A method and system for generating personnel trajectories in complex indoor scenes

Abstract

This invention belongs to the field of indoor positioning and provides a method and system for generating personnel trajectories in complex indoor scenes. The method includes: mapping the indoor scene to construct a complete 3D model; extracting all feasible indoor walking paths based on the 3D model to generate a complete 3D indoor path map; calibrating cameras at all key nodes indoors using visual calibration, and associating these cameras with the 3D path map as visual reference stations; identifying partial trajectories of personnel through the cameras at key nodes to generate directional indoor vector trajectory maps; and selecting the most feasible personnel movement trajectory based on the directional indoor vector trajectory map combined with the 3D indoor path map, and completing any blank trajectories to obtain a complete, seamless personnel trajectory route map. This solves the problem of discontinuous personnel trajectories and large gaps in the absence of positioning information.

Description

Technical Field

[0001] This invention belongs to the field of indoor positioning technology, specifically relating to a method and system for generating personnel trajectories in complex indoor scenarios. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Currently, the most accurate and reliable indoor positioning still relies on visual camera positioning. However, visual positioning has problems such as narrow camera field of view, limited positioning area, and discontinuous trajectory. These are defects determined by the technology itself. With the continuous development of information technology, people have an increasing demand for indoor positioning, especially in complex environments, particularly in scenarios such as indoor buildings and smart parks.

[0004] However, with the continuous application of security technology, smart buildings and smart tourism generally conduct detailed site surveys to build a complete geographic information base, which provides a good resource foundation for visual positioning information supplementation and can achieve continuous and accurate positioning in indoor buildings, parking lots and other scenarios. However, due to the problem that the camera can only capture one person's location and cannot capture outside the field of view, it is difficult to judge the real path between cameras and the trajectory is discontinuous, which makes it impossible to generate accurate and continuous trajectory of people indoors. Summary of the Invention

[0005] To address the aforementioned issues, this invention proposes a method and system for generating personnel trajectories in complex indoor scenarios. This invention solves the problems of discontinuous personnel trajectories and large gaps in the absence of location information by using preprocessed geographic information as a basis to intelligently select the most likely trajectory route of personnel and fill in the gaps in personnel trajectories.

[0006] According to some embodiments, the first solution of the present invention provides a method for generating personnel trajectories in complex indoor scenes, employing the following technical solution:

[0007] A method for generating personnel trajectories in complex indoor scenes includes:

[0008] The interior scene was surveyed and mapped to construct a complete 3D model of the interior scene;

[0009] Based on the 3D model of the indoor scene, all feasible indoor walking paths are extracted to generate a complete 3D indoor path map.

[0010] Visual calibration is used to calibrate the cameras at all key nodes in the room, and the cameras at the key nodes are used as visual reference stations and associated with the indoor three-dimensional path map.

[0011] By identifying parts of a person's trajectory through cameras at key nodes, an indoor vector trajectory map with direction is generated;

[0012] Based on the indoor vector trajectory map with direction and the indoor three-dimensional path map, the most feasible personnel movement trajectory is selected and the blank trajectory is filled in.

[0013] All completed trajectory routes are reorganized to generate a new route. The time corresponding to the inserted trajectory point is determined by multiplying the ratio of the difference between the start node time and the end node time to the total number of inserted trajectory points, and the sum of this product and the start node time. The time corresponding to the trajectory point is then added to the new route to obtain a complete and continuous personnel trajectory route map.

[0014] Furthermore, based on the 3D model of the indoor scene, all feasible indoor walking paths are extracted to generate a complete 3D indoor path map, specifically as follows:

[0015] Based on the 3D model of the indoor scene, for indoor buildings where the model has been completed, the key intersections of the indoor paths are marked as key nodes according to the floor level.

[0016] Determine whether any two key nodes are accessible to each other. If they are, record it as 1; if they are not, record it as 0. This forms a path matrix and creates an indoor 3D path map.

[0017] Furthermore, the process involves calibrating cameras at all key indoor nodes using visual calibration, and then associating these cameras as visual reference stations with the indoor 3D path map. Specifically:

[0018] The cameras at all key indoor nodes were calibrated sequentially, and the camera numbers, longitudes, latitudes, and elevations were obtained as calibration results.

