Data processing method and device, equipment and storage medium
By obtaining and matching the historical trajectory data and the first trajectory data of the target object, the problem of difficult to maintain detection target consistency is solved, data consistency and accuracy in the target tracking process is achieved, and data fusion processing is simplified.
Patent Information
- Application Number
- CN202411800075.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-09
- Publication Date
- 2025-03-28
AI Technical Summary
The prior art is difficult to accurately maintain the consistency of detection targets, resulting in data confusion during target tracking.
By obtaining the historical trajectory data and the first trajectory data of the target object, the matching relationship between the two is determined, the historical trajectory data is updated based on the first trajectory data, the third trajectory data is obtained, and the data is output. This method uses Hungarian matching algorithm and time alignment processing to ensure the consistency of trajectory data.
Effectively maintain the consistency of the detection target, improve the accuracy of the target tracking process, eliminate the need for additional data collection and model training, and simplify sensor data fusion processing.
Smart Images
Figure CN119719124A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a data processing method, apparatus, device and storage medium. Background Art
[0002] In recent years, vehicle networking technology has become one of the solutions to solve traffic congestion and traffic safety problems, and the roadside perception system is an important part of the vehicle networking system. Among them, the roadside perception system can include sensors, such as at least one of a camera, a millimeter-wave radar, and a lidar.
[0003] In practical applications, if the sensing areas of various sensors overlap, the data detected by the sensors needs to be fused to achieve consistency in the target tracking process and avoid data confusion caused by switching between different detection targets. However, the current means of fusing the data detected by sensors has defects, which makes it impossible to accurately maintain the consistency of the detection targets. Summary of the invention
[0004] The embodiments of the present application provide a data processing method, apparatus, device and storage medium to maintain the consistency of detected targets, thereby improving the accuracy of the target tracking process.
[0005] In a first aspect, an embodiment of the present application provides a data processing method, including:
[0006] Acquire historical trajectory data and first trajectory data of the target object;
[0007] Determining that there is a matching relationship between the first trajectory data and second trajectory data in the historical trajectory data;
[0008] Update the second trajectory data based on the first trajectory data to obtain third trajectory data;
[0009] The third trajectory data is output.
[0010] Optionally, the determining that the first trajectory data has a matching relationship with second trajectory data in the historical trajectory data includes:
[0011] Determine the distances between the first trajectory data and the second trajectory data at a plurality of time points, respectively, wherein the time difference between the plurality of time points is greater than a second preset time length and less than a third preset time length;
[0012] Determine an average distance between the first trajectory data and the second trajectory data based on distances between the first trajectory data and the second trajectory data at a plurality of time points;
[0013] A Hungarian matching algorithm is applied to determine, based on the average distance, that a matching relationship exists between the first trajectory data and the second trajectory data.
[0014] Optionally, the method further comprises:
[0015] When the average distance is greater than a preset distance, the matching relationship between the first trajectory data and the second trajectory data is cancelled.
[0016] Optionally, the determining that the first trajectory data has a matching relationship with second trajectory data in the historical trajectory data includes:
[0017] Performing time alignment processing on the first trajectory data to obtain processed first trajectory data;
[0018] When the generation time of the first trajectory data is less than the first preset time, it is determined that there is a matching relationship between the processed first trajectory data and the second trajectory data.
[0019] Optionally, the method further comprises:
[0020] When the time length during which the first trajectory data is not updated is greater than the first preset time length, the matching relationship between the first trajectory data and the second trajectory data is cancelled.
[0021] Optionally, the method further comprises:
[0022] When the generation time of the first trajectory data is longer than the first preset time, generating fourth trajectory data based on the processed first trajectory data;
[0023] A matching relationship between the processed first trajectory data and the fourth trajectory data is established.
[0024] Optionally, obtaining first trajectory data of the target object includes:
[0025] receiving target detection data, wherein the target detection data includes identification information and trajectory detection data of a target object;
[0026] According to the identification information, searching the historical trajectory data for trajectory data that matches the trajectory detection data;
[0027] In a case where it is determined that the trajectory detection data matches the fifth trajectory data in the historical trajectory data, updating the fifth trajectory data based on the trajectory detection data to obtain the first trajectory data;
[0028] When it is determined that the trajectory detection data does not match any trajectory data in the historical trajectory data, the trajectory detection data is used as the first trajectory data.
