Traffic data identification method and device, electronic equipment, storage medium and program

Abstract

This invention discloses a traffic data identification method, device, electronic device, storage medium, and program. The method includes: acquiring at least one valid trajectory data set, and constructing a trajectory point data set based on the height and location data of the trajectory points within the valid trajectory data set; clustering the trajectory points within the trajectory point data set according to their location and height data, and determining the height level based on the clustering results; associating the trajectory points within the trajectory point data set with the height levels to obtain trajectory height data; determining the initial height level for incorporating road data based on the trajectory direction of the valid trajectory data, and filtering the road data incorporated at the initial height level based on the trajectory height data to obtain multi-height-level road incorporation results. This invention, through vehicle trajectory identification and height-level road incorporation, achieves automated annotation of traffic data, improving the intelligence and standardization of traffic data annotation.

Description

Technical Field

[0001] This invention relates to the field of computer application technology, and in particular to traffic data identification methods, devices, electronic devices, storage media, and programs. Background Technology

[0002] With the development of electronic technology, intelligent vehicles have gradually transitioned from assisted driving to intelligent driving. Especially since the beginning of the 21st century, rapid advancements in sensor, computer, and communication technologies have provided a solid technological foundation for the development of intelligent vehicles, leading to significant breakthroughs in autonomous driving technology. Major automakers and technology companies have increased their R&D investment, and some vehicles have already achieved highly automated driving functions. The accuracy of intelligent driving's traffic situation recognition directly impacts the user's driving experience. Currently, the determination of complex traffic scenarios still requires manual calibration. Taking multi-level road merging as an example, it requires manually traversing all road network areas to collect tunnel locations, resulting in high labor and time costs, low accuracy of the labeled locations, and inconsistent labeling standards, leading to insufficient reliability of the labeled data and affecting the driving safety of intelligent vehicles. Summary of the Invention

[0003] This invention provides a traffic data identification method, device, electronic device, storage medium, and program to identify the height level of vehicle trajectory data and integrate it into the road, thereby achieving automated labeling of traffic data. This improves the intelligence and standardization of traffic data labeling and helps enhance the safety of intelligent vehicle operation.

[0004] According to one aspect of the present invention, a traffic data identification method is provided, wherein the method includes:

[0005] Obtain at least one valid trajectory data, and construct a trajectory point data set based on the height data and position data of the trajectory points within the valid trajectory data;

[0006] The trajectory points within the trajectory point dataset are clustered according to the location data and the height data, and the height level is determined based on the clustering results;

[0007] The trajectory points in the trajectory point data set are associated with the height level to obtain trajectory height data;

[0008] Based on the trajectory direction of the effective trajectory data, the initial height level of the merged road data is determined, and the merged road data at the initial height level is filtered based on the trajectory height data to obtain multi-height level merged road results.

[0009] According to another aspect of the present invention, a traffic data identification device is provided, wherein the device comprises:

[0010] The trajectory data module is used to acquire at least one valid trajectory data and construct a trajectory point data set based on the height data and position data of the trajectory points within the valid trajectory data.

[0011] The height hierarchy module is used to cluster the trajectory points in the trajectory point data set according to the position data and the height data, and determine the height hierarchy based on the clustering results;

[0012] The height association module is used to associate the trajectory points in the trajectory point data set with the height level to obtain trajectory height data;

[0013] The road determination module is used to determine the initial height level of the merged road data based on the trajectory direction of the effective trajectory data, and to filter the merged road data at the initial height level based on the trajectory height data to obtain a multi-height level merged road result.

[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, which enables the at least one processor to perform the traffic data identification method 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 traffic data identification method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer program product is provided, wherein the computer program product includes a computer program that, when executed by a processor, implements the traffic data identification method according to any embodiment of the present invention.

[0020] The technical solution of this invention involves acquiring valid trajectory data and extracting the height and position data of trajectory points within the valid trajectory data to form a trajectory point data set. The trajectory points within the data set are then clustered according to their height and position data, and a height level is determined based on the clustering results. The trajectory points within the set are then associated with their corresponding height levels to obtain trajectory height data. Using the valid trajectory data, an initial height level is determined within the valid trajectory data based on the trajectory direction and incorporated into road data. This initial height level road data is then filtered using the trajectory height data to obtain multi-height-level road incorporation results. This invention achieves automated traffic data labeling by identifying height levels in vehicle trajectory data, improving the intelligence and standardization of traffic data labeling, and contributing to enhanced safety for intelligent vehicles.

[0021] 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

[0022] 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.

[0023] Figure 1 This is a flowchart of a traffic data identification method provided in Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of another traffic data identification method provided in Embodiment 2 of the present invention;

[0025] Figure 3 This is a flowchart of another traffic data identification method provided in Embodiment 3 of the present invention;

[0026] Figure 4 This is a flowchart of another traffic data identification method provided in Embodiment 4 of the present invention;

[0027] Figure 5 This is an example diagram of another traffic data identification method provided in Embodiment 5 of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of a traffic data identification device according to Embodiment Six of the present invention;

[0029] Figure 7This is a schematic diagram of the structure of an electronic device that implements the traffic data recognition method of this invention. Detailed Implementation

[0030] 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.

[0031] 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 interchanged 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 apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flowchart of a traffic data identification method according to Embodiment 1 of the present invention. This embodiment is applicable to the case of automated identification of roads with high-level merging. The method can be executed by a traffic data identification device, which can be implemented in hardware and / or software, and can be configured in a server or vehicle terminal. Figure 1 As shown, the method includes:

[0034] Step 110: Obtain at least one valid trajectory data and construct a trajectory point data set based on the height and position data of the trajectory points within the valid trajectory data.

