A method, device and equipment for determining trajectory of moving target and storage medium

Abstract

A trajectory determination method, device and equipment of a moving target and a storage medium are disclosed. The method comprises: obtaining a target time interval, a first node and a second node of a target road network; the first node is an all-around snapshot device, and the second node is a non-all-around snapshot device; determining an initial trajectory point of the moving target according to first node collected data and the target time interval; determining an initial trajectory and an extended trajectory according to the initial trajectory point and second node collected data having a position matching relationship with the initial trajectory point, and connecting the initial trajectory and the extended trajectory to obtain a movement trajectory of the moving target in the target road network. This scheme can solve the problems of large resource consumption and low retrieval efficiency in all-area snapshot image comparison, and can improve the rapid determination of the target trajectory while saving computing, storage and other resources.

Description

Technical Field

[0001] This invention relates to the field of video surveillance technology, and in particular to a method, apparatus, device, and storage medium for determining the trajectory of a moving target. Background Technology

[0002] In the field of video surveillance, determining the movement trajectory of targets such as people and vehicles is a very important task.

[0003] Existing technical solutions mainly determine the target trajectory by using information such as target features, area range, and time range. Specifically, the server acquires images from all capture devices within the area, determines the set of points of the moving target based on the comparison results of all images with the target features, and then arranges the points in time order to obtain the target's motion trajectory.

[0004] However, existing solutions require comparison of all captured images within the area, involving a huge amount of resource data, a wide time range, and low retrieval efficiency, making it difficult to meet the demand for timely and accurate target trajectory positioning. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for determining the trajectory of a moving target, in order to solve the problems of high resource consumption and low retrieval efficiency in comparing captured images across the entire area. It can quickly determine the trajectory of a target while saving computational and storage resources.

[0006] According to one aspect of the present invention, a method for determining the trajectory of a moving target is provided, the method comprising:

[0007] The system acquires the target time interval, the first node of the target road network, and the second node; wherein the first node is an omnidirectional capture device, and the second node is a non-omnidirectional capture device.

[0008] Based on the data collected by the first node and the target time interval, the initial trajectory points of the moving target are determined;

[0009] Based on the initial trajectory points and the data collected from the second node that has a positional matching relationship with the initial trajectory points, the initial trajectory and the extended trajectory are determined, and the initial trajectory and the extended trajectory are connected to obtain the movement trajectory of the moving target within the target road network.

[0010] According to another aspect of the present invention, a trajectory determination device for a moving target is provided, the device comprising:

[0011] The node and time acquisition module is used to acquire the target time interval, the first node of the target road network, and the second node; wherein, the first node is an omnidirectional capture device, and the second node is a non-omnidirectional capture device;

[0012] The initial trajectory point determination module is used to determine the initial trajectory point of the moving target based on the data collected by the first node and the target time interval;

[0013] The motion trajectory determination module is used to collect data based on the initial trajectory point and the second node that has a positional matching relationship with the initial trajectory point, determine the initial trajectory and the extended trajectory, and connect the initial trajectory and the extended trajectory to obtain the motion trajectory of the moving target in the target road network.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the trajectory determination method for a moving target according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the trajectory determination method for a moving target as described in any embodiment of the present invention.

[0019] The technical solution of this invention generates the initial trajectory points of a moving target by collecting data from a first node in the target road network. Then, based on data collected from a second node with a positional matching relationship to the initial trajectory points, the initial trajectory and extended trajectory are determined, thereby obtaining the movement trajectory of the moving target within the target road network. This solution solves the problems of high resource consumption and low retrieval efficiency in comparing images captured across the entire area, and can quickly determine the target trajectory while saving computational and storage resources.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a method for determining the trajectory of a moving target according to Embodiment 1 of the present invention;

[0023] Figure 2 This is a schematic diagram of the distribution of target road network capture devices according to an embodiment of the present invention;

[0024] Figure 3 This is a flowchart of a method for determining the trajectory of a moving target according to Embodiment 2 of the present invention;

[0025] Figure 4 This is a schematic diagram of the path from point C to point D provided according to an embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of a trajectory determination device for a moving target according to Embodiment 3 of the present invention;

[0027] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the trajectory determination method for a moving target according to an embodiment of the present invention. Detailed Implementation

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

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0030] Example 1

[0031] Figure 1This is a flowchart of a method for determining the trajectory of a moving target according to Embodiment 1 of the present invention. This embodiment is applicable to determining the movement trajectory of moving targets such as people and vehicles in a monitoring scenario. This method can be executed by a trajectory determination device for the moving target, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0032] S110, Obtain the target time interval, the first node and the second node of the target road network.

