Personnel positioning tracking method and device, computer device and storage medium

Abstract

The application relates to the technical field of personnel tracking, and discloses a personnel positioning and tracking method and device, computer equipment and a storage medium, the method comprising the following steps: identifying and positioning a target person according to input video data, and obtaining three-dimensional space position coordinates of the target person at different time points; obtaining the time when the target person is blocked by an object and the space region blocked by the object according to a sequence of the three-dimensional space position coordinates; obtaining a preset region advancing route based on the space region blocked by the object; and generating a positioning and tracking path of the target person in the space region blocked by the object according to the time when the target person is blocked by the object and the preset region advancing route. The application can predict and supplement the path of the target person in the space region blocked by the object, and solves the positioning and tracking problem of the target person when the target person is blocked by irregular objects such as buildings or equipment.

Description

Technical Field

[0001] This invention relates to the field of personnel tracking technology, and specifically to a personnel location tracking method, device, computer equipment, and storage medium. Background Technology

[0002] Safety monitoring requires accurate location information of workers. Current high-precision personnel positioning technologies include GNSS, UWB, Bluetooth, and Wi-Fi. Satellite-based positioning cannot locate personnel in indoor environments, while UWB, Bluetooth, and Wi-Fi methods require the installation of numerous positioning base stations, which imposes a significant deployment cost burden on production environments.

[0003] Currently, many production environments have deployed a large number of surveillance cameras, and the information from these cameras can be used for personnel location and motion recognition analysis. However, when surveillance cameras cannot capture workers, their location during that time period is unknown, making it difficult to assess the risks associated with their actions.

[0004] To address the problem of tracking visually recognized targets, related technologies employ filtering algorithms to predict behavior and correlate preceding and following points. This method effectively handles continuous tracking in situations where multiple people are crossing paths within the same frame, and achieves good results in personnel location tracking in scenarios with very short-term occlusion. However, in scenarios with irregular occlusion such as buildings and equipment, the manner and duration of pedestrian occlusion vary significantly, making filtering tracking algorithms prone to failure. This makes it difficult to predict target behavior and correlate preceding and following points for effective personnel location tracking. Summary of the Invention

[0005] In view of this, the present invention provides a method, apparatus, computer equipment and storage medium for personnel positioning and tracking, in order to solve the problem of difficulty in locating, tracking and identifying personnel in irregular occlusion scenarios.

[0006] In a first aspect, the present invention provides a method for locating and tracking personnel, the method comprising: identifying and locating a target person based on input video data, and obtaining the three-dimensional spatial coordinates of the target person at different time points; obtaining the time and spatial area of ​​the target person being occluded by an object based on the sequence of the three-dimensional spatial coordinates; obtaining a preset regional forward route based on the spatial area of ​​the target person being occluded by the object; and generating a location tracking path for the target person in the spatial area of ​​the object being occluded based on the time and the preset regional forward route.

[0007] This invention discloses a personnel positioning and tracking method. It identifies and locates a target person based on input video data, obtaining the target person's three-dimensional spatial coordinates at different time points. Based on the sequence of these three-dimensional spatial coordinates, it obtains the time and spatial area where the target person is occluded by an object. A preset route is obtained based on the occluded spatial area. Finally, a positioning and tracking path for the target person within the occluded spatial area is generated based on the occlusion time and the preset route. Thus, this invention can predict and supplement the path of the target person within the occluded spatial area, solving the problem of positioning and tracking when the target person is occluded by irregular objects such as buildings or equipment.

[0008] In one optional implementation, the target person is identified and located based on the input video data, and the three-dimensional spatial coordinates of the target person at different time points are obtained. This includes: determining the coordinates of the center point of the target person in each frame of the input video data using a pedestrian recognition algorithm; and converting the coordinates of the center point of the target person in each frame of the video data into three-dimensional spatial coordinates at different time points based on a spatial transformation model.