[0035] The effective trajectory data can be pre-collected vehicle driving trajectories. This data can be collected by the vehicle itself or provided by an external data team. The effective trajectory data can undergo preprocessing, which may include data cleaning, smoothing, coordinate transformation, densification, and sparsification. Trajectory points can be undetermined position points on the trajectory of a moving object such as an intelligent vehicle or other trajectory data acquisition device. These position points reflect the instantaneous state of the moving object at a given moment. Trajectory points can include location information, time information, speed information, and altitude information. Altitude data can be the altitude of each trajectory point at a given moment. Location data can be information indicating the spatial location of a trajectory point at a given moment, including geographic coordinate data, planar coordinate data, and relative position data. The trajectory point dataset can be a dataset constructed from the trajectory points of each effective trajectory data set. The trajectory point dataset can include at least the altitude and location data of all trajectory points within each effective trajectory data set. It is understood that each set of altitude and location data within the trajectory point dataset can have a unique correspondence with its corresponding trajectory point. For example, each set of height and location data can be stored in association with the trajectory point number of its corresponding trajectory point.

[0036] In this embodiment of the invention, one or more valid trajectory data provided by an intelligent vehicle or an external data team can be read. The height data and position data of each trajectory point can be extracted sequentially from each valid trajectory data. The height data and position data of all extracted trajectory points can be saved as a trajectory point data set. It is understood that the trajectory point data set may include the height data and position data of all trajectory points in multiple valid trajectory data.

[0037] Step 120: Cluster the trajectory points in the trajectory point dataset according to their location and height data, and determine the height level based on the clustering results.

[0038] Clustering can be achieved by grouping the height and position data of all trajectory points within a trajectory point dataset. Clustering can be implemented using algorithms such as K-Means, DBSCAN, and hierarchical clustering. The clustering result can include clusters and discrete points. Clusters can be datasets composed of trajectory points that conform to certain classification rules, while discrete points can be isolated trajectory points within the corresponding data space. Height level refers to the height range of trajectory points within different clusters and the height range of discrete points within the clustering result. The height level can be obtained through statistical analysis of the clustering results.

[0039] In this embodiment of the invention, different trajectory points within the trajectory point dataset can be clustered according to their height and position data to obtain the clustering results of the trajectory point dataset. Statistical analysis can be performed on the height data of the clusters and discrete points in the clustering results to obtain the height hierarchy.

[0040] Step 130: Associate the trajectory points in the trajectory point data set with the height level to obtain the trajectory height data.

[0041] The trajectory height data can be a collection of trajectory point data with height hierarchy. Each trajectory point in the trajectory height data can have height data, location data, and height hierarchy.

[0042] In this embodiment of the invention, height data and location data within a trajectory point dataset can be associated with corresponding trajectory points and determined by clustering results to form a height level. The associated height data, location data, and height levels can then be stored as trajectory height data. For example, the trajectory points corresponding to the height data and location data within the trajectory point dataset can be determined. The corresponding height level value of each trajectory point within a height level can be determined, and this height level value can be associated with and stored in the trajectory height data along with the height data and location data of the trajectory point.

[0043] Step 140: Determine the initial height level of the merged road data based on the trajectory direction of the valid trajectory data, and filter the initial height level merged road data based on the trajectory height data to obtain multi-height level merged road results.

[0044] The trajectory direction can be the direction of travel of the valid trajectory data. The trajectory direction can be determined based on the position data of different trajectory points within the valid trajectory data. The initial height level merging road data can be data representing the height level merging road. The height level merging road can include roads from multiple different height levels merging into each other.

[0045] In this embodiment of the invention, the trajectory direction of the valid trajectory data can be filtered to determine the valid trajectory data with multiple trajectory directions as the initial height level road data. The initial height level road data can be filtered by the height level in the trajectory height data to determine the initial height level road data with multiple height levels. The initial height level road data with multiple height levels can be used as the multi-height level road data result.

[0046] This invention, in its embodiments, acquires valid trajectory data and extracts the height and position data of trajectory points within this data to form a trajectory point dataset. The trajectory points within this dataset are then clustered, and height levels are determined based on the clustering results. The trajectory points are then associated with their corresponding height levels to obtain trajectory height data. Using this valid trajectory data, an initial height level is determined based on the trajectory direction and incorporated into road data. This initial height level road data is then filtered using the trajectory height data to obtain multi-height-level road incorporation results. This invention, by identifying height levels in vehicle trajectory data and incorporating them into roads, achieves automated traffic data labeling, improving the intelligence and standardization of traffic data labeling, and ultimately enhancing the safety of intelligent vehicle operation.

[0047] Example 2

[0048] Figure 2 This is a flowchart of another traffic data identification method provided in Embodiment 2 of the present invention. The embodiments of the present invention are specific modifications based on the above embodiments. See also... Figure 2 The method provided in this embodiment of the invention specifically includes the following steps:

[0049] Step 210: Obtain the crowdsourced trajectory dataset; for each trajectory in the crowdsourced trajectory dataset, calculate the distance and time difference between adjacent trajectory points within the trajectory, and use the ratio of distance to time difference as the real-time speed value of the current trajectory point within the adjacent trajectory points.

[0050] The crowdsourced trajectory dataset can be a trajectory dataset provided by a third-party data team. It can include one or more trajectories, each of which can include at least two trajectory points' height, location, and time data. Distance can be the relative distance between the location data of different trajectory points, time difference can be the relative time distance between the time data of different trajectory points, adjacent trajectory points can be two adjacent trajectory points within a single trajectory in the crowdsourced trajectory dataset, and the current trajectory point can be the adjacent trajectory point with the later time data.