[0033] This solution can be executed by a moving target retrieval platform. The platform supports user input of the time interval to be searched and can also periodically search for moving targets in each road network. The moving target retrieval platform can communicate with the capture devices in each road network to obtain device information such as location and model, and construct a distribution diagram of each road network based on this information. Figure 2 This is a schematic diagram of the distribution of target road network capture devices according to an embodiment of the present invention, such as... Figure 2 As shown, the thin lines represent roads, and the rectangles represent the area encompassed by the target road network.

[0034] Specifically, road network nodes can be divided into first nodes and second nodes based on the differences in the monitoring range of the capture devices. First nodes can be capture devices with a larger monitoring range, such as omnidirectional capture devices, while second nodes can be capture devices with a smaller monitoring range, such as non-omnidirectional capture devices. Figure 2 In the target road network, circular markers indicate omnidirectional capture devices, capable of capturing images of lanes in all directions, such as 360° panoramic cameras. Triangular markers indicate non-omnidirectional capture devices, unable to capture images of lanes in all directions, such as bullet cameras that only capture images of a single lane. For moving targets, omnidirectional capture devices can often acquire richer trajectory information compared to non-omnidirectional capture devices.

[0035] S120. Based on the data collected by the first node and the target time interval, determine the initial trajectory points of the moving target.

[0036] Understandably, the data collected by the first node can include information such as the captured image, capture time, and the direction of movement of the moving target. The moving target retrieval platform can use the first node as a basis to construct a general framework of the motion trajectory. Specifically, the moving target retrieval platform can determine the initial trajectory points within the target time interval based on the data collected by the first node. The moving target retrieval platform can filter the data collected by the first node within the target road network based on the target time interval, retrieving captured images that match the time range. By comparing the filtered captured images with the features of the moving target, the moving target retrieval platform can determine the first node where the moving target was captured.

[0037] The initial trajectory point can be the actual position of the moving target determined from the captured image of the moving target, or it can be the position of the first node captured by the moving target. Using the position of the first node captured by the moving target as the initial trajectory point makes it easier to find the second node between two adjacent initial trajectory points, but this embodiment does not limit the specific form of the initial trajectory point.

[0038] like Figure 2 The circular markers shown can be initial trajectory points determined within the target road network. Based on the capture time, the moving target retrieval platform can also determine the starting and ending points of the motion trajectory analysis, for example, based on... Figure 2 The capture time sorting results of the first node shown indicate that point A is determined as the starting point of the analysis and point B is determined as the ending point of the analysis.

[0039] After obtaining the initial trajectory points, the moving target retrieval platform needs to further combine the data collected by the second node to locate the moving target's trajectory. Specifically, based on the analysis start and end points of the initial trajectory points, such as points A and B, the moving target retrieval platform can further determine the initial trajectory between the start and end points, or it can determine the extended trajectory of the initial trajectory within the target road network area with the analysis start and end points as the center, thereby obtaining the complete movement trajectory of the moving target within the target road network.

[0040] S130. Based on the initial trajectory points and the data collected from the second node that has a positional matching relationship with the initial trajectory points, determine the initial trajectory and the extended trajectory, and connect the initial trajectory and the extended trajectory to obtain the movement trajectory of the moving target in the target road network.

[0041] Similarly, the data collected by the second node may also include information such as the captured image, capture time, and the direction of movement of the moving target. The data collected by the second node that has a positional matching relationship with the initial trajectory points may be data collected by the second node deployed between two adjacent initial trajectory points, or data collected by the second node at a preset distance from each initial trajectory point.

[0042] For example, a moving target retrieval platform can... Figure 2 The target retrieval platform uses data collected by the second nodes a and b between points A and C for target retrieval. Alternatively, the platform can ignore data collected by the second node a, which is closer to point A, and only retrieve data from the second node a. Figure 2 The data collected by the second node b, located at a preset distance from point A, is used for target retrieval. It should be noted that the second node can be deployed in non-intersection locations such as the middle section of a road, such as point a, or at an intersection, such as point b.