[0009] The personnel positioning and tracking method of the present invention determines the center point coordinates of the target personnel through a pedestrian recognition algorithm, and uses a spatial transformation model to convert the center point coordinates of the personnel in each frame of video into three-dimensional spatial position coordinates at different time points, thereby realizing the positioning and tracking of the target personnel based on video data. This eliminates the need to install a large number of positioning base stations in the positioning environment, thus reducing positioning costs.

[0010] In one optional implementation, obtaining the time and spatial area of ​​the target person being occluded by an object based on the sequence of the three-dimensional spatial position coordinates includes: determining whether the identification and positioning of the target person is interrupted based on the continuity of the sequence of the three-dimensional spatial position coordinates; if an interruption occurs, obtaining the time and spatial area of ​​the target person being occluded by an object based on the two three-dimensional spatial position coordinates before and after the interruption.

[0011] The personnel positioning and tracking method of the present invention determines whether the identification and positioning of the target personnel is interrupted by judging the continuity of the sequence of the three-dimensional spatial position coordinates, and obtains the time and spatial area of ​​the target personnel being occluded by the object based on the two three-dimensional spatial position coordinates before and after the interruption, which can improve the efficiency of obtaining the time and spatial area of ​​the target personnel being occluded by the object.

[0012] In one optional implementation, after an interruption occurs, the process includes: determining whether the interruption is caused by the target person being obscured by an object based on a preset area design diagram; if the interruption is caused by the target person being obscured by an object, then obtaining the time and spatial area of ​​the target person being obscured by the object based on the two three-dimensional spatial position coordinates before and after the interruption.

[0013] The personnel positioning and tracking method of the present invention determines the cause of interruption. When the cause of interruption is that the target personnel is obstructed by an object, the time and spatial area of ​​the obstruction are obtained. This avoids situations where the obtained obstructed spatial area is an unrecoverable obstruction, resulting in the inability to supplement the positioning and tracking path or the supplemented positioning and tracking path being inaccurate.

[0014] In one optional implementation, a location tracking path for the target person in the space area occluded by the object is generated based on the time the target person is occluded by the object and a preset regional travel route. This includes: determining whether the time the target person is occluded by the object is less than a preset regional duration; if it is less than the preset regional duration, then using the preset regional travel route as the location tracking path for the target person in the space area occluded by the object.

[0015] The personnel positioning and tracking method of the present invention determines whether the time when the target personnel is occluded by an object is less than the preset time of the area. When it is less than the preset time of the area, it means that the target personnel has not made any special path change. At this time, the preset area forward route is used as the positioning and tracking path of the target personnel in the spatial area occluded by the object, which can accurately predict the positioning and tracking path of the target personnel in the spatial area occluded by the object.

[0016] In one alternative implementation, the preset regional travel route includes a straight path or a fixed path based on a spatial region obscured by an object.

[0017] In spatial areas obscured by objects, there are usually fixed paths. In cases where there are no fixed paths, predictions can be made using straight-line paths to avoid unpredictable situations.

[0018] In one optional implementation, after obtaining the time and spatial region where the target person is occluded by an object based on the sequence of the three-dimensional spatial coordinates, the process includes: acquiring several supplementary video data to the input video data, wherein the supplementary video data and the input video data are respectively obtained by multiple cameras located in the same space but with different shooting angles; performing video fusion positioning on the supplementary video data and the input video data; determining whether there is a spatial region where the target person is occluded by an object after performing video fusion positioning; if there is no spatial region where the target person is occluded by an object, then outputting a fusion positioning path based on the video positioning fusion result; if there is a spatial region where the target person is occluded by an object, then obtaining a preset regional forward route based on the spatial region where the target person is occluded by the object, and generating a positioning and tracking path for the target person in the spatial region where the object is occluded based on the time the target person is occluded by the object and the preset regional forward route.

[0019] By performing video fusion positioning on video data obtained from multiple cameras, the process only proceeds to obtain a preset route for advancing through the area and generate a location tracking path for the target person in the space area obscured by objects if there are still spatial areas that are obscured after video fusion positioning. This reduces the range of spatial areas obscured by objects and improves positioning accuracy.