[0051] In this embodiment of the invention, a crowdsourced trajectory dataset provided by a third-party data team can be obtained. One or more trajectories can be extracted from the crowdsourced trajectory dataset. All adjacent trajectory points in the trajectory can be determined, and the distance and time difference can be determined for each group of adjacent trajectory points. The distance can be the distance between the position data of two trajectory points belonging to adjacent trajectory points, and the time difference can be the time difference between the time point data of two trajectory points belonging to adjacent trajectory points. For a group of adjacent trajectory points, the ratio of the distance to the time difference of the adjacent trajectory points can be used as the real-time speed value of the current trajectory point in the adjacent trajectory points.

[0052] Step 220: For each trajectory, select the current trajectory points whose real-time speed values ​​are within the preset speed range as valid trajectory points, and use the trajectory dataset composed of each valid trajectory point as valid trajectory data.

[0053] The preset speed range can be the effective speed range for determining the speed of the trajectory point, and the value of the preset speed range can be set based on experience.

[0054] In this embodiment of the invention, the real-time speed values ​​of all current trajectory points can be compared with a preset speed range for each trajectory. If the real-time speed value of the current trajectory point is within the preset speed range, the current trajectory point can be determined as a valid trajectory point. If the real-time speed value of the current trajectory point is not within the preset speed range, the current trajectory point is not a valid trajectory point. The trajectory data composed of all valid trajectory points in each trajectory can be regarded as a valid trajectory data. It can be understood that the real-time speed values ​​of the trajectory points in each valid trajectory data are all within the preset speed range.

[0055] Step 230: Extract the trajectory points within the valid trajectory data and statistically analyze the height and position data of each trajectory point.

[0056] In this embodiment of the invention, the height and position data of a trajectory point within the valid trajectory data can be statistically analyzed.

[0057] Step 240: Save the height data, location data, and trajectory point index of the trajectory points to the trajectory point data set.

[0058] The trajectory point index can be a unique identifier for the trajectory point. The trajectory point index can be set according to the order of the trajectory points in the valid trajectory data. For example, starting from the starting trajectory point, the trajectory point index can be set for all trajectory points in the valid trajectory data in the form of 0, 1, 2.

[0059] In this embodiment of the invention, the trajectory point index of the trajectory point is obtained, and the height data and position data of the trajectory point are saved to the trajectory point data set along with the trajectory point index, so that the height data and position data of each trajectory point in the trajectory point data set can be associated with the trajectory point index of the trajectory point.

[0060] Step 250: Cluster the trajectory points in the trajectory point dataset according to their location and height data, and determine the height level based on the clustering results.

[0061] Step 260: Associate the trajectory points in the trajectory point data set with the height level to obtain the trajectory height data.

[0062] Step 270: Determine the initial height level of the merged road data based on the trajectory direction of the valid trajectory data, and filter the initial height level merged road data based on the trajectory height data to obtain multi-height level merged road results.

[0063] In this embodiment of the invention, by acquiring a crowdsourced trajectory dataset, the distance and time difference between adjacent trajectory points are determined for each trajectory within the dataset. The ratio of the distance to the time difference is used as the real-time speed value of the current trajectory point within the adjacent trajectory points. The real-time speed values ​​of the current trajectory points in each trajectory are filtered through a preset speed range to obtain the valid trajectory points for each trajectory. Valid trajectory data is constructed using the valid trajectory points belonging to the same trajectory. For each trajectory point in the valid trajectory data, height and location data are statistically analyzed, and the height and location data, along with the trajectory point index, are saved to a trajectory point data set. Clustering is performed on the location and height data of each trajectory point in the trajectory point data set to obtain clustering results. The height level is determined based on the clustering results, and each trajectory point is associated with the corresponding height level to form trajectory height data. Based on the trajectory direction, an initial height level is determined within the valid trajectory data to incorporate road data. The initial height level incorporated road data is then filtered using the trajectory height data to obtain multi-height-level incorporated road results. This invention extracts valid trajectory points based on a preset speed range to form valid trajectory data, which can improve the effectiveness of valid trajectory data and help improve the accuracy of data recognition. By integrating vehicle trajectory data into the road at different height levels, it realizes automated labeling of traffic data, which can improve the intelligence and standardization of traffic data labeling and help improve the safety of intelligent vehicle driving.

[0064] Example 3

[0065] Figure 3 This is a flowchart of another traffic data identification method provided in Embodiment 3 of the present invention. This embodiment of the present invention is a concretization based on the above embodiments, describing the determination of the height level and the association process. See [link to documentation]. Figure 3 The method provided in this embodiment of the invention specifically includes the following steps:

[0066] Step 310: Obtain at least one valid trajectory data and construct a trajectory point data set based on the height and position data of the trajectory points within the valid trajectory data.

[0067] Step 320: Extract the height and position data of each trajectory point in the trajectory point dataset, and determine the coordinate position of each trajectory point in three-dimensional space according to the height and position data.

[0068] In this context, three-dimensional space can be a three-dimensional spatial coordinate system consisting of longitude, latitude, and height, and the coordinate position can be a three-dimensional spatial coordinate point consisting of longitude, latitude, and height.

[0069] In this embodiment of the invention, the height data and position data of each trajectory point in the trajectory point data set can be extracted, and the height data and position data can be converted to a three-dimensional spatial coordinate system to obtain the coordinate position in three-dimensional space. The coordinate position may include longitude, latitude, and height, etc.

