Vehicle track compression method and device, vehicle and storage medium

Abstract

The invention provides a vehicle track compression method and device, a vehicle and a storage medium, and the method relates to the field of data compression, and comprises the steps: obtaining the feature information of each track point in a plurality of track points of a vehicle driving track, the feature information comprising first feature information and second feature information; determining a first track point of which the first feature information meets a first preset condition in the plurality of track points, wherein the first track point represents a reserved track point and the driving track is not segmented at the first track point; determining a second track point of which the second feature information meets a second preset condition in the plurality of track points, wherein the second track point represents a reserved track point and the driving track is segmented at the second track point; and compressing the driving track based on the first track point and the second track point to obtain a compressed track. According to the method, when the driving track is compressed, mutual influence between track characteristics can be avoided, and the track compression effect is improved.

Description

Technical Field

[0001] The present application relates to the field of data compression, and more specifically, to a vehicle trajectory compression method, device, vehicle, and storage medium in the field of data compression. Background Art

[0002] By recording and saving the vehicle's driving trajectory under different terrain conditions, it can help the vehicle plan its driving route and provide early warning information to the driver or autonomous driving system, thereby reducing the probability of accidents and improving vehicle safety.

[0003] Existing technologies typically compress trajectory based on distance and speed characteristics. However, during trajectory compression, multiple trajectory characteristics may interact with each other, leading to conflicts and affecting the compression effect. Therefore, how to prevent the mutual influence of trajectory characteristics during trajectory compression is a technical problem that needs to be solved. Summary of the Invention

[0004] The present application provides a vehicle trajectory compression method, device, vehicle, and storage medium. The method can avoid mutual influence between different types of trajectory features and improve the accuracy of trajectory compression.

[0005] In a first aspect, a vehicle trajectory compression method is provided, the method comprising:

[0006] Acquire characteristic information of each of a plurality of trajectory points of the vehicle's driving trajectory, the characteristic information including first characteristic information and second characteristic information, the first characteristic information being characteristic information unrelated to a starting point and an end point of the driving trajectory, and the second characteristic information being characteristic information related to the starting point and the end point of the driving trajectory;

[0007] Determine a first trajectory point among the plurality of trajectory points, wherein the first feature information satisfies a first preset condition, the first trajectory point indicating a retained trajectory point and the driving trajectory is not segmented at the first trajectory point;

[0008] Determine a second trajectory point among the plurality of trajectory points, wherein the second characteristic information satisfies a second preset condition, the second trajectory point being a retained trajectory point and the driving trajectory is segmented at the second trajectory point;

[0009] The driving trajectory is compressed based on the first trajectory point and the second trajectory point to obtain a compressed trajectory.

[0010] In an embodiment of the present application, a first trajectory point is determined based on a first feature, and a second trajectory point is determined based on a second feature; wherein, the driving trajectory is not segmented at the first trajectory point, and is segmented at the second trajectory point; and the driving trajectory is compressed based on two different types of trajectory points. Since, when the driving trajectory is segmented, the starting point and the end point of the driving trajectory after segmentation may be different from the starting point and the end point of the driving trajectory before segmentation, the second feature of the trajectory point is changed, which may cause the trajectory points that originally need to be retained to be deleted, affecting the accuracy of the trajectory compression. Therefore, this solution divides the trajectory points that need to be retained into first trajectory points and second trajectory points; segmentation is not performed at the first trajectory point, but segmentation is performed only at the second trajectory point; and the influence of the second feature caused by segmentation at the first trajectory point is avoided. Therefore, compared with the prior art, this solution can avoid the mutual influence between different trajectory features, ensure that the trajectory points that need to be retained will not be mistakenly deleted, and thus improve the accuracy of trajectory compression.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the second feature information includes distance, where the distance represents the distance from each trajectory point to a target line, where the target line is a line connecting a starting point and an end point of the driving trajectory;

[0012] Determining a second trajectory point whose second characteristic information satisfies a second preset condition among the plurality of trajectory points includes:

[0013] Determine the target trajectory point with the largest distance from the target line among the multiple trajectory points;

[0014] If the distance between the target trajectory point and the target line is greater than a preset distance threshold, the target trajectory point is determined as the second trajectory point.