[0019] Using the cameras at key nodes as visual reference stations, the camera numbers are used as the visual reference station numbers based on the calibration results, and the longitude, latitude, and elevation of the cameras are used as the longitude, latitude, and elevation of the visual reference stations, thereby constructing a visual reference station array.

[0020] Based on key nodes, the visual reference station array is correlated with the indoor 3D path map.

[0021] Furthermore, the step of identifying partial trajectories of personnel through cameras at key nodes and generating directional indoor vector trajectory maps specifically involves:

[0022] By using cameras at key nodes to acquire dynamic trajectory information of people passing through each key node, the indoor trajectory of people can be obtained. The dynamic trajectory information includes multiple trajectory points arranged in chronological order.

[0023] Based on the location information in the trajectory point information, the trajectory direction between each pair of key nodes is determined according to the time sequence, thereby generating indoor vector trajectory segments with vector representation between the nodes;

[0024] Until all key nodes in the personnel's indoor trajectory are determined, multiple discontinuous indoor vector trajectory segments with vector representation are obtained, thereby generating an indoor vector trajectory map with direction.

[0025] Furthermore, the trajectory point information includes the time, location information, personnel information, mobile phone number ID, and device information for each trajectory point passed through;

[0026] The location information includes the longitude, latitude, and elevation of the trajectory point.

[0027] Furthermore, the process of selecting the most feasible personnel movement trajectory based on the directional indoor vector trajectory map combined with the indoor three-dimensional path map, and completing the blank trajectories, specifically involves:

[0028] Based on the directional indoor vector trajectory map, obtain all indoor vector trajectory segments of the same person and sort them in chronological order;

[0029] Traverse all indoor vector trajectory segments;

[0030] Obtain the starting node and determine the vector direction;

[0031] Construct a three-dimensional coordinate system, with the starting node as the starting point and the vector direction as the direction. Determine the node that is closest to the starting node as the ending node.

[0032] Based on the indoor 3D path map, read the path matrix and determine whether the starting node and the ending node are connected. If they are connected, insert a simulated trajectory between the two points as a supplement; otherwise, return to the previous step to search for the remaining paths between the pointing nodes and the starting node.

[0033] The process iterates through the remaining indoor vector trajectory segments, filling in any blanks, and then continues until the last indoor vector trajectory segment is reached.

[0034] According to some embodiments, the second aspect of the present invention provides a personnel trajectory generation system for complex indoor scenes, employing the following technical solution:

[0035] A system for generating personnel trajectories in complex indoor scenes includes:

[0036] The indoor scene model building module is configured to survey and map indoor scenes and build complete 3D models of indoor scenes.

[0037] The 3D path map construction module is configured to extract all feasible indoor walking paths based on the 3D model of the indoor scene and generate a complete indoor 3D path map.

[0038] The visual reference station association module is configured to use visual calibration to calibrate the cameras at all key nodes in the room, and associate the cameras at the key nodes with the indoor 3D path map as visual reference stations.

[0039] The indoor vector trajectory map construction module is configured to identify parts of a person's trajectory through cameras at key nodes and generate an indoor vector trajectory map with direction.

[0040] The personnel path determination module is configured to select the most feasible personnel movement trajectory based on the indoor vector trajectory map with direction combined with the indoor three-dimensional path map, and to complete the blank trajectory.

[0041] The personnel trajectory generation module is configured to reorganize all completed trajectory routes to generate a new route. It determines the time corresponding to the inserted trajectory point based on the product of the ratio of the difference between the start node time and the end node time to the total number of inserted trajectory points and the inserted trajectory point, and the sum of the product and the start node time. The time corresponding to the trajectory point is then added to the new route to obtain a complete and continuous personnel trajectory route map.

[0042] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium.

[0043] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for generating personnel trajectories in a complex indoor scene as described in the first aspect above.

[0044] According to some embodiments, a fourth aspect of the present invention provides a computer device.

[0045] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of a method for generating personnel trajectories in a complex indoor scene as described in the first aspect above.

[0046] According to some embodiments, a fifth aspect of the present invention provides a computer program product or computer program.