[0020] Secondly, the present invention provides a personnel positioning and tracking device, comprising: a coordinate acquisition module for identifying and locating a target person based on input video data, and acquiring the three-dimensional spatial coordinates of the target person at different time points; an occlusion area acquisition module for acquiring the time and spatial area of ​​the target person being occluded by an object based on the sequence of the three-dimensional spatial coordinates; a route acquisition module for acquiring a preset regional forward route based on the spatial area of ​​the target person being occluded by an object; and a path generation module for generating a positioning and tracking path for the target person in the spatial area occluded by the object based on the time of the target person being occluded by the object and the preset regional forward route.

[0021] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the personnel location tracking method of the first aspect or any corresponding embodiment described above.

[0022] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the personnel location tracking method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a personnel location tracking method according to an embodiment of the present invention;

[0025] Figure 2 This is a flowchart illustrating another personnel location tracking method according to an embodiment of the present invention;

[0026] Figure 3 This is a structural block diagram of a personnel positioning and tracking device according to an embodiment of the present invention;

[0027] Figure 4 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] The personnel positioning and tracking method of this invention is mainly applied in scenarios such as safety production monitoring where it is necessary to identify the accurate location information of workers. It uses visual methods to locate and track personnel, solving the problem that it is difficult to track personnel when they are obstructed by equipment, buildings, etc. in visual positioning.

[0030] This invention provides a method for locating and tracking personnel. 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] The personnel location tracking method provided in this embodiment of the invention can be used on a server or a mobile terminal, including mobile phones, tablets, etc. Figure 1 This is a flowchart of the personnel location tracking method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0032] Step S101: Identify and locate the target person based on the input video data, and obtain the three-dimensional spatial coordinates of the target person at different time points.

[0033] Specifically, the input video data is obtained through cameras installed in production scenarios such as factories and construction sites. The video data is composed of several discrete video frames, each with a corresponding time point, and any two adjacent frames have the same time interval. Therefore, video tracking algorithms, such as machine learning-based pedestrian recognition algorithms, are used to identify and locate target personnel in each frame of the video. This involves determining whether a target person exists in the current frame, detecting their position within the video frame, and ultimately obtaining the target person's three-dimensional spatial coordinates at different time points.

[0034] Step S102: Obtain the time and spatial area of ​​the target person being occluded by the object based on the sequence of three-dimensional spatial position coordinates.

[0035] Specifically, the sequence of three-dimensional spatial coordinates is obtained by sorting the time points of each video frame. For example, if there are 10 video frames in chronological order, the target person is detected in the first to third frames and the three-dimensional spatial coordinates are obtained in sequence 1 to 3. The target person is detected in the seventh to tenth frames and the three-dimensional spatial coordinates are obtained in sequence 7 to 10. The target person is not detected in the fourth to sixth frames. At this time, the sequence of three-dimensional spatial coordinates is 1, 2, 3, 7, 8, 9, 10, indicating that the fourth to sixth frames cannot be identified. Therefore, the time when the target person is occluded by the object can be obtained based on the time points of the fourth to sixth frames, and the area captured by the fourth to sixth frames is taken as the spatial area occluded by the object.

[0036] Step S103: Obtain a preset regional forward route based on the spatial area where the target person is obscured by objects.

[0037] Specifically, the production scenario has strict regulations regarding pedestrian space. Each area has fixed equipment, buildings, and safety regulations. Based on the actual production scenario, personnel can only move forward using fixed routes. These fixed routes are known information and can be obtained from the construction deployment diagram of the production scenario or through analysis of actual site visits. In other words, fixed routes for each spatial area are obtained through pre-analysis of the production scenario's spatial regions, and these fixed routes are used as the preset routes for moving within those areas.

[0038] Step S104: Generate a location tracking path for the target person in the spatial area where the object is occluded, based on the time the target person is occluded by the object and the preset regional forward route.