[0029] In a second aspect, an embodiment of the present application provides a data processing device, including:
[0030] A data acquisition module, used to acquire historical trajectory data and first trajectory data of a target object;
[0031] a relationship determination module, configured to determine whether the first trajectory data has a matching relationship with the second trajectory data in the historical trajectory data;
[0032] a data updating module, configured to update the second trajectory data based on the first trajectory data to obtain third trajectory data;
[0033] A data output module is used to output the third trajectory data.
[0034] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising: a processor, a memory, and a system bus;
[0035] The processor and the memory are connected via the system bus;
[0036] The memory is used to store a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes any implementation step of the above-mentioned data processing method based on weak measurement technology.
[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on an electronic device, the electronic device executes any implementation step of the above-mentioned data processing method based on weak measurement technology.
[0038] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:
[0039] In an embodiment of the present application, after acquiring the historical trajectory data and the first trajectory data of the target object, it can be determined that there is a matching relationship between the first trajectory data and the second trajectory data in the historical trajectory data; then, the second trajectory data can be updated based on the first trajectory data to obtain the third trajectory data, and the third trajectory data can be output. It can be seen that when it is determined that the first trajectory data and the second trajectory data obtained historically have a matching relationship, it can be shown that the first trajectory data and the second trajectory data are both trajectory data for the same target object. Therefore, updating the second trajectory data through the first trajectory data can fuse the trajectory data of the same target object, thereby maintaining the consistency of the target object, that is, the detection target, during the target tracking process. In addition, there is no need for additional data collection and model training. Only the trajectory data detected by the sensor can maintain the consistency of the detection target, and there is no need to distinguish the types of sensors or divide the sensor's perception area, which helps to improve the detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 A schematic diagram of a roadside perception system provided in an embodiment of the present application;
[0041] Figure 2 A flowchart of a data processing method provided in an embodiment of the present application;
[0042] Figure 3 A schematic diagram of a data structure provided in an embodiment of the present application;
[0043] Figure 4 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0044] As mentioned above, combined with Figure 1 As shown, the roadside perception system may include sensors, such as at least one of a camera, a millimeter wave radar, and a laser radar. If the perception areas of the sensors overlap, the data detected by the sensors need to be fused. However, currently, there are defects in the means of fusing the data detected by the sensors.
[0045] For example, the method of hard cutting of the sensing area can be adopted, that is, the sensing areas of adjacent sensors are divided so that they are adjacent but not overlapping, so that the detection target is detected by only a single sensor in different areas. In this way, it is possible to effectively avoid the sensors in the roadside sensing system from repeatedly detecting the detection target. However, when the detection target crosses the sensing area, since it is detected by different sensors, it is actually impossible to maintain the continuity of the detection target, that is, the consistency of the detection target cannot be maintained.
[0046] For another example, deep learning algorithms can be used to learn the features of different sides of the detection target, so as to identify the same detection target from the data detected by different sensors to maintain the consistency of the detection target. However, deep learning algorithms require a large amount of data and time for training, have low detection efficiency, and cannot well introduce data from millimeter-wave radar or lidar, which has high limitations.
[0047] Based on this, in order to solve the above problem, an embodiment of the present application provides a data processing method, which may include: after acquiring historical trajectory data and first trajectory data of a target object, it may be determined that there is a matching relationship between the first trajectory data and second trajectory data in the historical trajectory data; then, the second trajectory data may be updated based on the first trajectory data to obtain third trajectory data, and the third trajectory data may be output.
[0048] It can be seen that when it is determined that the first trajectory data and the second trajectory data obtained historically have a matching relationship, it can be shown that the first trajectory data and the second trajectory data are both trajectory data for the same target object. Therefore, updating the second trajectory data through the first trajectory data can fuse the trajectory data of the same target object, thereby maintaining the consistency of the target object, that is, the detection target, during the target tracking process. In addition, there is no need for additional data collection and model training. Only the trajectory data detected by the sensor can maintain the consistency of the detection target, and there is no need to distinguish the types of sensors or divide the sensor's perception area, which helps to improve the detection efficiency.