[0015] In an embodiment of the present application, the second feature includes the distance from each trajectory point to the target line connecting the starting point and the end point of the driving trajectory; based on the distance, it is determined whether each trajectory point is a second trajectory point that meets the second preset condition; if the distance to the target trajectory point with the largest distance among multiple trajectory points is greater than the preset distance threshold, it means that the distance from the target trajectory point to the target line is large, and if the target trajectory point is deleted, the shape of the compressed trajectory may be significantly different from that of the original trajectory; therefore, the target trajectory point is determined as the second trajectory point that needs to be retained, ensuring that the compressed trajectory is relatively similar in shape to the original trajectory, thereby ensuring the accuracy of the trajectory compression.

[0016] In combination with the first aspect and the above implementations, in certain implementations of the first aspect, determining the target trajectory point having the largest distance from the target line among the multiple trajectory points includes:

[0017] Determine the trajectory point with the largest vertical distance from the target line among the multiple trajectory points as the target trajectory point;

[0018] Alternatively, determining the mapping point of each trajectory point in the target line;

[0019] The trajectory point with the largest mapping distance from the mapping point among the multiple trajectory points is determined as the target trajectory point.

[0020] In an embodiment of the present application, when determining the target trajectory point, the trajectory point with the largest vertical distance from the target line is determined as the target trajectory point, or the trajectory point with the largest mapping distance from the mapping point is determined as the target trajectory point; the distance from the trajectory point to the target line is determined in two different ways, thereby ensuring that the target trajectory point with the largest distance from the target line can be determined.

[0021] In combination with the first aspect and the above implementations, in some implementations of the first aspect, the method further includes:

[0022] Segmenting the driving trajectory based on the second trajectory point to obtain two sub-trajectories, the sub-trajectories including a first sub-trajectory and a second sub-trajectory, the first sub-trajectory representing a sub-trajectory from the starting point of the driving trajectory to the second trajectory point, and the second sub-trajectory representing a sub-trajectory from the second trajectory point to the end point of the driving trajectory;

[0023] For each sub-trajectory, traverse each trajectory point in the sub-trajectory to determine whether the sub-trajectory has a second trajectory point;

[0024] If the second track point exists in the sub-track, the sub-track is segmented based on the second track point in the sub-track until the second track point does not exist in the segmented sub-track.

[0025] In an embodiment of the present application, the driving trajectory is segmented based on the second trajectory point to obtain two sub-trajectories. Each trajectory point in the sub-trajectory is traversed, and based on the second feature information of each trajectory point in the sub-trajectory, it is determined whether the second trajectory point exists. If the second trajectory point exists, the sub-trajectory is segmented based on the second trajectory point of the sub-trajectory to implement a recursive process. The segmentation process stops when the second trajectory point no longer exists in the sub-trajectory. This ensures that each sub-trajectory is recursively processed during the compression process of the driving trajectory, so that all second trajectory points that need to be retained can be determined, and the second trajectory points in the sub-trajectory are prevented from being accidentally deleted, thereby improving the accuracy of the trajectory compression.

[0026] In combination with the first aspect and the above implementation manner, in some implementation manners of the first aspect, the first feature information includes a direction angle and a speed difference;

[0027] Determining a first trajectory point among the plurality of trajectory points whose first characteristic information satisfies a first preset condition includes:

[0028] A trajectory point having a direction angle greater than a preset angle or a speed difference greater than a preset difference among the multiple trajectory points is determined as a first trajectory point.

[0029] In an embodiment of the present application, a trajectory point with a direction angle greater than a preset angle or a speed difference greater than a preset difference among multiple trajectory points is determined as a first trajectory point. Because trajectory points with large speed differences or large direction angles typically contain important information in the trajectory, trajectory points with large speed differences or large direction angles need to be considered when planning a path based on a compressed trajectory. Therefore, a trajectory point with a direction angle greater than a preset angle or a speed difference greater than a preset difference is determined to be a trajectory point to be retained. In addition, to avoid segmenting the driving trajectory at this trajectory point, which would cause a change in the second characteristic, this trajectory point is determined as the first trajectory point.