[0039] Specifically, the location tracking path of the target person in a spatial area obscured by objects is supplemented by a preset regional travel route. For unobstructed spatial areas, the corresponding walking path can be obtained by acquiring the three-dimensional spatial coordinates of the target person at different time points in step S101. The location tracking path includes the target pedestrian's walking route and the pedestrian's specific position on the walking route at each time point. The preset regional travel route is used as the predicted walking route of the target pedestrian, and the specific time and location are assumed to be the target person walking at a constant speed on the preset regional travel route. The pedestrian's forward speed is calculated by dividing the length of the preset regional travel route by the obstruction time, and then the specific location of the target person at different time points is determined based on the forward time and speed. If there are elements such as stairs, ladders, or obstacles that affect the forward speed, the forward speed can also be adjusted accordingly to obtain the specific location of the target person at different time points.

[0040] This invention provides a method for personnel positioning and tracking. It identifies and locates a target person based on input video data, obtaining the target person's three-dimensional spatial coordinates at different time points. Based on the sequence of these coordinates, it obtains the time and spatial area where the target person is occluded by an object. A preset route is then obtained based on the occluded spatial area. Finally, a tracking path is generated for the target person within the occluded spatial area based on the occlusion time and the preset route. Therefore, this invention can predict and supplement the path of a target person within the occluded spatial area, solving the problem of positioning and tracking when the target person is occluded by irregular objects such as buildings or equipment.

[0041] In some optional implementations, step S101 above includes:

[0042] Step S1011: Determine the center point coordinates of the target person in each frame of the input video data using a pedestrian recognition algorithm.

[0043] Specifically, pedestrian recognition algorithms are deep learning algorithms, including a series of algorithms such as R-CNN, Faster R-CNN, and YOLO. For example, the R-CNN algorithm is used to identify the target person in the video frame, and then the position of the target person in the video frame is obtained, that is, the coordinates of the person's center point.

[0044] Step S1012: Based on the spatial transformation model, the coordinates of the center point of the person in each frame of the video are converted into three-dimensional spatial position coordinates at different time points.

[0045] Specifically, the spatial transformation model is a computational model that transforms the coordinates of a person's center point from two-dimensional pixel coordinates to three-dimensional spatial coordinates. Specifically, it is a camera projection model. By using the spatial transformation model, the coordinates of the person's center point in each frame of video are transformed into three-dimensional spatial position coordinates at different time points, thereby obtaining the spatial position of the target person.

[0046] The personnel positioning and tracking method of this invention determines the center point coordinates of the target personnel through a pedestrian recognition algorithm and uses a spatial transformation model to convert the center point coordinates of the personnel in each frame of video into three-dimensional spatial position coordinates at different time points. This achieves the positioning and tracking of the target personnel based on video data, without the need to install a large number of positioning base stations in the positioning environment, thus reducing positioning costs.

[0047] In some alternative embodiments, step S102 includes:

[0048] Step S1021: Determine whether the identification and positioning of the target person is interrupted based on the continuity of the sequence of three-dimensional spatial position coordinates.

[0049] Specifically, the sequence of three-dimensional spatial coordinates is obtained by sorting the time points of each video frame. The judgment of interruption is as follows: There are 10 video frames in chronological order. In the first to third video frames, the target person is detected and the three-dimensional spatial coordinates of sequence 1 to 3 are obtained. In the seventh to tenth video frames, the target person is detected and the three-dimensional spatial coordinates of sequence 7 to 10 are obtained. In the fourth to sixth video frames, the target person is not detected. Therefore, the sequence of three-dimensional spatial coordinates is 1, 2, 3, 7, 8, 9, 10. At this time, the three-dimensional spatial coordinates are discontinuous, that is, the identification and positioning has been interrupted.

[0050] In step S1022, if an interruption occurs, the time and spatial area of ​​the target person being occluded by the object are obtained based on the two three-dimensional spatial coordinates before and after the interruption.

[0051] Specifically, when an interruption occurs, it indicates that the target person is obscured by an object. Based on the three-dimensional spatial coordinates before and after the interruption, it is known that no target person was detected in the 4th to 6th frames of the video. Therefore, the time when the target person was obscured by the object can be obtained based on the time points of the 4th to 6th frames of the video, and the area captured in the 4th to 6th frames of the video is taken as the spatial area obscured by the object.