[0047] A computer program product or computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in the method for generating personnel trajectories in a complex indoor scene as described in the first embodiment above.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0049] This invention proposes a method for generating personnel trajectories in complex indoor scenes. Based on personnel trajectories identified by a defined visual reference station, and combined with a predicted indoor building model, a complete representation of key nodes and access paths in the indoor 3D path map is extracted. By using trajectory paths with vector directions, the most likely movement routes of personnel are supplemented as blank segments of the trajectory, thereby obtaining a complete indoor personnel trajectory. This method solves the problem of discontinuous personnel trajectories and large blank intervals when there is no positioning information. It uses preprocessed geographic information as a basis to intelligently select the most likely trajectory routes of personnel and fill in blank personnel trajectories. Attached Figure Description

[0050] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0051] Figure 1 This is a flowchart of a method for generating personnel trajectories in a complex indoor scene according to an embodiment of the present invention;

[0052] Figure 2 This is a 3D model of the indoor scene in an embodiment of the present invention;

[0053] Figure 3 This is an indoor three-dimensional path map in an embodiment of the present invention;

[0054] Figure 4 This is a schematic diagram of an indoor vector trajectory in an embodiment of the present invention. Figure 1 ;

[0055] Figure 5 This is a schematic diagram of an indoor vector trajectory in an embodiment of the present invention. Figure 2 ;

[0056] Figure 6 This is a flowchart of personnel path determination in an embodiment of the present invention;

[0057] Figure 7 This is an architecture diagram of a personnel trajectory generation system in a complex indoor scene according to an embodiment of the present invention. Detailed Implementation

[0058] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0059] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0060] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0061] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0062] Example 1

[0063] like Figure 1 As shown, this embodiment provides a method for generating personnel trajectories in complex indoor scenes. This embodiment uses the application of this method to a server as an example for illustration. It can be understood that this method can also be applied to terminals, and can also be applied to systems including terminals, servers, and other components, and can be implemented through the interaction between the terminal and the server. The server can be an independent physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication, middleware services, domain name services, CDN security services, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and the server can be directly or indirectly connected through wired or wireless communication, which is not limited in this application. In this embodiment, the method includes the following steps:

[0064] Step S1: Survey the indoor scene and construct a complete 3D model of the indoor scene;

[0065] Step S2: Based on the 3D model of the indoor scene, extract all feasible indoor walking paths and generate a complete 3D indoor path map;

[0066] Step S3: Use visual calibration to calibrate the cameras at all key nodes in the room, and associate the cameras at the key nodes with the indoor 3D path map as visual reference stations.

[0067] Step S4: Identify part of the personnel's trajectory through the cameras at key nodes and generate an indoor vector trajectory map with direction;

[0068] Step S5: Based on the indoor vector trajectory map with direction and the indoor three-dimensional path map, select the most feasible personnel movement trajectory and complete the blank trajectory;

[0069] Step S6: Reorganize all completed trajectory routes to generate a new route. Then, determine the time corresponding to the inserted trajectory point based on the product of the ratio of the difference between the start node time and the end node time to the total number of inserted trajectory points and the inserted trajectory point, and the sum of this product and the start node time. Add the time corresponding to the trajectory point to the new route to obtain a complete and continuous personnel trajectory route map.

[0070] This embodiment proposes a method for generating personnel trajectories in complex indoor scenes. First, the indoor scene is surveyed to construct a complete 3D model of the indoor scene, extracting all feasible indoor walking paths and generating a complete 3D indoor path map. Then, visual calibration is used to calibrate the cameras at all key nodes in the indoor scene, and the cameras at the key nodes are used as visual reference stations and associated with the 3D indoor path map. The personnel trajectories identified by the cameras at the key nodes are used to generate directional vector trajectory data. Combined with the 3D path map, the most probable walking path is intelligently selected to complete the indoor personnel trajectory information and generate a complete, seamless personnel trajectory route map.

[0071] Specifically, for step S1, the digital construction of the indoor scene is as follows:

[0072] Generally, indoor scenes are complex in terms of floors, structure, and paths, making their digital construction challenging. Typically, 3D modeling technology is used to fully construct the indoor scene, requiring complete coverage of all indoor paths, including staircases, elevators, corridors, fire exits, emergency exits, and all pedestrian walkways. A building model diagram is shown below. Figure 2 As shown, a 3D model of the indoor scene is obtained.