[0043] Specifically, the moving target retrieval platform can determine a time range based on the capture time of moving targets at points A and C, use this time range to filter the data collected by the second node, and then determine the initial trajectory based on the filtered data collected by the second node.

[0044] The data collected by the second node that has a positional matching relationship with the initial trajectory points can also be the data collected by the second node closest to each initial trajectory point. For example, after obtaining the initial trajectory, the moving target retrieval platform can use the start and end points of the initial trajectory as extension center points, and determine the extension time interval based on the target time interval and the capture time of the extension center points. Based on the extension time interval, the moving target retrieval platform can filter the data collected by the second nodes adjacent to the extension center points, and then determine the extension trajectory based on the data collected by the filtered second nodes.

[0045] It is easy to understand that after the initial trajectory and the extended trajectory are determined, the moving target retrieval platform can connect the initial trajectory and the extended trajectory to obtain the movement trajectory of the moving target within the target road network.

[0046] This technical solution generates the initial trajectory points of a moving target by collecting data from the first node in the target road network. Then, based on the data collected from the second node, which has a positional matching relationship with the initial trajectory points, the initial trajectory and extended trajectory are determined, thus obtaining the movement trajectory of the moving target within the target road network. This solution solves the problems of high resource consumption and low retrieval efficiency in comparing images captured across the entire area, and can quickly determine the target trajectory while saving computing and storage resources.

[0047] Example 2

[0048] Figure 3 This is a flowchart of a method for determining the trajectory of a moving target according to Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Figure 3 As shown, the method includes:

[0049] S210, Obtain the target time interval, the first node and the second node of the target road network.

[0050] S220. Based on the data collected by the first node and the target time interval, determine the initial trajectory points of the moving target.

[0051] S230. Based on the pre-acquired road information, determine the set of paths between adjacent initial trajectory points.

[0052] The moving target retrieval platform can communicate with traffic management and urban management systems to obtain timely road information such as road construction, traffic control, and traffic volume at different times within the target road network. Based on this road information, the moving target retrieval platform can determine traversable paths between adjacent initial trajectory points. For example... Figure 2 The target road network can include multiple paths between points C and D. Based on the pre-acquired road information, the moving target retrieval platform can eliminate impassable paths, such as paths closed due to construction or traffic control, and can also eliminate paths with low probability of passage, such as paths where the traffic volume at any time is less than the preset traffic volume threshold.

[0053] Figure 4 This is a schematic diagram of the path from point C to point D provided according to an embodiment of the present invention, as shown below. Figure 4 Path 1, Path 2, and Path 3 can be three paths from the set of paths between point C and point D determined by the moving target retrieval platform based on road information.

[0054] S240. Based on the data collected from adjacent initial trajectory points and second nodes that have a positional matching relationship with the adjacent initial trajectory points, the target path is determined in the path set.

[0055] Among them, the data collected by the second node that has a positional matching relationship with the adjacent initial trajectory points can be the data collected by the second node whose location is between the adjacent initial trajectory points, for example... Figure 2 The data collected by the second nodes a and b between points A and C. The moving target retrieval platform can directly filter the second node data that meets the time range based on the capture time of adjacent initial trajectory points. Then, by comparing the moving target features with the images collected by each second node, it determines the second node where the moving target was captured. Finally, the capture time of the moving target images collected by the second nodes is sorted, and the target path is determined from the path set.

[0056] In this scheme, optionally, the target path is determined from the path set based on data collected from adjacent initial trajectory points and second nodes that have a positional matching relationship with the adjacent initial trajectory points, including:

[0057] Based on the capture time of adjacent initial trajectory points, determine the sub-intervals of the target time interval;

[0058] Based on the sub-interval and the data collected from the second node that has a positional matching relationship with the adjacent initial trajectory point, the target path of the adjacent initial trajectory point is determined in the path set.

[0059] In this scheme, the moving target retrieval platform can filter the second node collection data that meets the time range based on the capture time of adjacent initial trajectory points, and then evaluate each path in the path set based on the second node collection data that meets the time constraints to determine the target path.

[0060] The moving target retrieval platform can retrieve data collected from the second node within the time range of each path, for example, directly targeting... Figure 4 Moving target retrieval is performed on X1, X2, X3, X4, and X5. The target path is determined based on the retrieval results of the data collected from the second node on each path. For example, assuming that X1, X2, and X5 capture moving targets, while X3 and X4 do not capture moving targets, then path 2 can be determined as the target path.