[0052] The personnel positioning and tracking method of the present invention determines whether the identification and positioning of the target personnel is interrupted by judging the continuity of the sequence of three-dimensional spatial position coordinates, and obtains the time and spatial area of ​​the target personnel being occluded by the object based on the two three-dimensional spatial position coordinates before and after the interruption, which can improve the efficiency of obtaining the time and spatial area of ​​the target personnel being occluded by the object.

[0053] In some alternative implementations, after an interruption occurs in step S1022, the following steps are included:

[0054] Step a1: Determine whether the interruption is caused by the target person being obscured by an object based on the preset area design map.

[0055] Step a2: If the interruption is caused by the target person being obscured by an object, then obtain the time and spatial area of ​​the target person being obscured by the object based on the two three-dimensional spatial coordinates before and after the interruption.

[0056] Specifically, the preset area design map includes architectural and equipment deployment design maps for each area of ​​the production scene. These maps are obtained from the construction team of the production scene or constructed independently based on the actual buildings and equipment. The preset area design map marks the location of each building or piece of equipment. Based on the relationship between the building and equipment locations in the preset area design map and the camera's location, it is calculated whether the camera's shooting area is occupied by equipment, and thus whether the interruption is caused by equipment obstruction. If the interruption is not caused by equipment obstruction, it means that there is no building or equipment obstruction between the camera and the target person. In this case, it is assumed that the reason for the inability to identify the target person and the interruption in identification and positioning is due to factors such as distance and lighting. When the reason for the inability to identify is due to too little light or too far distance, the unidentifiable area is large, and the movement pattern is more difficult to predict. Therefore, the obstruction cannot be compensated for. Conversely, it can be compensated for if the light is good or the distance is sufficient.

[0057] When the interruption is caused by the target person being obscured by objects such as buildings or equipment, the unidentifiable area is small. In this case, it is necessary to obtain the time and spatial area of ​​the target person being obscured by the object to avoid the obscured spatial area being an unrecoverable obstruction, which could lead to the inability to supplement the positioning and tracking path or the supplemented positioning and tracking path being inaccurate.

[0058] In some optional implementations, step S104, generating a location tracking path for the target person in the space area occluded by the object based on the time the target person is occluded by the object and a preset regional travel route, includes:

[0059] Step S1041: Determine whether the time the target person is obscured by the object is less than the preset time for the area;

[0060] Step S1042: If the time is less than the preset time for the area, the preset route for advancing through the area will be used as the location tracking path for the target person in the space area obscured by objects.

[0061] Specifically, the preset duration for a given area is determined based on a fixed route within that area. For example, if factors such as stairs affect walking speed, the preset duration will be increased accordingly. If the time a person is obscured by an object is less than the preset duration, it indicates that the obscuration time is short, meaning the person did not linger or detour in the obscured area, and there were no unusual path changes. Therefore, by using the preset route to compensate for the time obscured, the actual walking path can be accurately supplemented.

[0062] The personnel positioning and tracking method of the present invention determines whether the time when the target personnel is occluded by an object is less than the preset time of the area. When it is less than the preset time of the area, it means that the target personnel has not made any special path change. At this time, the preset area forward route is used as the positioning and tracking path of the target personnel in the spatial area occluded by the object, which can accurately predict the positioning and tracking path of the target personnel in the spatial area occluded by the object.

[0063] In some alternative implementations, the preset area travel route in step S103 includes a straight path or a fixed path based on the spatial area occluded by the object.

[0064] Specifically, the preset regional forward route is a possible forward route obtained based on the actual road conditions of the current region. For example, if there are obstacles in the current region and only one fixed route is passable, then that fixed route can be used as the preset regional forward route. If there are multiple fixed routes in the current region, then the shortest route can be selected as the preset regional forward route, that is, the straight path of the obscured area can be used as the preset regional forward route.