[0073] For step S2, the indoor 3D path map is constructed as follows:

[0074] For indoor buildings where the model has already been built, key nodes and key paths are marked according to floor level to form a 3D digital display of paths. Key nodes mainly represent the deployment locations of visual cameras, and key paths mainly represent all possible indoor pedestrian paths, further divided by nodes, such as... Figure 3 As shown.

[0075] Based on the 3D model of the indoor scene, all feasible indoor walking paths are extracted to generate a complete 3D indoor path map, specifically:

[0076] Based on the 3D model of the indoor scene, for indoor buildings where the model has been completed, the key intersections of the indoor paths are marked as key nodes according to the floor level.

[0077] Determine whether any two key nodes are accessible to each other. If they are, record it as 1; if they are not, record it as 0. This forms a path matrix and creates an indoor 3D path map.

[0078] The path graph is digitally represented, using a numerical matrix to indicate whether there are paths connecting key nodes, such as... Figure 3 Taking the example shown, there are 9 key nodes within the building, so a 9x9 path matrix is ​​constructed. , This indicates that it is possible to travel from critical node 1 to critical node 1 itself. This indicates that it is possible to travel from critical node 1 to critical node 2. This indicates that the path from key node 1 to key node 3 is blocked. Thus, the path matrix L fully expresses the connectivity between all key nodes.

[0079] (1);

[0080] Based on the above principles, the path matrix will be obtained. As an indoor 3D path map.

[0081] Understandably, for any building, the corresponding key nodes are determined based on the 3D model of the indoor scene, and then the corresponding path matrix is ​​generated, ultimately resulting in a complete 3D indoor path map.

[0082] In a specific embodiment, for step S3, the visual reference station is associated as follows:

[0083] Visual calibration is used to calibrate cameras at all key nodes indoors. These cameras, acting as visual reference stations, are then associated with the indoor 3D path map. Specifically:

[0084] The cameras at all key indoor nodes were calibrated sequentially, and the camera numbers, longitudes, latitudes, and elevations were obtained as calibration results.

[0085] Using the cameras at key nodes as visual reference stations, the camera numbers are used as the visual reference station numbers based on the calibration results, and the longitude, latitude, and elevation of the cameras are used as the longitude, latitude, and elevation of the visual reference stations, thereby constructing a visual reference station array.

[0086] Based on key nodes, the visual reference station array is correlated with the indoor 3D path map.

[0087] In this step, after data association, based on the camera number corresponding to each key node, we can find out whether the path is accessible and other information about the key node. Here, the key nodes are the camera locations. Cameras are pre-positioned in the corresponding key nodes in sequence, the camera location information is marked, and all key nodes are fully covered.

[0088] An array of visual reference stations is constructed to store the information of the visual reference stations, including their number, longitude, latitude, and elevation. For example, [number: visual reference station 1, Lng: 3927768.355, Lat: 594456.064, High: 987.192]. All camera information is marked sequentially according to the above rules. Visual reference station 1 is determined to be the first key node, and so on.

[0089] Specifically, for step S4, visual positioning trajectory vectorization involves recognizing portions of a person's trajectory using cameras at key nodes to generate a directional indoor vector trajectory map, specifically:

[0090] By using cameras at key nodes to acquire dynamic trajectory information of people passing through each key node, the indoor trajectory of people can be obtained. The dynamic trajectory information includes multiple trajectory points arranged in chronological order.

[0091] Based on the location information in the trajectory point information, the trajectory direction between each pair of key nodes is determined according to the time sequence, thereby generating indoor vector trajectory segments with vector representation between the nodes;

[0092] Until all key nodes in the personnel's indoor trajectory are determined, multiple discontinuous indoor vector trajectory segments with vector representation are obtained, thereby generating an indoor vector trajectory map with direction.

[0093] The trajectory point information includes the time, location information, personnel information, mobile phone number ID, and device information for each trajectory point passed through; wherein, the location information includes the longitude, latitude, and elevation of the trajectory point.

[0094] It is understandable that the above determination of trajectory direction uses existing technology and conventional methods, which can be made by using trajectory point information, and there is no need to elaborate.