[0030] In combination with the first aspect and the above implementations, in some implementations of the first aspect, the direction angle of the trajectory point represents the angle between a first vector and a second vector, where the first vector is a vector formed by the trajectory point before the current trajectory point and the current trajectory point, and the second vector is a vector formed by the current trajectory point and the trajectory point after the current trajectory point;

[0031] The speed difference of a track point represents the speed difference between the current track point and the track point before the current track point.

[0032] In an embodiment of the present application, the first vector represents the vector formed by the previous trajectory point and the current trajectory point, and the second trajectory point represents the vector formed by the current trajectory point and the next trajectory point. The angle between the first and second vectors is determined as the direction angle of the trajectory point, ensuring that the degree of change in the vehicle's driving direction at the current trajectory point can be measured by the direction angle. The speed difference between the current trajectory point and the previous trajectory point is determined as the speed difference of the trajectory point, ensuring that the degree of change in the vehicle's speed at the trajectory point can be measured by the speed difference of the trajectory point.

[0033] In combination with the first aspect and the above implementations, in certain implementations of the first aspect, compressing the driving trajectory based on the first trajectory point and the second trajectory point to obtain the compressed trajectory includes:

[0034] Determine the starting point, the end point, the first track point, and the second track point in the driving track as reserved track points, and delete the track points in the driving track except the reserved track points;

[0035] The polyline trajectory composed of the retained trajectory points is determined as the compressed trajectory.

[0036] In an embodiment of the present application, the starting point, the end point, the first trajectory point, and the second trajectory point of the driving trajectory are determined as retained trajectory points, and the trajectory points other than the retained trajectory points are deleted; and the broken line trajectory composed of the retained trajectory points is determined as a compressed trajectory; ensuring that the compressed trajectory only contains the trajectory points that need to be retained, reducing the number of trajectory points to reduce data storage and transmission costs.

[0037] In a second aspect, a vehicle trajectory compression device is provided, the device comprising:

[0038] an acquisition module, configured to acquire characteristic information of each of a plurality of trajectory points of a vehicle's driving trajectory, the characteristic information including first characteristic information and second characteristic information, wherein the first characteristic information is characteristic information unrelated to a starting point and an end point of the driving trajectory, and the second characteristic information is characteristic information related to the starting point and the end point of the driving trajectory;

[0039] The processing module is used to determine a first trajectory point among multiple trajectory points whose first characteristic information meets a first preset condition, the first trajectory point indicating that the trajectory point is retained and the driving trajectory is not segmented at the first trajectory point; determine a second trajectory point among multiple trajectory points whose second characteristic information meets a second preset condition, the second trajectory point indicating that the trajectory point is retained and the driving trajectory is segmented at the second trajectory point; and compress the driving trajectory based on the first trajectory point and the second trajectory point to obtain a compressed trajectory.

[0040] In conjunction with the second aspect, in some implementations of the second aspect, the processing module is specifically configured to:

[0041] Determine a target trajectory point with the largest distance from the target line among the multiple trajectory points; if the distance between the target trajectory point and the target line is greater than a preset distance threshold, determine the target trajectory point as the second trajectory point.

[0042] In combination with the second aspect and the foregoing implementations, in some implementations of the second aspect, the processing module is specifically configured to:

[0043] The trajectory point with the largest vertical distance from the target line among the multiple trajectory points is determined as the target trajectory point; or, the mapping point of each trajectory point in the target line is determined; the trajectory point with the largest mapping distance from the mapping point among the multiple trajectory points is determined as the target trajectory point.