[0061] The moving target retrieval platform can also progressively retrieve the collected data from the second nodes distributed along the path. Specifically, the platform can start from the path's origin and simultaneously retrieve the collected data from the first second node on each path, or it can select the collected data from the first second node of the path with the highest probability of passage and ultimately determine the target path based on the retrieval results of the second node's collected data.

[0062] The moving target retrieval platform can simultaneously perform... Figure 4 The data collected by X1 and X4 are retrieved. If only X1 captures a moving target, then the data collected by X2 and X3 are retrieved. If X2 does not capture a moving target but X3 does, then path 3 is determined as the target path. If X3 does not capture a moving target but X2 does, then path 2 is determined as the target path.

[0063] This solution can significantly reduce the number of times the moving target retrieval platform searches for data collected from the second node, reduce the consumption of hardware resources, and improve retrieval efficiency.

[0064] Based on the above scheme, according to the sub-intervals and the data collected from the second node that has a positional matching relationship with the adjacent initial trajectory points, the target path of the adjacent initial trajectory points is determined in the path set, including:

[0065] Determine the first initial trajectory point with the earlier capture time among adjacent initial trajectory points;

[0066] The capture time is determined by sequentially collecting data from the second node that has a positional matching relationship with the first initial trajectory point, and the path points within the sub-interval are determined until the target path of the adjacent initial trajectory point is determined in the path set based on the path points.

[0067] by Figure 4 Taking adjacent initial trajectory points C and D as an example, point C is the starting point of the target path, and point D is the ending point. Point C was captured earlier and is the first initial trajectory point. The moving target retrieval platform can also select the second node X1 closest to point C and search the data collected by X1. If X1 captures a moving target, path 1 is excluded, and the path point is determined based on the moving target image information captured by the second node X1. The moving target retrieval platform can continue to search the data collected by the second node X2 closest to X1. If X2 captures a moving target, path 3 is excluded, and path 2 is determined as the target path.

[0068] If X2 fails to capture a moving target, the moving target retrieval platform can search the data collected by X3. If X3 captures a moving target, the platform can determine path 3 as the target path. If X3 fails to capture a moving target, the platform continues to search the data collected by X5. If X5 captures a moving target, the platform can determine which path, 2 or 3, is the target path based on the direction of the moving target captured by X5 and the shooting direction of X5.

[0069] This scheme uses the retrieval results from the data collected at each second node to reasonably exclude paths in the path set, which can avoid invalid calculations, minimize the number of searches, and facilitate the rapid and accurate determination of the target path.

[0070] S250. Connect the target paths between adjacent initial trajectory points to obtain the initial trajectory.

[0071] It's easy to understand that after determining the target paths between each group of adjacent initial trajectory points, connecting these target paths yields the initial trajectory. For example... Figure 2 As shown, based on A and C, C and D, D and F, and F and B, the target paths AC, CD, DF, and FB can be determined respectively. Connecting the beginning and end of each target path yields the initial trajectory AB.

[0072] S260. Determine the extension center point based on the starting and / or ending points of the initial trajectory.

[0073] After obtaining the initial trajectory, the moving target retrieval platform can determine whether the starting and ending points of the initial trajectory are located on the boundary of the target road network. If neither is on the boundary, the path can be extended using the starting and ending points as extension center points respectively. If one of the starting and ending points is on the boundary of the target road network, the path can be extended using either the starting or ending point that is not on the boundary as the extension center point.

[0074] S270. Determine the extension time interval based on the capture time of the extension center point and the target time interval.

[0075] Assuming Figure 2 Points A and B are shown as extension center points. The capture time for point A is 3:00 and the capture time for point B is 4:00. The target time interval is [2:30, 4:30]. The extension time interval of the extension trajectory with point A as the extension center point can be [2:30, 3:00), and the extension time interval of the extension trajectory with point B as the extension center point can be (4:00, 4:30).

[0076] S280. Collect data from the second node that has a positional matching relationship with the extension center point to determine the extension point where the capture time is within the extension time interval.

[0077] The data collected by the second node that has a positional matching relationship with the extension center point can be data collected by the second node whose location is within a preset distance threshold range of the extension center point, or data collected by the second node whose location is closest to the extension center point. The moving target retrieval platform can exclude the second node data involved in the initial trajectory, and determine the extension point whose capture time is within the extension time interval based on the other second node data in the target road network and the retrieval results of the second node data.

