding to the personnel in the target shooting equipment group is determined as the target coordinate information; Based on the predetermined coordinate information and the identity information, a target shooting device group among the multiple shooting devices is determined, including: Obtain all the predetermined coordinate information corresponding to the same identity information in multiple image information at the same time; When multiple predetermined coordinate information exists and the difference between the multiple predetermined coordinate information is within a predetermined range, the multiple shooting devices corresponding to the multiple image information are determined to form the target shooting device group; In the case where there are multiple predetermined coordinate information and the difference between the multiple predetermined coordinate information is not within the predetermined range, the deviation coefficients corresponding to the multiple shooting devices are determined, and the target shooting device group is determined based on the deviation coefficients corresponding to the multiple shooting devices. The deviation coefficient is used to characterize the tracking difference of the personnel trajectory of the multiple shooting devices in the predetermined space, and the deviation coefficient is proportional to the difference of the multiple shooting devices.

2. The method for tracking personnel trajectories according to claim 1, characterized in that, Obtain parameter information for multiple pre-reserved shooting devices within the designated space, including: The acquisition step involves acquiring the intrinsic parameters and distortion parameters of the pre-capture device; The calibration step involves using the intrinsic parameters to calibrate the distortion parameters, thereby obtaining new distortion parameters. The first determining step is to determine the new intrinsic parameters based on the new distortion parameters; The calibration step and the first determination step are executed repeatedly until the new values ​​of the distortion parameter and the new intrinsic parameter converge. The second determination step involves determining the converged new intrinsic parameter as the target intrinsic parameter and the converged new distortion parameter as the target distortion parameter. The target intrinsic parameter and the target distortion parameter constitute the parameter information.

3. The method for tracking personnel trajectories according to claim 1, characterized in that, Obtaining the identity information corresponding to the persons in each of the aforementioned image information includes: The identity information of the persons in each of the aforementioned image information is determined by facial recognition technology.

4. The method for tracking personnel trajectories according to claim 1, characterized in that, The target shooting device group is determined based on the deviation coefficients corresponding to the multiple shooting devices, including: If the deviation coefficient is within a predetermined range, it is determined that the shooting device corresponding to the deviation coefficient has not malfunctioned; If the deviation coefficient is not within the predetermined range, it is determined that the shooting device corresponding to the deviation coefficient has malfunctioned; The target imaging equipment group consists of the imaging devices that have been determined to be malfunctioning.

5. The method for tracking personnel trajectories according to claim 4, characterized in that, After determining that the shooting device corresponding to the deviation coefficient has malfunctioned, the method further includes: If the deviation coefficient is greater than a predetermined value, it is determined that multiple shooting devices in the predetermined space have experienced a group failure, and the predetermined value is greater than the maximum value of the predetermined interval; If the deviation coefficient is not greater than the predetermined value, it is determined that a single fault has occurred in one of the multiple shooting devices in the predetermined space.

6. The method for tracking personnel trajectories according to claim 5, characterized in that, After determining that a group of the shooting devices in the predetermined space has experienced a collective failure, the method further includes: The time interval between two consecutive group failures is obtained to determine the first duration. If the first duration exceeds the predetermined duration, a first message is sent to the first terminal device, and the first message is used to indicate that the repair result of the group fault is qualified. If the first duration is not greater than the predetermined duration, a second message is sent to the first terminal device, the second message being used to characterize that the repair result of the group fault is unqualified.

7. The method for tracking personnel trajectories according to claim 5, characterized in that, After determining that a single malfunction has occurred among the multiple imaging devices in the predetermined space, the method further includes: Send the serial number information of the shooting device corresponding to the single fault to the second terminal device.

8. A personnel trajectory tracking device, characterized in that, The device includes: The first acquisition unit is used to acquire multiple image information and multiple parameter information of multiple pre-shooting devices within a predetermined space, wherein the parameter information is information on multiple parameters of the pre-shooting devices. The first determining unit is configured to determine the predetermined coordinate information of the person in each of the image information based on the parameter information and the image information, wherein the predetermined coordinate information is the three-dimensional coordinate information of the person in the image information; The second acquisition unit is used to acquire the identity information corresponding to the person in each of the image information; The second determining unit is used to determine a target shooting device group among the multiple shooting devices based on the predetermined coordinate information and the identity information. The target shooting device group is a shooting device without faults among the multiple prepared shooting devices. The third determining unit is used to determine the predetermined coordinate information corresponding to the personnel in the target shooting equipment group as target coordinate information; The second determining unit includes a second acquisition module, a fourth determining module, and a fifth determining module, wherein the second acquisition module is used to acquire all the predetermined coordinate information corresponding to the same identity information in multiple image information at the same time. The fourth determining module is used to determine, when there are multiple predetermined coordinate information and the difference between the multiple predetermined coordinate information is within a predetermined range, that the multiple shooting devices corresponding to the multiple image information form the target shooting device group. The fifth determining module is used to determine the deviation coefficients corresponding to multiple shooting devices when there are multiple predetermined coordinate information and the difference between the multiple predetermined coordinate information is not within the predetermined range. Based on the deviation coefficients corresponding to the multiple shooting devices, the target shooting device group is determined. The deviation coefficient is used to characterize the tracking difference of the personnel trajectory of the multiple shooting devices in the predetermined space. The deviation coefficient is proportional to the difference of the multiple shooting devices.

9. A personnel trajectory tracking system, characterized in that, The tracking system includes: Multiple shooting devices are located within a predetermined space, and the shooting devices are used to provide image information; A processor for executing the method for tracking the trajectory of a person as described in any one of claims 1 to 7.

Images