[0049] It should be noted that the embodiments of the present application may not limit the execution subject of the data processing method. For example, the data processing method of the embodiments of the present application may be applied to data processing devices such as terminal devices or servers. Among them, the terminal device may be an electronic device such as a smart phone, a computer, a personal digital assistant (PDA), a tablet computer, etc. The server may be an independent server, a cluster server, or a cloud server.
[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0051] Figure 2 A flowchart of a data processing method provided in an embodiment of the present application. Figure 2As shown, the data processing method provided in the embodiment of the present application takes the corresponding data processing device as the execution subject to describe the specific implementation of the scheme. The data processing method may include the following steps S201-S204.
[0052] S201: Acquire historical trajectory data and first trajectory data of a target object.
[0053] The target object is the detection target mentioned above, for example, a vehicle. The first track data of the target object refers to the latest track data of the target object.
[0054] The historical trajectory data refers to the trajectory data acquired historically, and the historical trajectory data may come from different objects. The historical trajectory data may include the second trajectory data.
[0055] For ease of understanding, a process of obtaining the first trajectory data is first described below in conjunction with a possible implementation manner.
[0056] As a possible implementation, the process of acquiring the first trajectory data, that is, step S201, may include the following steps 11-14.
[0057] Step 11: Receive target detection data.
[0058] Among them, combined Figure 3 As shown, the target detection data (i.e. Figure 3 The object in the roadside perception system may include identification information of the target object and trajectory detection data. The trajectory detection data refers to data detected by sensors in the roadside perception system and used to represent the trajectory of the target object, such as location information, timestamp information, speed information, or heading angle information.
[0059] Step 12: According to the identification information, search the historical trajectory data for trajectory data that matches the trajectory detection data.
[0060] Here, the trajectory detection data may be matched according to the identification information of the target object so as to maintain the uniqueness of the target object.
[0061] Step 13: When it is determined that the trajectory detection data matches the fifth trajectory data in the historical trajectory data, the fifth trajectory data is updated based on the trajectory detection data to obtain the first trajectory data.
[0062] It can be seen that when the trajectory detection data matches the fifth trajectory data in the historical trajectory data, it can be indicated that the historical trajectory data already has the detection data of the target object. Therefore, the trajectory detection data can be used to update the fifth trajectory data to obtain the latest trajectory data, that is, the first trajectory data.
[0063] Step 14: When it is determined that the trajectory detection data does not match any trajectory data in the historical trajectory data, the trajectory detection data is used as the first trajectory data.
[0064] It can be seen that when the trajectory detection data does not match any trajectory data in the historical trajectory data, it can be indicated that there is no detection data of the target object in the historical trajectory data. Therefore, the trajectory detection data can be used as the latest trajectory data of the target object, that is, the first trajectory data.
[0065] In addition, it should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.
[0066] S202: Determine whether the first trajectory data has a matching relationship with the second trajectory data in the historical trajectory data.
[0067] In the embodiment of the present application, after the first trajectory data is generated, the first trajectory data can be time-aligned to obtain the processed first trajectory data, and the processed first trajectory data is stored in the trajectory pool to be matched and wait for matching. The time alignment process can enable different trajectory data at the same time point to be fused with the first trajectory data, thereby improving the consistency of the data.
[0068] Specifically, the time alignment processing method can be embodied as follows: according to the latest time of the sensor, the position coordinates of all trajectory data are updated using an interpolation method to unify the latest detection time of all trajectory data. The interpolation method may include at least one of linear interpolation, polynomial interpolation, spline interpolation and Kalman filtering, which is not specifically limited here.
[0069] Next, when the generation time of the first trajectory data is less than the first preset time, the processed first trajectory data can be obtained from the trajectory pool to be matched, and it can be determined that the processed first trajectory data and the second trajectory data have a matching relationship. The generation time of the first trajectory data is the life span of the first trajectory data, and the first preset time span can be half a frame interval. In other words, when the life span of the first trajectory data is less than half a frame interval, it can be indicated that the first trajectory data has not been matched with the historical trajectory data in a short period of time. Therefore, the processed first trajectory data can be matched with the data in the historical trajectory data to determine that it has a matching relationship with the second trajectory data.