[0044] In combination with the second aspect and the foregoing implementations, in some implementations of the second aspect, the processing module is further configured to:

[0045] The driving trajectory is segmented based on the second trajectory point to obtain two sub-trajectories. The sub-trajectories include a first sub-trajectory and a second sub-trajectory. The first sub-trajectory represents the sub-trajectory from the starting point of the driving trajectory to the second trajectory point, and the second sub-trajectory represents the sub-trajectory from the second trajectory point to the end point of the driving trajectory. For each sub-trajectory, each trajectory point in the sub-trajectory is traversed to determine whether the sub-trajectory contains the second trajectory point. If the sub-trajectory contains the second trajectory point, the sub-trajectory is segmented based on the second trajectory point in the sub-trajectory until the second trajectory point no longer exists in the segmented sub-trajectory.

[0046] In combination with the second aspect and the above-mentioned implementation methods, in some implementation methods of the second aspect, the processing module is specifically used to: determine a trajectory point among multiple trajectory points whose direction angle is greater than a preset angle or whose speed difference is greater than a preset difference as a first trajectory point.

[0047] In combination with the second aspect and the above-mentioned implementation methods, in some implementation methods of the second aspect, the processing module is specifically used to: determine the starting point, end point, first trajectory point and second trajectory point in the driving trajectory as retained trajectory points, and delete the trajectory points other than the retained trajectory points in the driving trajectory; and determine the broken line trajectory composed of the retained trajectory points as a compressed trajectory.

[0048] In a third aspect, a vehicle is provided, comprising a memory and a processor, wherein the memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the vehicle executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0049] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0050] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed, it implements the method in the above-mentioned first aspect or any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a schematic diagram of trajectory compression provided by an embodiment of the present application;

[0052] Figure 2 is a schematic flow chart of a vehicle trajectory compression method provided in an embodiment of the present application;

[0053] Figure 3 is a schematic diagram of a distance feature of a trajectory point provided in an embodiment of the present application;

[0054] Figure 4 is a schematic diagram of a directional feature of a trajectory point provided in an embodiment of the present application;

[0055] Figure 5 is a schematic diagram of another trajectory compression provided by an embodiment of the present application;

[0056] Figure 6 is a schematic flow chart of another vehicle trajectory compression method provided in an embodiment of the present application;

[0057] Figure 7 is a schematic diagram of a trajectory compression process provided by an embodiment of the present application;

[0058] Figure 8 This is a schematic structural diagram of a vehicle trajectory compression device provided in an embodiment of the present application;

[0059] Figure 9 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] The following will clearly and thoroughly describe the technical solutions in this application in conjunction with the accompanying drawings. In the description of the embodiments of this application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more than two.

[0061] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0062] Recording and preserving a vehicle's driving trajectory under different terrain conditions has important practical significance. First, by recording and preserving the vehicle's driving trajectory under different terrain conditions, it can provide a reference for subsequent path planning, helping the vehicle to more efficiently avoid obstacles and optimize the driving route, thereby improving the vehicle's operating efficiency. Second, the preservation of trajectory data provides a basis for vehicle behavior analysis, helping researchers identify vehicle behavior patterns in complex terrain, such as key actions such as sharp turns and steep slope climbing, thereby providing data support for vehicle performance optimization and the development of autonomous driving technology.

[0063] Furthermore, trajectory preservation can provide an important basis for improving vehicle safety. By analyzing trajectory data, dangerous road sections or high-risk behaviors can be identified, providing early warning information to the driver or autonomous driving system, reducing the probability of accidents. At the same time, the preservation of trajectory data also provides an important reference for vehicle operation and maintenance. For example, by analyzing trajectory characteristics, the vehicle's energy consumption and wear under different terrain conditions can be evaluated, thereby optimizing vehicle maintenance strategies and resource allocation. By recording and preserving vehicle driving trajectories, not only can the vehicle's operating efficiency and safety be improved, but it also provides a data foundation for the innovation and development of related technologies.