[0065] In spatial areas obscured by objects, there are usually fixed paths. In cases where there are no fixed paths, predictions can be made using straight-line paths to avoid unpredictable situations.

[0066] In one alternative implementation, such as Figure 2 As shown, after obtaining the time and spatial area of ​​the target person being occluded by the object based on the sequence of three-dimensional spatial position coordinates in step S102, the process includes:

[0067] Step S201: Acquire several supplementary video data to the input video data. The supplementary video data and the input video data are obtained by multiple cameras located in the same space but at different shooting angles. Specifically, by installing multiple cameras in various areas to acquire supplementary video data, blind spots are reduced, and video data from other cameras can be used to supplement the image when one camera is obstructed.

[0068] Step S202: Perform video fusion localization on the supplementary video data and the input video data. Specifically, video fusion localization merges the localization results of the supplementary video data and the input video data, and the localization results are fused using existing video fusion localization algorithms. The localization results that fuse the supplementary video data and the input video data may not contain occluded spatial areas. For example, if three cameras are set up, the first camera collects the input video data, and the second and third cameras transmit supplementary video, with 10 frames of video footage in chronological order, the video data from the first camera detects the target person in frames 1 to 4, but not in the remaining frames; the video data from the second camera detects the target person in frames 5 to 7, but not in the remaining frames; and the video data from the third camera detects the target person in frames 8 to 10, but not in the remaining frames. The positions of the target person detected by each camera are fused to obtain the fused localization path. The localization results that combine supplementary video data and input video data may still contain occluded spatial areas. For example, all three cameras may only detect the target person in the first to seventh frames of the video, or one camera may detect the target person in the first to seventh frames of the video, while the other two cameras may detect the target person in the first to seventh, ninth, and tenth frames of the video.

[0069] Step S203: Determine if there is a spatial region where the target person is occluded by an object after video fusion localization. If no such region exists, output a fused localization path based on the video localization fusion result. If a spatial region exists where the target person is occluded, obtain a preset regional forward route based on the occluded region. Generate a localization tracking path for the target person within the occluded region based on the time of occlusion and the preset regional forward route. Specifically, check if the sequence of 3D spatial coordinates in the fused localization path is continuous. If it is discontinuous, it indicates that some video frames did not detect the target person, and the fused localization path still contains a spatial region where the target person is occluded. Conversely, if the sequence is continuous, it indicates that no such region exists. When no such region exists, videos captured by multiple cameras can compensate for the occlusions between them. In this case, outputting a fused localization path eliminates the need for route prediction, resulting in a more accurate localization result. By using video fusion localization, path supplementation is only performed in areas not captured by any camera, reducing the spatial area requiring supplementation of the preset regional forward route.

[0070] This invention utilizes video fusion positioning to combine video data captured by multiple cameras, compensating for the limited coverage of each camera. Furthermore, only when object occlusion exists in the spatial area after video fusion positioning is the process of obtaining a preset regional travel route and generating a location tracking path for the target person within the occluded area performed. This reduces the extent of the occluded spatial area and, when multiple cameras cover the positioning space, minimizes the range of the location tracking path generated using the preset regional travel route, thereby improving positioning accuracy.

[0071] This invention also provides a personnel location tracking device for implementing the above embodiments and preferred embodiments, which will not be repeated hereafter. 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. The personnel location tracking device in this invention is presented in the form of a functional unit, where a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0072] This invention provides a personnel positioning and tracking device, such as... Figure 3 As shown, the device includes:

[0073] The coordinate acquisition module 301 is used to identify and locate the target person based on the input video data, and to obtain the three-dimensional spatial coordinates of the target person at different time points;

[0074] The occlusion area acquisition module 302 is used to acquire the time and spatial area of ​​the target person being occluded by the object based on the sequence of three-dimensional spatial position coordinates.

[0075] Route acquisition module 303 is used to acquire a preset route for moving forward in a region based on the spatial area where the target person is occluded by an object;

[0076] The path generation module 304 is used to generate a positioning and tracking path for the target person in the spatial area occluded by the object based on the time the target person is occluded by the object and the preset regional forward route.