[0070] Accordingly, when the generation time of the first trajectory data is longer than the first preset time, the fourth trajectory data can be generated based on the processed first trajectory data, and a matching relationship between the processed first trajectory data and the fourth trajectory data can be established. That is to say, when the life span of the first trajectory data is longer than half a frame interval, it can be indicated that the first trajectory data has not been matched with the historical trajectory data for a long period of time, and there may be no data in the historical trajectory data that has a matching relationship with the first trajectory data. Therefore, the fourth trajectory data can be generated based on the processed first trajectory data, and the two can be matched to determine that the processed first trajectory data and the fourth trajectory data have a matching relationship. Accordingly, the first trajectory data and the second trajectory data are both trajectory data for the same target object, and therefore, the fourth trajectory data can be output later to maintain the consistency of the target object.
[0071] Furthermore, the process of determining whether the first trajectory data and the second trajectory data in the historical trajectory data have a matching relationship may be implemented by using a Hungarian matching algorithm. For ease of understanding, a possible implementation is described below.
[0072] In one possible implementation, combining Figure 3 As shown, the first trajectory data (i.e. Figure 3 The second track data (i.e., the SubTrack in the target object) includes the identification information of the target object, the timestamp information, and the track detection data corresponding to the target object in the form of a time series. Figure 3 The MainTrack in the data includes the identification information of the target object, the latest updated trajectory data in the form of a time series, the matching relationship between the trajectory data, etc. It can be seen that time series are stored in both the first trajectory data and the second trajectory data. Therefore, first, the distances between the first trajectory data and the second trajectory data at multiple time points can be determined. Among them, when the time difference between multiple time points is greater than the second preset time length and less than the third preset time length, and the time difference between multiple time points is less than the second preset time length, it is considered to be a unified time. Therefore, the above-mentioned multiple time points are adjacent but not at the same time. In addition, the number of multiple time points is, for example, 8, 10 or 12, etc., which is no longer limited here.
[0073] Next, an average distance between the first trajectory data and the second trajectory data may be determined based on the distances between the first trajectory data and the second trajectory data at a plurality of time points.
[0074] Then, the Hungarian matching algorithm can be applied to determine whether there is a matching relationship between the first trajectory data and the second trajectory data based on the average distance. That is, the average distance is used as the data of the Hungarian matching algorithm, and the Hungarian matching algorithm is applied to perform trajectory matching.
[0075] S203: updating the second trajectory data based on the first trajectory data to obtain third trajectory data.
[0076] In actual applications, since the sensing areas of multiple sensors, such as the first sensor and the second sensor, have overlapping areas, the target object will be recognized by the first sensor and the second sensor in the overlapping sensing area and multiple detection trajectory data will be generated. In this way, the second trajectory data can be the detection trajectory data generated by the first sensor in the past, and the first trajectory data can be generated by the second sensor after the target object enters the overlapping sensing area. Therefore, after determining that the first trajectory data and the second trajectory data have a matching relationship, it can be shown that both are trajectory data of the target object. Therefore, the first trajectory data can be used to update the second trajectory data to obtain the third trajectory data. In addition, it can be shown that the trajectory data subsequently generated by the first sensor and the second sensor can be used to update the second trajectory data.
[0077] S204: Output third trajectory data.
[0078] Based on the relevant contents of the above steps S201 to S204, it can be known that in the embodiment of the present application, after obtaining the historical trajectory data and the first trajectory data of the target object, it can be determined that there is a matching relationship between the first trajectory data and the second trajectory data in the historical trajectory data; then, the second trajectory data can be updated based on the first trajectory data to obtain the third trajectory data, and the third trajectory data can be output. It can be seen that when it is determined that the first trajectory data and the second trajectory data obtained historically have a matching relationship, it can be shown that the first trajectory data and the second trajectory data are both trajectory data for the same target object. Therefore, updating the second trajectory data through the first trajectory data can fuse the trajectory data of the same target object, thereby maintaining the consistency of the target object, that is, the detection target, during the target tracking process. In addition, there is no need for additional data collection and model training. Only the trajectory data detected by the sensor can maintain the consistency of the detection target, and there is no need to distinguish the types of sensors or divide the sensor's perception area, which helps to improve the detection efficiency.