[0078] To further narrow down the search scope, the moving target retrieval platform can search the data collected by the second node layer by layer according to the distance of the second node from the extension center point, thereby obtaining the extension point that meets the extension time interval constraint.

[0079] In a preferred embodiment, the extension points whose capture time falls within the extension time interval are determined sequentially based on data collected from the second node that matches the extension center point, including:

[0080] Data is collected from at least one priority second node that has a positional matching relationship with the extended center point;

[0081] If, based on the data collected by the second node of the first priority, it is determined that there is an extension point whose capture time is within the extension time interval, then the extension point is taken as the new extension center point.

[0082] Return to the operation of collecting data from at least one priority second node that has a positional matching relationship with the extended center point, until the processing of all second node data that has a positional matching relationship with the extended center point is completed.

[0083] Based on the above scheme, after determining that at least one priority second node with a positional matching relationship with the extended center point has collected data, the method further includes:

[0084] If it is determined from the second node data of the first priority that there is no extended point where the capture time is within the extended time interval, then it is determined from the second node data of the second priority that there is an extended point where the capture time is within the extended time interval, until it is determined from the second node data of at least one priority that there is an extended point where the capture time is within the extended time interval, or, the processing of all second node data that match the extended center point is completed.

[0085] In this scheme, the distance between the location of the second node with the first priority and the extension center point can be less than or equal to the distance between the location of the second node with the second priority and the extension center point. Specifically, the moving target retrieval platform can determine the data collection of at least one second node with a priority based on the extension center point. The priority can be determined based on the relative position of the second node and the extension center point. Figure 2 As shown, multiple concentric circular regions with different radii are set with the extended center point A as the center, and at least one priority is determined by these concentric circles. The moving target retrieval platform can determine the collected data of the second node closest to the center of the circle as the highest priority, i.e., the first priority. The collected data of the second node c can have the highest priority, and the collected data of the second node d can have the second highest priority, i.e., the second priority.

[0086] The moving target retrieval platform can first search the data collected by the second node within the first priority range. If a moving target is detected in the image captured by the second node within the extended time interval within the first priority range, the extended point is determined based on the image of the detected moving target. This extended point is then used as the new extended center point to continue determining subsequent extended points until the extended center point reaches the boundary of the target road network or the capture time of the moving target image collected by the second node exceeds the extended time interval.

[0087] If the second node within the first priority range does not capture a moving target, the data collection for the second node within the second priority range will continue until the extended point is located within the target road network range in the extended time interval.

[0088] The above scheme can prioritize the data collected by the second node and determine the extension points step by step, which is conducive to quickly and accurately locating the extension points and thus obtaining a precise extension trajectory, ensuring the integrity of the movement trajectory in the target road network.

[0089] It should be noted that if no moving target is detected in the data collected from each of the second nodes that match the extended center point, have a capture time within the extended time interval, and have a capture area within the boundary of the target road network, it indicates that there is no extended trajectory for the extended center point.

[0090] S290. Connect the extended points to obtain the extended trajectory.

[0091] S2100: Connect the initial trajectory and the extended trajectory to obtain the motion trajectory of the moving target within the target road network.

[0092] This technical solution generates the initial trajectory points of a moving target by collecting data from the first node in the target road network. Then, based on the data collected from the second node matched with the initial trajectory points, the initial trajectory and extended trajectory are determined, thus obtaining the moving trajectory of the target within the target road network. This solution solves the problems of high resource consumption and low retrieval efficiency in comparing images captured across the entire area, saving computational and storage resources while quickly determining the target trajectory.

[0093] Example 3

[0094] Figure 5 This is a schematic diagram of the structure of a trajectory determination device for a moving target provided in Embodiment 3 of the present invention. Figure 5 As shown, the device includes:

[0095] The node and time acquisition module 310 is used to acquire the target time interval, the first node of the target road network, and the second node; wherein, the first node is an all-around capture device, and the second node is a non-all-around capture device;

[0096] The initial trajectory point determination module 320 is used to determine the initial trajectory point of the moving target based on the data collected by the first node and the target time interval;

[0097] The motion trajectory determination module 330 is used to determine the initial trajectory and the extended trajectory based on the data collected from the initial trajectory point and the second node that has a positional matching relationship with the initial trajectory point, and to connect the initial trajectory and the extended trajectory to obtain the motion trajectory of the moving target in the target road network.