[0077] This invention provides a personnel positioning and tracking device that identifies and locates a target person based on input video data, obtaining the target person's three-dimensional spatial coordinates at different time points; obtains the time and spatial area where the target person is occluded by an object based on the sequence of the three-dimensional spatial coordinates; obtains a preset regional travel route based on the spatial area where the target person is occluded; and generates a positioning and tracking path for the target person in the spatial area where the object is occluded based on the time of occlusion and the preset regional travel route. Thus, this invention can predict and supplement the path of the target person in the spatial area where the object is occluded, solving the problem of positioning and tracking when the target person is occluded by irregular objects such as buildings or equipment.

[0078] In some optional implementations, the coordinate acquisition module 301 includes:

[0079] The personnel center point coordinate acquisition unit is used to determine the personnel center point coordinates of the target personnel in each frame of the input video data through a pedestrian recognition algorithm;

[0080] The three-dimensional spatial position coordinate acquisition unit is used to convert the coordinates of the center point of the person in each frame of video into three-dimensional spatial position coordinates at different time points based on the spatial transformation model.

[0081] In some optional implementations, the occlusion area acquisition module 302 includes:

[0082] The terminal identification unit is used to determine whether the identification and positioning of the target person is interrupted based on the continuity of the sequence of three-dimensional spatial position coordinates.

[0083] The occlusion acquisition unit is used to obtain the time and spatial area of ​​the target person being occluded by the object based on the two three-dimensional spatial coordinates before and after the interruption if an interruption occurs.

[0084] In some optional implementations, the occlusion acquisition unit includes:

[0085] The type judgment subunit is used to determine whether the interruption is caused by the target person being obscured by an object, based on the preset area design drawing.

[0086] The occlusion extraction subunit is used to obtain the time and spatial area of ​​the target person being occluded by the object based on the two three-dimensional spatial coordinates before and after the interruption if the interruption is caused by the target person being occluded by an object.

[0087] In some alternative implementations, the path generation module 303 includes:

[0088] The duration judgment unit is used to determine whether the time a target person is occluded by an object is less than the preset duration for the area.

[0089] The positioning and tracking path generation unit is used to take the preset regional forward route as the positioning and tracking path of the target person in the spatial area occluded by the object if the time is less than the preset time of the region.

[0090] In some alternative implementations, the preset regional travel route includes a straight path or a fixed path based on a spatial region occluded by an object.

[0091] In some alternative implementations, the personnel location and tracking device further includes:

[0092] A multi-camera video input unit is used to acquire several supplementary video data to the input video data, wherein the supplementary video data and the input video data are respectively acquired by multiple cameras located in the same space but with different shooting angles;

[0093] The fusion positioning unit is used to perform video fusion positioning by combining supplementary video data and input video data;

[0094] The path supplement unit is used to determine whether there is a spatial area where the target person is occluded by an object after video fusion localization. If there is no spatial area where the target person is occluded by an object, the fusion localization path is output based on the video localization fusion result. If there is a spatial area where the target person is occluded by an object, a preset regional forward route is obtained based on the spatial area where the target person is occluded by the object. The localization and tracking path of the target person in the spatial area where the object is occluded is generated based on the time when the target person is occluded by the object and the preset regional forward route.

[0095] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0096] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 Take a processor 10 as an example.