[0079] In addition, after each update, the existing matching relationship may be verified to remove invalid matching relationships. For ease of understanding, the following is an explanation in conjunction with a variety of possible implementations.
[0080] As a possible implementation, taking the matching relationship between the first trajectory data and the second trajectory data as an example, when the average distance between the first trajectory data and the second trajectory data is greater than a preset distance, the matching relationship between the first trajectory data and the second trajectory data can be cancelled. For example, the preset distance can be half a lane width or 1 lane width. When the above average distance is greater than the preset distance, it can be considered that the matching relationship between the first trajectory data and the second trajectory data is a mismatch. Therefore, the matching relationship between the two can be cancelled, and the first trajectory data can be stored in the trajectory pool to be matched and wait for re-matching.
[0081] As another possible implementation, still taking the matching relationship between the first trajectory data and the second trajectory data as an example, when the time length of the first trajectory data not being updated is greater than the first preset time length, the matching relationship between the first trajectory data and the second trajectory data can be cancelled. In other words, when the first trajectory data is not updated for a long time, it can be considered that the first trajectory data is invalid. Therefore, the matching relationship between the two can be cancelled, and the first trajectory data can be stored in the trajectory pool to be matched and wait for re-matching.
[0082] Furthermore, based on the data processing method provided in the above embodiment, the embodiment of the present application can also provide a data processing device. The data processing device is described below in conjunction with the embodiments and drawings.
[0083] Figure 4 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application. Figure 4 As shown, the data processing device 400 provided in the embodiment of the present application may include:
[0084] A data acquisition module 401 is used to acquire historical trajectory data and first trajectory data of a target object;
[0085] A relationship determination module 402, configured to determine whether the first trajectory data has a matching relationship with the second trajectory data in the historical trajectory data;
[0086] A data updating module 403 is used to update the second trajectory data based on the first trajectory data to obtain third trajectory data;
[0087] The data output module 404 is configured to output the third trajectory data.
[0088] Optionally, the relationship determination module 402 is specifically configured to:
[0089] Determine the distances between the first trajectory data and the second trajectory data at a plurality of time points, respectively, wherein the time difference between the plurality of time points is greater than a second preset time length and less than a third preset time length;
[0090] Determine an average distance between the first trajectory data and the second trajectory data based on distances between the first trajectory data and the second trajectory data at a plurality of time points;
[0091] A Hungarian matching algorithm is applied to determine, based on the average distance, that a matching relationship exists between the first trajectory data and the second trajectory data.
[0092] Optionally, the data processing device 400 further includes:
[0093] The relationship removal module is used to remove the matching relationship between the first trajectory data and the second trajectory data when the average distance is greater than a preset distance.
[0094] Optionally, the relationship determination module 402 is specifically configured to:
[0095] Performing time alignment processing on the first trajectory data to obtain processed first trajectory data;
[0096] When the generation time of the first trajectory data is less than the first preset time, it is determined that there is a matching relationship between the processed first trajectory data and the second trajectory data.
[0097] Optionally, the relationship removal module is further used to:
[0098] When the time length during which the first trajectory data is not updated is greater than the first preset time length, the matching relationship between the first trajectory data and the second trajectory data is cancelled.
[0099] Optionally, the data processing device 400 further includes:
[0100] A data generating module, configured to generate fourth trajectory data based on the processed first trajectory data when the generation time of the first trajectory data is greater than the first preset time;
[0101] The relationship establishing module is used to establish a matching relationship between the processed first trajectory data and the fourth trajectory data.