[0098] In this solution, optionally, the motion trajectory determination module 330 includes:

[0099] The path set determination unit is used to determine the path set between adjacent initial trajectory points based on pre-acquired road information.

[0100] The target path determination unit is used to collect data from the path set based on adjacent initial trajectory points and second nodes that have a positional matching relationship with the adjacent initial trajectory points;

[0101] The initial trajectory generation unit is used to connect the target paths between adjacent initial trajectory points to obtain the initial trajectory.

[0102] Based on the above scheme, the target path determination unit includes:

[0103] Sub-interval determination sub-units are used to determine the sub-intervals of the target time interval based on the capture time of adjacent initial trajectory points;

[0104] The target path determination subunit is used to determine the target path of adjacent initial trajectory points in the path set based on the data collected from the sub-interval and the second node that has a positional matching relationship with the adjacent initial trajectory points.

[0105] Optionally, the target path determination subunit is specifically used for:

[0106] Determine the first initial trajectory point with the earlier capture time among adjacent initial trajectory points;

[0107] The capture time is determined by sequentially collecting data from the second node that has a positional matching relationship with the first initial trajectory point, and the path points within the sub-interval are determined until the target path of the adjacent initial trajectory point is determined in the path set based on the path points.

[0108] In one feasible solution, the motion trajectory determination module 330 includes:

[0109] The extension center point determination unit is used to determine the extension center point based on the starting point and / or ending point of the initial trajectory.

[0110] The extended time interval determination unit is used to determine the extended time interval based on the capture time of the extended center point and the target time interval.

[0111] The extension point determination unit is used to collect data from the second node that has a positional matching relationship with the extension center point to determine the extension point within the extension time interval for the capture time.

[0112] The extended trajectory generation unit is used to connect the extended points to obtain the extended trajectory.

[0113] Based on the above scheme, optionally, the extension point determination unit includes:

[0114] The second node data acquisition determines the sub-unit, which is used to determine at least one priority second node data acquisition that has a positional matching relationship with the extended center point.

[0115] The extended center point update subunit is used to determine, based on the data collected by the second node with the first priority, that there is an extended point whose capture time is within the extended time interval, and then use the extended point as the new extended center point.

[0116] The termination judgment subunit is used to return to the operation of collecting data from at least one priority second node that has a positional matching relationship with the extension center point, until the processing of all second node data that has a positional matching relationship with the extension center point is completed.

[0117] In a preferred embodiment, the extension point determination unit is further configured to:

[0118] If it is determined from the second node data of the first priority that there is no extended point where the capture time is within the extended time interval, then it is determined from the second node data of the second priority that there is an extended point where the capture time is within the extended time interval, until it is determined from the second node data of at least one priority that there is an extended point where the capture time is within the extended time interval, or, the processing of all second node data that have a positional matching relationship with the extended center point is completed.

[0119] Among them, the distance between the location of the second node of the first priority and the extension center point is less than or equal to the distance between the location of the second node of the second priority and the extension center point.

[0120] The trajectory determination device for a moving target provided in the embodiments of the present invention can execute the trajectory determination method for a moving target provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0121] Example 4

[0122] Figure 6A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0123] like Figure 6 As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0124] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0125] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as methods for determining the trajectory of a moving target.

[0126] In some embodiments, the trajectory determination of a moving target may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the trajectory determination of the moving target described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the trajectory determination method of the moving target by any other suitable means (e.g., by means of firmware).

[0127] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0129] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0130] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0131] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0132] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0133] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0134] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining the trajectory of a moving target, characterized in that, include: The system acquires the target time interval, the first node of the target road network, and the second node; wherein the first node is an omnidirectional capture device, and the second node is a non-omnidirectional capture device. Based on the data collected by the first node and the target time interval, the initial trajectory points of the moving target are determined; Based on the data collected from the initial trajectory points and the second node that has a positional matching relationship with the initial trajectory points, the initial trajectory and the extended trajectory are determined, and the initial trajectory and the extended trajectory are connected to obtain the movement trajectory of the moving target in the target road network. The step of determining the initial trajectory based on the initial trajectory points and data collected from second nodes that have a positional matching relationship with the initial trajectory points includes: Based on the pre-acquired road information, determine the set of paths between adjacent initial trajectory points; Based on the data collected from adjacent initial trajectory points and second nodes that have a positional matching relationship with the adjacent initial trajectory points, the target path is determined from the path set; The initial trajectory is obtained by connecting the target paths between adjacent initial trajectory points; The step of determining the extended trajectory based on the data collected from the initial trajectory points and the second node that has a positional matching relationship with the initial trajectory points includes: Determine the center point of the extension based on the starting and / or ending points of the initial trajectory; The extended time interval is determined based on the capture time of the extended center point and the target time interval. Based on the data collected from the second node that has a positional matching relationship with the extension center point, the extension point is determined to be within the extension time interval for the capture time. Connect the extended points to obtain the extended trajectory.