[0095] Since each visual reference station can determine a positioning trajectory within a certain range, but can determine the chronological order of each trajectory point according to time, a trajectory segment with vector identification can be generated. For example, the trajectory point information of visual reference station No. 1 is recorded as:

[0096] {[Equipment Name: Visual Reference Station No. 1; Personnel Name: Zhang San; Mobile Phone ID: 12345678910; Longitude: 117.1459, Latitude: 31.7195; Elevation: 18.6274; Time: 2024-02-07 14:42:22],

[0097] [Equipment Name: Visual Reference Station No. 1; Personnel Name: Zhang San; Mobile Phone ID: 12345678910; Longitude: 117.1460, Latitude: 31.7196; Elevation: 18.6274; Time: 2024-02-07 14:42:23]

[0098] [Equipment Name: Visual Reference Station No. 1; Personnel Name: Zhang San; Mobile Phone ID: 12345678910; Longitude: 117.1461, Latitude: 31.7196; Elevation: 18.6274; Time: 2024-02-07 14:42:24]}, arranged in chronological order, a new trajectory sequence is obtained. Based on the positioning information, a three-dimensional spatial trajectory is constructed, such as... Figure 4 As shown, a directional trajectory segment is generated within the field of view of visual reference station 1, pointing in the direction of visual reference station 2.

[0099] Following the above principles, multiple discontinuous trajectories with vector identifiers can be obtained. An indoor vector trajectory diagram for the same person is shown below. Figure 5 As shown.

[0100] For step S5, determining the personnel trajectory route, based on the indoor vector trajectory map with direction combined with the indoor three-dimensional path map, the most feasible personnel movement trajectory is selected, and blank trajectories are completed, specifically as follows:

[0101] Based on the directional indoor vector trajectory map, obtain all indoor vector trajectory segments of the same person and sort them in chronological order;

[0102] Traverse all indoor vector trajectory segments;

[0103] Obtain the starting node and determine the vector direction;

[0104] Construct a three-dimensional coordinate system, with the starting node as the starting point and the vector direction as the direction. Determine the node that is closest to the starting node as the ending node.

[0105] Based on the indoor 3D path map, read the path matrix and determine whether the starting node and the ending node are connected. If they are connected, insert a simulated trajectory between the two points as a supplement; otherwise, return to the previous step to search for the remaining paths between the pointing nodes and the starting node.

[0106] The process iterates through the remaining indoor vector trajectory segments, filling in any blanks, and then continues until the last indoor vector trajectory segment is reached.

[0107] Combine the indoor vector trajectory map obtained in step S4 with the path matrix obtained in step S2. To determine the most likely movement trajectory of personnel, fill in the blank trajectories. The specific method is as follows. Flowchart is shown below. Figure 6 As shown, specifically:

[0108] Obtain indoor vector trajectory segments for the same person. Based on the indoor vector trajectory map, obtain all indoor vector trajectory segments for the same person. The system retrieves all vector trajectory segments within the system based on the unique ID of the mobile phone number, and numbers the indoor vector trajectory segments in chronological order for subsequent processing.

[0109] Traverse all indoor vector trajectory segments of personnel, and search for personnel vector trajectory information in chronological order, including information such as latitude and longitude, elevation, capture device, time, and personnel for all points.

[0110] Obtain the starting node, determine the starting node visual reference station number, and determine the vector direction.

[0111] Obtain the vector pointing node. After obtaining the vector pointing, construct a three-dimensional coordinate system, using the coordinates of the starting node as the starting point and the vector pointing as the direction, and obtain the vector pointing node closest to the starting node as the ending node.

[0112] Read the path matrix and search for a starting node that is visual reference station 2 and an ending node that is visual reference station 3. If the value is 1, it means the nodes are connected, and a simulated trajectory can be inserted between the two points as a supplement; if the value is 0, it means the nodes are not connected, and the search returns to the previous step to search for the remaining paths between the pointing nodes and the starting node.

[0113] Complete the trajectory between the start and end nodes. Loop through the remaining indoor vector path segments. After completing the blank trajectory, traverse the next indoor vector trajectory segment. If it is the last one, end the traversal; otherwise, continue traversing.

[0114] For step S6, personnel trajectory generation involves reorganizing all completed trajectory routes to generate a new route.

[0115] The time corresponding to the inserted trajectory point is determined by multiplying the ratio of the difference between the start node time and the end node time to the total number of inserted trajectory points with the product of the inserted trajectory points and the sum of the product with the start node time.