[0102] Optionally, the data acquisition module 401 is specifically used for:
[0103] receiving target detection data, wherein the target detection data includes identification information and trajectory detection data of a target object;
[0104] According to the identification information, searching the historical trajectory data for trajectory data that matches the trajectory detection data;
[0105] In a case where it is determined that the trajectory detection data matches the fifth trajectory data in the historical trajectory data, updating the fifth trajectory data based on the trajectory detection data to obtain the first trajectory data;
[0106] When it is determined that the trajectory detection data does not match any trajectory data in the historical trajectory data, the trajectory detection data is used as the first trajectory data.
[0107] Furthermore, an embodiment of the present application also provides an electronic device, comprising: a processor, a memory, and a system bus;
[0108] The processor and the memory are connected via the system bus;
[0109] The memory is used to store one or more programs, and the one or more programs include instructions. When the instructions are executed by the processor, the processor executes any implementation step of the above-mentioned data processing method.
[0110] Furthermore, an embodiment of the present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on an electronic device, any step of the above-mentioned data processing method is implemented.
[0111] It can be known from the description of the above implementation mode that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a storage medium, such as ROM / RAM, a disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in each embodiment of the present application or certain parts of the embodiments. It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.
[0112] As for the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.
[0113] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0114] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A data processing method, characterized in that: include: Acquire historical trajectory data and first trajectory data of the target object; Determining that there is a matching relationship between the first trajectory data and second trajectory data in the historical trajectory data; Update the second trajectory data based on the first trajectory data to obtain third trajectory data; The third trajectory data is output.
2. The data processing method according to claim 1, characterized in that: The determining that the first trajectory data has a matching relationship with the second trajectory data in the historical trajectory data includes: Determine the distances between the first trajectory data and the second trajectory data at a plurality of time points, respectively, wherein the time difference between the plurality of time points is greater than a second preset time length and less than a third preset time length; Determine an average distance between the first trajectory data and the second trajectory data based on distances between the first trajectory data and the second trajectory data at a plurality of time points; A Hungarian matching algorithm is applied to determine, based on the average distance, that a matching relationship exists between the first trajectory data and the second trajectory data.
3. The data processing method according to claim 2, characterized in that: The method further comprises: When the average distance is greater than a preset distance, the matching relationship between the first trajectory data and the second trajectory data is cancelled.
4. The data processing method according to claim 1, characterized in that: The determining that the first trajectory data has a matching relationship with the second trajectory data in the historical trajectory data includes: Performing time alignment processing on the first trajectory data to obtain processed first trajectory data; When the generation time of the first trajectory data is less than the first preset time, it is determined that there is a matching relationship between the processed first trajectory data and the second trajectory data.
5. The data processing method according to claim 4, characterized in that: The method further comprises: When the time length during which the first trajectory data is not updated is greater than the first preset time length, the matching relationship between the first trajectory data and the second trajectory data is cancelled.
6. The data processing method according to claim 4, characterized in that: The method further comprises: When the generation time of the first trajectory data is longer than the first preset time, generating fourth trajectory data based on the processed first trajectory data; A matching relationship between the processed first trajectory data and the fourth trajectory data is established.
7. The data processing method according to any one of claims 1 to 6, characterized in that: Obtaining first trajectory data of a target object includes: receiving target detection data, wherein the target detection data includes identification information and trajectory detection data of a target object; According to the identification information, searching the historical trajectory data for trajectory data that matches the trajectory detection data; In a case where it is determined that the trajectory detection data matches the fifth trajectory data in the historical trajectory data, updating the fifth trajectory data based on the trajectory detection data to obtain the first trajectory data; When it is determined that the trajectory detection data does not match any trajectory data in the historical trajectory data, the trajectory detection data is used as the first trajectory data.
8. A data processing device, characterized in that: include: A data acquisition module, used to acquire historical trajectory data and first trajectory data of a target object; a relationship determination module, configured to determine whether the first trajectory data has a matching relationship with the second trajectory data in the historical trajectory data; a data updating module, configured to update the second trajectory data based on the first trajectory data to obtain third trajectory data; A data output module is used to output the third trajectory data.
9. An electronic device, characterized in that: The device includes: a processor, a memory, and a system bus; The processor and the memory are connected via the system bus; The memory is used to store a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the steps of the data processing method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is executed by a terminal device, the steps of the data processing method according to any one of claims 1 to 7 are implemented.