2. The method according to claim 1, characterized in that, Based on data collected from adjacent initial trajectory points and second nodes that have a positional matching relationship with the adjacent initial trajectory points, the target path is determined from the path set, including: Based on the capture time of adjacent initial trajectory points, determine the sub-intervals of the target time interval; Based on the sub-interval and the data collected from the second node that has a positional matching relationship with the adjacent initial trajectory point, the target path of the adjacent initial trajectory point is determined in the path set.

3. The method according to claim 2, characterized in that, Based on the sub-intervals and the data collected from the second node that has a positional matching relationship with the adjacent initial trajectory points, the target path for the adjacent initial trajectory points is determined in the path set, including: Determine the first initial trajectory point with the earlier capture time among adjacent initial trajectory points; The capture time is determined by sequentially collecting data from the second node that has a positional matching relationship with the first initial trajectory point, and the path points within the sub-interval are determined until the target path of the adjacent initial trajectory point is determined in the path set based on the path points.

4. The method according to claim 1, characterized in that, Based on the data collected from the second node that has a positional matching relationship with the extension center point, the extension points whose capture time falls within the extension time interval are determined, including: Data is collected from at least one priority second node that has a positional matching relationship with the extended center point; If, based on the data collected by the second node of the first priority, it is determined that there is an extension point whose capture time is within the extension time interval, then the extension point is taken as the new extension center point. Return to the operation of collecting data from at least one priority second node that has a positional matching relationship with the extended center point, until the processing of all second node data that has a positional matching relationship with the extended center point is completed.

5. The method according to claim 4, characterized in that, After determining that at least one priority second node has a location matching relationship with the extended center point, the method further includes: If it is determined from the second node data of the first priority that there is no extended point where the capture time is within the extended time interval, then it is determined from the second node data of the second priority that there is an extended point where the capture time is within the extended time interval, until it is determined from the second node data of at least one priority that there is an extended point where the capture time is within the extended time interval, or, the processing of all second node data that have a positional matching relationship with the extended center point is completed. Among them, the distance between the location of the second node of the first priority and the extension center point is less than or equal to the distance between the location of the second node of the second priority and the extension center point.

6. A trajectory determination device for a moving target, characterized in that, include: The node and time acquisition module is used to acquire the target time interval, the first node of the target road network, and the second node; wherein, the first node is an omnidirectional capture device, and the second node is a non-omnidirectional capture device; The initial trajectory point determination module is used to determine the initial trajectory point of the moving target based on the data collected by the first node and the target time interval; The motion trajectory determination module is used to collect data based on the initial trajectory point and the second node that has a positional matching relationship with the initial trajectory point, determine the initial trajectory and the extended trajectory, and connect the initial trajectory and the extended trajectory to obtain the motion trajectory of the moving target in the target road network. The motion trajectory determination module includes: a path set determination unit, used to determine the path set between adjacent initial trajectory points based on pre-acquired road information; The target path determination unit is used to collect data from the path set based on adjacent initial trajectory points and second nodes that have a positional matching relationship with the adjacent initial trajectory points; The initial trajectory generation unit is used to connect the target paths between adjacent initial trajectory points to obtain the initial trajectory. The extension center point determination unit is used to determine the extension center point based on the starting point and / or ending point of the initial trajectory. The extended time interval determination unit is used to determine the extended time interval based on the capture time of the extended center point and the target time interval. The extension point determination unit is used to collect data from the second node that has a positional matching relationship with the extension center point to determine the extension point within the extension time interval for the capture time. The extended trajectory generation unit is used to connect the extended points to obtain the extended trajectory.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the trajectory determination method for a moving target according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the trajectory determination method for a moving target as described in any one of claims 1-5.

Images