[0116] The time corresponding to the trajectory points is added to the new route to obtain a complete, seamless personnel trajectory route map.

[0117] All the completed trajectory routes are reorganized to generate a new route. Time information is added according to formula (2). After the time information is added, a continuous and smooth indoor personnel trajectory route map can be obtained.

[0118] (2);

[0119] in, The starting time is... The time of the termination point, This represents the total number of inserted trajectory points. For the inserted first Points For the inserted first The time for each point.

[0120] In the indoor field, the method of this embodiment can effectively ensure the positioning of indoor personnel within the field of view of the visual reference station, and supplement the personnel trajectory route while ensuring positioning accuracy, thereby improving the trajectory continuity and smoothness.

[0121] In the cultural and tourism sector, this method can be applied to museums, exhibition halls, and other venues to identify visitor trajectories, effectively fill in blank trajectories, and generate complete indoor pedestrian routes as digital souvenirs.

[0122] Example 2

[0123] like Figure 7 As shown, this embodiment provides a system for generating personnel trajectories in complex indoor scenes, including:

[0124] The indoor scene model building module is configured to survey and map indoor scenes and build complete 3D models of indoor scenes.

[0125] The 3D path map construction module is configured to extract all feasible indoor walking paths based on the 3D model of the indoor scene and generate a complete indoor 3D path map.

[0126] The visual reference station association module is configured to use visual calibration to calibrate the cameras at all key nodes in the room, and associate the cameras at the key nodes with the indoor 3D path map as visual reference stations.

[0127] The indoor vector trajectory map construction module is configured to identify parts of a person's trajectory through cameras at key nodes and generate an indoor vector trajectory map with direction.

[0128] The personnel path determination module is configured to select the most feasible personnel movement trajectory based on the indoor vector trajectory map with direction combined with the indoor three-dimensional path map, and to complete the blank trajectory.

[0129] The personnel trajectory generation module is configured to reorganize all completed trajectory routes to generate a new route. It determines the time corresponding to the inserted trajectory point based on the product of the ratio of the difference between the start node time and the end node time to the total number of inserted trajectory points and the inserted trajectory point, and the sum of the product and the start node time. The time corresponding to the trajectory point is then added to the new route to obtain a complete and continuous personnel trajectory route map.

[0130] The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1 above. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0131] The descriptions of each embodiment in the above embodiments have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0132] The proposed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and the division of modules described above is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed.

[0133] Example 3

[0134] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the method for generating personnel trajectories in a complex indoor scene as described in Embodiment 1 above.

[0135] Example 4

[0136] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the method for generating personnel trajectories in a complex indoor scene as described in Embodiment 1 above.

[0137] Example 5

[0138] This embodiment provides a computer program product or computer program, including computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in the method for generating personnel trajectories in a complex indoor scene as described in Embodiment 1 above.

[0139] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention 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 and optical storage) containing computer-usable program code.

[0140] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0141] 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.

[0142] 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.

[0143] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0144] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for generating personnel trajectories in complex indoor scenes, characterized in that, include: The interior scene was surveyed and mapped to construct a complete 3D model of the interior scene; Based on the 3D model of the indoor scene, all feasible indoor walking paths are extracted to generate a complete 3D indoor path map. Visual calibration is used to calibrate the cameras at all key nodes in the room, and the cameras at the key nodes are used as visual reference stations and associated with the indoor three-dimensional path map. By identifying parts of a person's trajectory through cameras at key nodes, an indoor vector trajectory map with direction is generated; Based on the indoor vector trajectory map with direction and the indoor three-dimensional path map, the most feasible personnel movement trajectory is selected and the blank trajectory is filled in. All completed trajectory routes are reorganized to generate a new route. The time corresponding to the inserted trajectory point is determined by multiplying the ratio of the difference between the start node time and the end node time to the total number of inserted trajectory points, and the sum of this product and the start node time. The time corresponding to the trajectory point is then added to the new route to obtain a complete and continuous personnel trajectory route map.