[0070] For example, the location data within the trajectory point dataset can specifically be latitude and longitude coordinates, which may belong to the EPSG:4326 coordinate system. These latitude and longitude coordinates can be transformed to the EPSG:3857 coordinate system, and the longitude, latitude, and height after coordinate system transformation can be used as the coordinate position of the trajectory point in three-dimensional space.

[0071] Step 330: Perform density-based clustering for each coordinate location to obtain the clustering results.

[0072] Density-based clustering can form clusters for high-density regions in the data and treat low-density regions as discrete points or boundaries. It does not require pre-specifying the number of clusters and can detect clusters of trajectory points within a trajectory point dataset. Density-based clustering can be implemented using algorithms such as DBSACN (Density-Based Spatial Clustering of Applications with Noise) and OPTICS (Ordering Points To Identify the Clustering Structure).

[0073] In this embodiment of the invention, the coordinate positions of each trajectory point in the trajectory point dataset can be processed by a density-based clustering method. Each coordinate position can be clustered according to the density clustering parameters of the density-based clustering method to obtain clustering results. The clustering results can include clusters composed of one or more coordinate positions and discrete points. The height of the coordinate positions in the clusters can be the same or similar.

[0074] Step 340: Take the average height of the coordinate positions within the clusters in the clustering results as the first height level value of the fixed height level within the height level.

[0075] The fixed height level can be a height level determined by clustering, and the first height level value can be the height level value of each fixed height level, which can be determined by the average height of the coordinate positions in the cluster.

[0076] In this embodiment of the invention, the coordinate position of each cluster in the clustering result can be extracted, the height of the coordinate position of each cluster can be extracted, and the average height of the coordinate position within each cluster can be recorded as the first height level value generated by the cluster. The height level attribute of the first height level value is a fixed height level, that is, the first height level value is the height level value of the corresponding fixed height level.

[0077] Step 350: Use the height data of the coordinate positions of the trajectory points corresponding to the discrete points in the clustering results as the second height level value of the linearly changing height level within the height level.

[0078] Among them, the linearly varying height level can be a height level determined by discrete points, and the second height level value can be the height level value corresponding to each linearly varying height level. The value of the second height level value can be determined by the height data of the trajectory points corresponding to the discrete points.

[0079] In this embodiment of the invention, discrete points can be extracted from the clustering results, and the height data of the corresponding trajectory point can be determined for each discrete point. The height data can be used as the second height level value corresponding to the discrete point, and the second height level value can be a linearly changing height level.

[0080] Step 360: Determine the target trajectory within the valid trajectory data based on the discrete points of the clustering results, and extract the clusters of the clustering results, wherein the target trajectory consists of at least two consecutive discrete points.

[0081] The target trajectory can be a trajectory consisting of at least two consecutive discrete points. The target trajectory can be a part of the valid trajectory data corresponding to the trajectory point dataset. The target trajectory can be composed of consecutive trajectory points. The trajectory points in the target trajectory points are discrete points in the clustering results.

[0082] In this embodiment of the invention, clusters and discrete points in the clustering results can be extracted, and at least two trajectory points in the valid trajectory data can be determined as a trajectory segment. This trajectory segment can be used as the target trajectory, and the target trajectory of all valid trajectory data can be determined by the discrete points in the clustering results.

[0083] Step 370: When a trajectory point belongs to a cluster, obtain the first height level value within the height level corresponding to the cluster, and associate the first height level value with the trajectory point.

[0084] Specifically, when the trajectory points in the trajectory point dataset belong to a cluster, the first height level value of the cluster can be obtained. It can be understood that the first height level value can be determined by the average height of all trajectory points in the cluster. The first height level value of the cluster can be associated with the trajectory point. This association can include storing the first height level value in association with the height data and position data of the trajectory points in the trajectory point dataset, or setting a trajectory point index for the trajectory point for the first height level value.

[0085] Step 380: When a trajectory point belongs to the target trajectory, obtain the height data of the trajectory point, set the height data as the second height level value of the height level, and associate it with the trajectory point.

[0086] In this embodiment of the invention, when a trajectory point in the trajectory point data set belongs to a target trajectory, the height data of the trajectory point can be extracted. The height data can be used as the second height level value of the trajectory point in the trajectory point data set. The second height level value can be associated with the trajectory point. This association can include associating and storing the second height level value with the height data and position data of the trajectory point in the trajectory point data set, or setting a trajectory point index for the trajectory point for the second height level value.

[0087] Step 390: Use the height level associated with the trajectory point data set as the trajectory height data.

[0088] In this embodiment of the invention, after all the trajectory points corresponding to the trajectory point data set are associated with a height level, the associated height level can be used as the trajectory height data. That is, the trajectory height data can read the corresponding height level of each trajectory point in the trajectory point data set.

[0089] Step 3100: Determine the initial height level of the merged road data based on the trajectory direction of the valid trajectory data, and filter the initial height level merged road data based on the trajectory height data to obtain multi-height level merged road results.