[0097] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0098] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0099] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0100] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0101] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0102] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0103] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for locating and tracking personnel, characterized in that, The method includes: Based on the input video data, the target person is identified and located, and the three-dimensional spatial coordinates of the target person at different time points are obtained. The time and spatial area of ​​the target person being occluded by the object are obtained based on the sequence of the three-dimensional spatial position coordinates. Obtain a preset route for advancing within the area where the target person is obscured by objects. Based on the time the target person is obscured by an object and the preset regional forward route, a location tracking path for the target person is generated in the spatial area obscured by the object. Based on the sequence of the three-dimensional spatial coordinates, the time and spatial area of ​​the target person being occluded by the object are obtained, including: The continuity of the sequence of three-dimensional spatial position coordinates is used to determine whether the identification and positioning of the target person is interrupted; If an interruption occurs, the time and spatial area of ​​the target person being occluded by the object are obtained based on the two three-dimensional spatial position coordinates before and after the interruption. After an interruption occurs, including: Based on the preset area design map, determine whether the interruption is caused by the target person being obstructed by an object; If the interruption is caused by the target person being obscured by an object, then the time and spatial area of ​​the target person being obscured by the object are obtained based on the two three-dimensional spatial position coordinates before and after the interruption. Based on the time the target person is obscured by an object and a preset regional travel route, a location tracking path for the target person is generated within the spatial area obscured by the object, including: Determine whether the time the target person is obscured by an object is less than the preset time for the area; If the time is less than the preset time for the area, the preset route for moving forward in the area will be used as the location tracking path for the target person in the space area obscured by objects.

2. The method according to claim 1, characterized in that, Based on the input video data, the target person is identified and located, and the three-dimensional spatial coordinates of the target person at different time points are obtained, including: The center point coordinates of the target person in each frame of the input video data are determined by a pedestrian recognition algorithm. Based on the spatial transformation model, the coordinates of the center point of the person in each frame of the video are converted into three-dimensional spatial position coordinates at different time points.

3. The method according to claim 1, characterized in that, The preset regional travel route includes a straight path or a fixed path based on a spatial region obscured by an object.

4. The method according to claim 1, characterized in that, After obtaining the time and spatial area of ​​the target person being occluded by the object based on the sequence of the three-dimensional spatial coordinates, the process includes: Acquire several supplementary video data to the input video data, wherein the supplementary video data and the input video data are respectively obtained by multiple cameras located in the same space but with different shooting angles; Perform video fusion positioning on the supplementary video data and the input video data; After video fusion localization, determine whether there is a spatial area where the target person is occluded by an object. If there is no spatial area where the target person is occluded by an object, output the fused localization path based on the video localization fusion result. If there is a spatial area where the target person is occluded by an object, obtain a preset regional forward route based on the spatial area where the target person is occluded by the object, and generate the localization tracking path of the target person in the spatial area where the object is occluded based on the time the target person is occluded by the object and the preset regional forward route.

5. A personnel positioning and tracking device, characterized in that, The device includes: The coordinate acquisition module is used to identify and locate target personnel based on the input video data, and to obtain the three-dimensional spatial coordinates of the target personnel at different time points; The occlusion area acquisition module is used to acquire the time and spatial area of ​​the target person being occluded by the object based on the sequence of the three-dimensional spatial position coordinates. The route acquisition module is used to obtain a preset route for the target person to move forward in a given area based on the spatial area where the target person is obscured by objects. The path generation module is used to generate a location tracking path for the target person in the spatial area occluded by the object based on the time the target person is occluded by the object and the preset regional forward route. The occlusion area acquisition module includes: The terminal identification unit is used to determine whether the identification and positioning of the target person is interrupted based on the continuity of the sequence of three-dimensional spatial position coordinates. The occlusion acquisition unit is used to obtain the time and spatial area of ​​the target person being occluded by the object based on the two three-dimensional spatial position coordinates before and after the interruption if an interruption occurs. The occlusion acquisition unit includes: The type judgment subunit is used to determine whether the interruption is caused by the target person being obscured by an object, based on the preset area design drawing. The occlusion extraction subunit is used to obtain the time and spatial area of ​​the target person being occluded by the object based on the two three-dimensional spatial coordinates before and after the interruption if the interruption is caused by the target person being occluded by an object. The path generation module includes: The duration judgment unit is used to determine whether the time a target person is occluded by an object is less than the preset duration for the area. The positioning and tracking path generation unit is used to take the preset regional forward route as the positioning and tracking path of the target person in the spatial area occluded by the object if the time is less than the preset time of the region.

6. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the personnel location and tracking method according to any one of claims 1 to 4 by executing the computer instructions.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the personnel location and tracking method according to any one of claims 1 to 4.

Images