2. The method for generating personnel trajectories in complex indoor scenes as described in claim 1, characterized in that, Based on the 3D model of the indoor scene, all feasible indoor walking paths are extracted to generate a complete 3D indoor path map, specifically: Based on the 3D model of the indoor scene, for indoor buildings where the model has been completed, the key intersections of the indoor paths are marked as key nodes according to the floor level. Determine whether any two key nodes are accessible to each other. If they are, record it as 1; if they are not, record it as 0. This forms a path matrix and creates an indoor 3D path map.

3. The method for generating personnel trajectories in a complex indoor scene as described in claim 1, characterized in that, The process involves calibrating cameras at all key indoor nodes using visual calibration, and then associating these cameras with the indoor 3D path map, using these key node cameras as visual reference stations. Specifically: The cameras at all key indoor nodes were calibrated sequentially, and the camera numbers, longitudes, latitudes, and elevations were obtained as calibration results. Using the cameras at key nodes as visual reference stations, the camera numbers are used as the visual reference station numbers based on the calibration results, and the longitude, latitude, and elevation of the cameras are used as the longitude, latitude, and elevation of the visual reference stations, thereby constructing a visual reference station array. Based on key nodes, the visual reference station array is correlated with the indoor 3D path map.

4. The method for generating personnel trajectories in complex indoor scenes as described in claim 1, characterized in that, The process of identifying partial trajectories of personnel through cameras at key nodes and generating directional indoor vector trajectory maps specifically involves: By using cameras at key nodes to acquire dynamic trajectory information of people passing through each key node, the indoor trajectory of people can be obtained. The dynamic trajectory information includes multiple trajectory points arranged in chronological order. Based on the location information in the trajectory point information, the trajectory direction between each pair of key nodes is determined according to the time sequence, thereby generating indoor vector trajectory segments with vector representation between the nodes; Until all key nodes in the personnel's indoor trajectory are determined, multiple discontinuous indoor vector trajectory segments with vector representation are obtained, thereby generating an indoor vector trajectory map with direction.

5. The method for generating personnel trajectories in a complex indoor scene as described in claim 4, characterized in that, The trajectory point information includes the time, location information, personnel information, mobile phone number ID, and device information for each trajectory point passed through; The location information includes the longitude, latitude, and elevation of the trajectory point.

6. The method for generating personnel trajectories in a complex indoor scene as described in claim 1, characterized in that, The method involves combining a directional indoor vector trajectory map with an indoor 3D path map to select the most feasible personnel movement trajectory and completing any blank trajectories. Specifically: Based on the directional indoor vector trajectory map, obtain all indoor vector trajectory segments of the same person and sort them in chronological order; Traverse all indoor vector trajectory segments; Obtain the starting node and determine the vector direction; Construct a three-dimensional coordinate system, with the starting node as the starting point and the vector direction as the direction. Determine the node that is closest to the starting node as the ending node. Based on the indoor 3D path map, read the path matrix and determine whether the starting node and the ending node are connected. If they are connected, insert a simulated trajectory between the two points as a supplement; otherwise, return to the previous step to search for the remaining paths between the pointing nodes and the starting node. The process iterates through the remaining indoor vector trajectory segments, filling in any blanks, and then continues until the last indoor vector trajectory segment is reached.

7. A system for generating personnel trajectories in complex indoor scenes, characterized in that, include: The indoor scene model building module is configured to survey and map indoor scenes and build complete 3D models of indoor scenes. The 3D path map construction module is configured to extract all feasible indoor walking paths based on the 3D model of the indoor scene and generate a complete indoor 3D path map. The visual reference station association module is configured to use visual calibration to calibrate the cameras at all key nodes in the room, and associate the cameras at the key nodes with the indoor 3D path map as visual reference stations. The indoor vector trajectory map construction module is configured to identify parts of a person's trajectory through cameras at key nodes and generate an indoor vector trajectory map with direction. The personnel path determination module is configured to select the most feasible personnel movement trajectory based on the indoor vector trajectory map with direction combined with the indoor three-dimensional path map, and to complete the blank trajectory. The personnel trajectory generation module is configured to reorganize all completed trajectory routes to generate a new route, resulting in a complete and continuous personnel trajectory route map.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the method for generating personnel trajectories in a complex indoor scene as described in any one of claims 1-6.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the method for generating personnel trajectories in a complex indoor scene as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps in the method for generating personnel trajectories in a complex indoor scene as described in any one of claims 1-6.

Images