[0090] In this embodiment of the invention, valid trajectory data is acquired, and the height and position data of trajectory points within the valid trajectory data are extracted to form a trajectory point data set. The height and position data of each trajectory point within the trajectory point data set are converted into coordinates in three-dimensional space, and density-based clustering is performed on these coordinates to obtain clustering results. The average height of each cluster in the clustering results is used as a first height level value, and the height data of each discrete point in the clustering results is used as a second height level value. Based on the clustering results, discrete points within the valid trajectory data are determined to include at least two consecutive... The target trajectory is obtained by continuing the clustering of the target trajectory. When a trajectory point in the trajectory point dataset belongs to a cluster, the first height level value of the cluster is associated with that trajectory point. When a trajectory point in the trajectory point dataset belongs to the target trajectory, the height data of the trajectory point is managed as the second height level value. The trajectory point dataset associated with the height level is combined into trajectory height data. Based on the trajectory direction, the initial height level is determined within the valid trajectory data to merge road data. The initial height level merged road data is then filtered using the trajectory height data to obtain multi-height level merged road results. This embodiment of the invention clusters the trajectory point dataset and determines the height level values ​​of different clusters and discrete points through clustering. The determined height level values ​​are associated with the trajectory points in the trajectory point dataset, facilitating the identification of multi-height level merged roads through height level values. This achieves automated annotation of traffic data, improves the intelligence and standardization of traffic data annotation, and helps improve the safety of intelligent vehicle driving.

[0091] Example 4

[0092] Figure 4 This is a flowchart of another traffic data identification method provided in Embodiment 4 of the present invention. This embodiment is a concretization based on the above embodiments, describing the identification process of roads merging at multiple height levels. See also... Figure 4 The method provided in this embodiment of the invention specifically includes the following steps:

[0093] Step 410: Obtain at least one valid trajectory data, and construct a trajectory point data set based on the height data and position data of the trajectory points within the valid trajectory data.

[0094] Step 420: Cluster the trajectory points in the trajectory point dataset according to their location and height data, and determine the height level based on the clustering results.

[0095] Step 430: Associate the trajectory points in the trajectory point data set with the height level to obtain the trajectory height data.

[0096] Step 440: For each valid trajectory data, determine the direction angle between two adjacent trajectory points with the first direction as 0 degrees, and take the average of each direction angle as the trajectory direction of the valid trajectory data.

[0097] The first direction can be the direction indicating 0 degrees. The first direction can be pre-configured and can include due north, due south, 45 degrees south of north, etc.

[0098] In this embodiment of the invention, the position data of each trajectory point can be extracted from the valid trajectory data. The orientation of each trajectory point can be determined based on the position data with the first direction as 0 degrees as the reference. For each valid trajectory data, all trajectory points in adjacent states are determined. For each group of trajectory points in adjacent states, the angle difference of the corresponding orientation can be determined as the direction angle of the two adjacent trajectory points. All corresponding direction angles are extracted for each valid trajectory data, and the average value of the above direction angles is taken as the trajectory direction of the valid trajectory data.

[0099] Step 450: Obtain the pre-divided direction intervals, wherein the direction intervals are generated by dividing the direction intervals with the first direction as 0 degrees and each interval threshold angle as a direction interval.

[0100] The threshold angle can be a pre-configured direction angle value. This threshold angle can be used to divide the planar space into different direction intervals. The span of the direction angle of the generated direction interval can be the threshold angle. The value of the threshold angle can be 45 degrees, 30 degrees, 60 degrees, etc.

[0101] In this embodiment of the invention, the spatial direction can be pre-divided into different directional intervals, each directional interval being a threshold degree. The directional region has a first direction as 0 degrees. After the directional intervals are divided, the directional intervals spanned by the trajectory direction of the valid trajectory data can be determined to identify the travel direction of the valid trajectory data. For example, the spatial direction can be divided into 8 directional intervals, each directional interval occupying 45 degrees.

[0102] Step 460: Determine the number of directional intervals that each valid trajectory data spans.

[0103] In this embodiment of the invention, the number of pre-divided directional intervals that the corresponding trajectory direction of each valid trajectory data can be determined. For example, if the trajectory direction is 90 degrees, it can span two 45-degree directional intervals. The number of directional intervals spanned by the trajectory direction of all valid trajectory data can be obtained, and this number of cross-domain directional intervals can be used to measure the number of communication directions for each valid trajectory data.

[0104] Step 470: Obtain target trajectory data in each valid trajectory data set that is greater than the threshold number, and extract the information of the target trajectory data from the trajectory point data set as the initial height level to be incorporated into the road data.

[0105] The threshold number can be a critical value for measuring the effective trajectory data as the multi-level road data. The threshold number can be set based on experience, and can specifically be 2.

[0106] In this embodiment of the invention, the number of directional intervals crossed by the trajectory direction of each valid trajectory data can be compared with a threshold number. When the number is greater than the threshold number, the valid trajectory data can be used as the target trajectory data. The position data and height data of the same trajectory points in the trajectory point data set can be extracted according to the target trajectory data as the initial height level and incorporated into the road data.

[0107] Step 480: Extract the target trajectory points of the initial height level imported into the road data.

[0108] In this embodiment of the invention, trajectory points from the initial height level road data can be extracted as target trajectory points. This extraction process may include extracting trajectory points from the initial height level road data in the order of the target trajectory data as target trajectory points.

[0109] Step 490: Determine the target height level associated with the target trajectory point within the trajectory height data.

[0110] In this embodiment of the invention, the height level associated with each target trajectory point can be found within the trajectory height data as the target height level. For example, the height level associated with the trajectory point identifier of the target trajectory point can be found within the trajectory height data as the target height level.

[0111] Step 4100: When the target height level includes all height levels corresponding to the clustering results, and the number of categories of the target height level is greater than 1, the initial height level is incorporated into the road data as a multi-height level incorporated road result.

[0112] Among them, "type" can refer to different level values ​​at higher levels, and / or different level types at higher levels, etc.

[0113] In this embodiment of the invention, it can be determined whether all target height levels of the road data merged into the initial height level cover all height levels corresponding to the clustering result. All height levels of the clustering result may include height levels of all height level values, or height levels of all height level types, etc. If all target height levels of the road data merged into the initial height level cover all height levels corresponding to the clustering result, and the number of target height levels is greater than 1, that is, the road data merged into the initial height level has at least two different height levels, then the road data merged into the initial height level can be regarded as a multi-height-level road merged result.

[0114] In this embodiment of the invention, valid trajectory data is acquired, and the height and position data of trajectory points within the valid trajectory data are extracted to form a trajectory point data set. The clustering results of the trajectory point data set are obtained, and the height level is determined based on the clustering results. The trajectory points within the trajectory point data set are associated with different height levels to obtain trajectory height data. The direction angles of all adjacent trajectory points within the valid trajectory data are determined, and the average of the direction angles is used as the trajectory direction of the valid trajectory data. The target trajectory data is determined within the valid trajectory data by the number of pre-divided direction intervals crossed by the trajectory direction. The initial height level is constructed and incorporated into the road data according to the information obtained from the trajectory point data set based on the target trajectory data. For the target trajectory points incorporated into the road data at the initial height level, the corresponding target height level is determined within the trajectory height data. The target height level includes all height levels corresponding to the clustering results, and the height level category of the target height level is greater than 1. Then, the road data incorporated into the road data at the initial height level is used as the multi-height-level road incorporation result. This invention determines the merging road data within the effective trajectory data by using trajectory direction, and mines the topology of the merging road data based on height level, thereby determining merging roads at multiple height levels. This improves the accuracy of road identification, enables automated labeling of traffic data, enhances the intelligence and standardization of traffic data labeling, and helps improve the safety of intelligent vehicle driving.

[0115] Furthermore, based on the above embodiments of the invention, the effective trajectory data is stored based on a trajectory point index list, which stores the indexes of the trajectory points of the effective trajectory data.

[0116] In this embodiment of the invention, each valid trajectory data can be stored in the form of an index list. The index list can store the index of the trajectory point in the valid trajectory data. The index can be used to execute the specific information of the trajectory point, such as location data, height data, and height level.

[0117] Example 5

[0118] Figure 5This is an example diagram of another traffic data identification method provided in Embodiment 5 of the present invention. See also... Figure 5 The traffic data identification method provided in this embodiment of the invention may include steps such as trajectory filtering and cleaning, trajectory point set processing, density clustering, trajectory point height hierarchical association processing, directional mining, and trajectory topology mining. Specifically, the method includes the following steps:

[0119] (1) Trajectory filtering and cleaning

[0120] a. Taking each trajectory in the crowdsourced trajectory data set within the selected area as a unit, starting from the starting trajectory point, calculate the distance and time difference between each trajectory point and the previous trajectory point. The ratio of distance to time difference can be used as the real-time speed value of the current trajectory point. The current trajectory point can be the trajectory point slightly later in time.

[0121] b. Select trajectory points whose real-time velocity values ​​are within the interval [m,n] as valid trajectory data.

[0122] (2) Trajectory point set processing

[0123] a. Using each trajectory in the valid trajectory data as a unit, store the indexes of the trajectory points in a list in the order of the trajectory points to generate a trajectory-related data set.

[0124] b. Using the trajectory points in each trajectory of the valid trajectory data as a unit, summarize the latitude, longitude and altitude data of all trajectory points to generate a trajectory point data set.

[0125] (3) Density clustering

[0126] a. The latitude and longitude coordinates of each trajectory point in the trajectory point dataset are converted from the EPSG:4326 coordinate system to the EPSG:3857 coordinate system.

[0127] b. Set the density clustering parameters: radius e, minimum number of clusters MinPts.

[0128] c. Map the longitude, latitude, and height feature data of the trajectory points to a three-dimensional space and cluster them according to the DBSCANd algorithm.

[0129] d. Use the clusters and discrete points in the clustering results data as trajectory point height level data.

[0130] (4) Trajectory point height hierarchy association processing

[0131] a. The average height value of the trajectory points contained in each independent cluster in the trajectory point height hierarchy data is calculated, and the average height value is used as the fixed height hierarchy height value of the trajectory points in that cluster.

[0132] b. Filter the trajectory associated data set to include trajectories with continuous segment clustered discrete points, and use the array of height values ​​of the continuous discrete points of the trajectory as the linearly changing level height.

[0133] (5) Trajectory Direction Mining

[0134] a. Calculate the direction angle between each pair of trajectory points in the trajectory association data, with due north as 0 degrees. The average of the direction angles is the direction angle of the trajectory association data.

[0135] b. Starting from due north as 0 degrees, divide the area into 8 intervals, each interval being 45 degrees.

[0136] c. Calculate the interval containing the direction angle of each associated data.

[0137] d. Filter valid trajectory sets containing the interval of the associated data direction angle greater than or equal to m into multi-height-level road data.

[0138] (6) Trajectory topology mining

[0139] a. Taking the roads merging at multiple height levels as units, extract the trajectory points of all trajectory-related data as a trajectory point data set.

[0140] b. For all trajectory points in the trajectory point dataset, calculate the height level of the correlation and matching of all trajectory points in the passage order.

[0141] c. Count whether multiple (>=2) height levels of a multi-height-level road are matched by the same trajectory.

[0142] d. Filter the multi-level inbound road data that contains all height levels matched by the same trajectory as the final multi-level inbound road result.

[0143] Example 6

[0144] Figure 6 This is a schematic diagram of the structure of a traffic data identification device according to Embodiment Six of the present invention. Figure 6 As shown, the device includes:

[0145] The trajectory data module 510 is used to acquire at least one valid trajectory data and construct a trajectory point data set based on the height data and position data of the trajectory points in the valid trajectory data.

[0146] The height hierarchy module 520 is used to cluster the trajectory points in the trajectory point data set according to the position data and the height data, and determine the height hierarchy based on the clustering results.

[0147] The height association module 530 is used to associate the trajectory points in the trajectory point data set with the height level to obtain trajectory height data.

[0148] The road determination module 540 is used to determine the initial height level of the merged road data based on the trajectory direction of the effective trajectory data, and to filter the initial height level merged road data based on the trajectory height data to obtain multi-height level merged road results.

[0149] In this embodiment of the invention, a trajectory data module acquires valid trajectory data and extracts the height and position data of trajectory points within the valid trajectory data to form a trajectory point data set. A height hierarchy module clusters the height and position data of the trajectory points within the trajectory point data set and determines the height hierarchy based on the clustering results. A height association module associates the trajectory points within the trajectory point set with the corresponding height hierarchy to obtain trajectory height data. A road determination module, based on the valid trajectory data and the trajectory direction, determines the initial height hierarchy within the valid trajectory data and incorporates it into road data. The road data incorporated into the initial height hierarchy is then filtered using the trajectory height data to obtain multi-height-level road incorporation results. This embodiment of the invention achieves automated labeling of traffic data by identifying height hierarchy in vehicle trajectory data, improving the intelligence and standardization of traffic data labeling, and contributing to enhanced safety for intelligent vehicles.

[0150] In some embodiments of the invention, the trajectory data module 510 includes:

[0151] The data acquisition unit is used to acquire crowdsourced trajectory datasets.

[0152] The speed determination unit is used to calculate the distance and time difference between adjacent trajectory points within each trajectory in the crowdsourced trajectory dataset, and to use the ratio of the distance to the time difference as the real-time speed value of the current trajectory point within the adjacent trajectory points.

[0153] The data cleaning unit is used to filter the current trajectory points whose real-time speed values ​​are within a preset speed range as valid trajectory points for each trajectory, and to use the trajectory dataset composed of each valid trajectory point as the valid trajectory data.

[0154] In some embodiments of the invention, the trajectory data module 510 further includes:

[0155] The data extraction unit is used to extract trajectory points within the valid trajectory data, and to count the height data and position data of each trajectory point; and to save the height data and position data along with the trajectory point index of the trajectory point into the trajectory point data set.

[0156] In some embodiments of the invention, the high-level module 520 includes:

[0157] The coordinate transformation unit is used to extract the height data and position data of each trajectory point in the trajectory point data set, and determine the coordinate position of each trajectory point in three-dimensional space according to the height data and the position data.

[0158] A clustering processing unit is used to perform density-based clustering for each of the coordinate positions to obtain the clustering results.

[0159] A fixed height unit is used to take the average height of the coordinate positions of the trajectory points within the cluster in the clustering result as the first height level value of the fixed height level within the height level.

[0160] A linearly varying height unit is used to take the height data of the coordinate positions of the trajectory points corresponding to the discrete points in the clustering results as the second height level value of the linearly varying height level within the height level.

[0161] In some embodiments of the invention, the highly correlated module 530 includes:

[0162] A clustering information unit is used to determine a target trajectory within the valid trajectory data based on the discrete points of the clustering results, and to extract the clusters of the clustering results, wherein the target trajectory consists of at least two consecutive discrete points.

[0163] The first association unit is used to obtain a first height level value within the height level corresponding to the cluster when the trajectory point belongs to the cluster, and associate the first height level value with the trajectory point.

[0164] The second association unit is used to obtain the height data of the trajectory point when the trajectory point belongs to the target trajectory, set the height data as the second height level value of the height level, and associate it with the trajectory point.

[0165] A data storage unit is used to use the height level associated with the trajectory point data set as the trajectory height data.

[0166] In some embodiments of the invention, the road determination module 540 includes:

[0167] The trajectory direction unit is used to determine the direction angle of two adjacent trajectory points with the first direction as 0 degrees for each valid trajectory data, and to take the average of the direction angles as the trajectory direction of the valid trajectory data.

[0168] A direction interval unit is used to obtain a pre-divided direction interval, wherein the direction interval is generated by dividing the direction interval with a first direction as 0 degrees and each interval threshold angle as a direction interval.

[0169] A directional cross-domain unit is used to determine the number of times the trajectory direction of each valid trajectory data crosses the directional interval.

[0170] The data determination unit is used to acquire target trajectory data with a quantity greater than a threshold within each of the valid trajectory data, and extract information of the target trajectory data from the trajectory point data set as the initial height level to be incorporated into the road data.

[0171] In some embodiments of the invention, the road determination module 540 further includes:

[0172] The trajectory extraction unit is used to extract the target trajectory points of the road data merged into the initial height level.

[0173] A hierarchy determination unit is used to determine the target height hierarchy associated with the target trajectory point within the trajectory height data.

[0174] The data verification unit is configured to, when the target height level includes all height levels corresponding to the clustering result, and the number of categories of the target height level is greater than 1, use the initial height level imported into the road data as the multi-height level imported into the road result.

[0175] In some embodiments of the invention, the valid trajectory data in the device is stored based on a trajectory point index list, which stores the indexes of the trajectory points of the valid trajectory data.

[0176] The traffic data recognition device provided in the embodiments of the present invention can execute the traffic data recognition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0177] Example 7

[0178] Figure 7 This is a schematic diagram of the structure of an electronic device implementing the traffic data recognition method of this invention. 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.

[0179] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0180] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0181] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 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 11 performs the various methods and processes described above, such as traffic data recognition methods.

[0182] In some embodiments, the traffic data identification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the traffic data identification method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the traffic data identification method by any other suitable means (e.g., by means of firmware).

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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).

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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 traffic data recognition method, characterized by, The method includes: Obtain at least one valid trajectory data, and construct a trajectory point data set based on the height data and position data of the trajectory points within the valid trajectory data; The trajectory points within the trajectory point dataset are clustered according to the location data and the height data, and the height level is determined based on the clustering results; The trajectory points in the trajectory point data set are associated with the height level to obtain trajectory height data; Based on the trajectory direction of the effective trajectory data, the initial height level of the merged road data is determined, and the merged road data at the initial height level is filtered based on the trajectory height data to obtain multi-height level merged road results.

2. The method of claim 1, wherein, The acquisition of at least one valid trajectory data includes: Obtain the crowdsourced trajectory dataset; For each trajectory in the crowdsourced trajectory dataset, the distance and time difference between adjacent trajectory points within the trajectory are calculated, and the ratio of the distance to the time difference is used as the real-time speed value of the current trajectory point within the adjacent trajectory points. For each trajectory, the current trajectory points whose real-time speed values ​​are within a preset speed range are selected as valid trajectory points, and the trajectory dataset composed of each valid trajectory point is used as the valid trajectory data.

3. The method of claim 1, wherein, The step of constructing a trajectory point data set based on the height and position data of trajectory points within the valid trajectory data includes: Extract trajectory points from the valid trajectory data, and statistically analyze the height and position data of each trajectory point; The height data, the location data, and the trajectory point index of the trajectory point are saved to the trajectory point data set.

4. The method according to claim 1, characterized in that, The process of clustering the trajectory points within the trajectory point dataset according to the location data and the height data, and determining the height level based on the clustering results, includes: Extract the height data and position data of each trajectory point in the trajectory point data set, and determine the coordinate position of each trajectory point in three-dimensional space according to the height data and the position data; Density-based clustering is performed on each of the aforementioned coordinate locations to obtain the clustering results; The average height of the coordinates of the trajectory points within the clusters in the clustering results is taken as the first height level value of the fixed height level within the height level. The height data of the coordinate positions of the trajectory points corresponding to the discrete points in the clustering results are used as the second height level value of the linearly changing height level within the height level.

5. The method of claim 1, wherein, The step of associating the trajectory points within the trajectory point data set with the height level to obtain trajectory height data includes: The target trajectory is determined within the valid trajectory data based on the discrete points of the clustering results, and the clusters of the clustering results are extracted, wherein the target trajectory consists of at least two consecutive discrete points; When the trajectory point belongs to the cluster, the first height level value within the height level corresponding to the cluster is obtained, and the first height level value is associated with the trajectory point; When the trajectory point belongs to the target trajectory, the height data of the trajectory point is obtained, the height data is set as the second height level value of the height level, and associated with the trajectory point; The height level associated with the set of trajectory points is used as the trajectory height data.

6. The method of claim 1, wherein, The process of determining the initial height level and incorporating road data based on the trajectory direction of each of the valid trajectory data includes: For each valid trajectory data, determine the direction angle between two adjacent trajectory points with the first direction as 0 degrees, and take the average of the direction angles as the trajectory direction of the valid trajectory data; Obtain a pre-divided direction interval, wherein the direction interval is generated by dividing the direction interval with a first direction as 0 degrees and each interval threshold angle as a direction interval; Determine the number of times the trajectory direction of each valid trajectory data point crosses the direction interval; Within each of the valid trajectory data, obtain target trajectory data whose quantity exceeds a threshold, and extract information from the target trajectory data set as the initial height level to incorporate road data.

7. The method according to any one of claims 1-6, characterized in that, The process of filtering the initial height-level merging road data based on the trajectory height data to obtain multi-height-level merging road results includes: Extract the target trajectory points from the road data imported at the initial height level; Determine the target height level associated with the target trajectory point within the trajectory height data; If the target height level includes all height levels corresponding to the clustering results, and the number of categories of the target height level is greater than 1, then the initial height level is incorporated into the road data as the multi-height level incorporated road result.

8. The method according to any one of claims 1-6, characterized in that, The valid trajectory data is stored based on a trajectory point index list, which stores the indexes of the trajectory points of the valid trajectory data.

9. A traffic data recognition apparatus characterized by comprising: The device includes: The trajectory data module is used to acquire at least one valid trajectory data and construct a trajectory point data set based on the height data and position data of the trajectory points within the valid trajectory data. The height hierarchy module is used to cluster the trajectory points in the trajectory point data set according to the position data and the height data, and determine the height hierarchy based on the clustering results; The height association module is used to associate the trajectory points in the trajectory point data set with the height level to obtain trajectory height data; The road determination module is used to determine the initial height level of the merged road data based on the trajectory direction of the effective trajectory data, and to filter the merged road data at the initial height level based on the trajectory height data to obtain a multi-height level merged road result.

10. An electronic device, comprising: 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 traffic data identification method according to any one of claims 1-8.

11. A computer readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the traffic data identification method according to any one of claims 1-8.

12. A computer program product, characterised in that, The computer program product comprises a computer program which, when executed by a processor, implements the traffic data recognition method according to any one of claims 1-8.

Images