[0064] In the existing technology, trajectory compression is usually performed based on distance and speed features; for example, the top-down trajectory compression algorithm based on time ratio (TD-TR) and the top-down trajectory compression algorithm based on speed (TD-SP) are described below:

[0065] Among them, the main idea of the TD-TR algorithm is to recursively delete points in the trajectory that do not meet the set threshold until all points meet the conditions or the trajectory only has the endpoints left. The calculation process of the algorithm can be summarized into the following three steps. First, the first and last points of the original trajectory (i.e., the starting point and the end point) are connected as an approximate trajectory and the distance from the intermediate trajectory point to the approximate trajectory is calculated. Secondly, the trajectory point with the largest distance among the intermediate trajectory points is selected and the maximum distance is compared with the distance threshold. If the maximum distance is greater than the set distance threshold, the original trajectory is divided into two sub-trajectories from this point; otherwise, all intermediate trajectory points are deleted. Finally, the above steps are repeated on the two sub-trajectories until only the first and last endpoints are left of the sub-trajectory.

[0066] The TD-SP algorithm uses speed difference as the retained trajectory point, which can effectively retain the speed mutation point in the trajectory. The algorithm idea is to define a speed difference threshold. If the trajectory point P i The velocity of its previous trajectory point P i-1 If the speed difference between the two points is less than or equal to the speed difference threshold, the point will be deleted; if the speed difference between the two points is greater than the speed difference threshold, the point P will be retained. i , and P i As a segmentation point, the original trajectory is divided into two parts at P i The trajectory is divided into two sub-trajectories, and the above process is repeated in the sub-trajectory segments until there is no trajectory point with a speed difference greater than the speed difference threshold in the sub-trajectory.

[0067] The above TD-TR algorithm and TD-SP algorithm only consider the distance or speed characteristics, ignoring other trajectory features of the trajectory, which may lead to a large difference between the compressed trajectory and the original trajectory; therefore, the trajectory compression algorithm needs to combine multiple trajectory features to compress the driving trajectory. However, simple fusion may cause mutual influence between multiple trajectory features, resulting in conflicts between multiple trajectory features and affecting the trajectory compression effect. Figure 1 The mutual influence between multi-trajectory features is schematically illustrated.

[0068] For example, Figure 1 As shown, Figure 1 is a schematic diagram of trajectory compression provided by an embodiment of the present application; Figure 1As shown in (a), the driving trajectory includes four trajectory points, P1, P2, P3 and P4. For the convenience of representation, the driving trajectory is described as [P1, P2, P3, P4]. Assuming that the speed difference of point P2 is greater than the set speed difference threshold, and the distance L3 from trajectory point P3 to P1P4 is greater than the set distance threshold, then all trajectory points P1 to P4 in the above driving trajectory should be retained; where, Figure 1 The distance L3 shown is the Synchronized Euclidean Distance (SED) which includes the trajectory time information. However, if the compression is performed based on the speed feature first and then based on the distance feature, some trajectory points that need to be retained may be deleted. Figure 1 As shown in (b) of the figure, if the driving trajectory is segmented at P2, the original trajectory [P1, P2, P3, P4] will be divided into the first trajectory [P1, P2] and the second trajectory [P2, P3, P4]. The starting point of the second trajectory is P2 and the end point is P4. At this time, the distance L3 of P3 on the second trajectory is smaller than L3 in the original trajectory. This distance may be less than the preset distance threshold, resulting in P3 being deleted. The final compressed trajectory is as follows Figure 1 As shown in (c), since the trajectory point P3 that originally needed to be retained was deleted, the compressed trajectory is different from the original Figure 1 The compression trajectory shown in (a) is quite different and the compression accuracy is low.

[0069] Therefore, when compressing the driving trajectory, how to avoid the mutual influence between trajectory features is a technical problem that needs to be solved.

[0070] In view of this, the present application provides a vehicle trajectory compression method, device, vehicle, and storage medium. The method determines a first trajectory point based on a first feature and a second trajectory point based on a second feature. The driving trajectory is not segmented at the first trajectory point, but is segmented at the second trajectory point. By distinguishing two different types of trajectory points and compressing the driving trajectory based on the two different types of trajectory points, the mutual influence between different types of trajectory features can be avoided.

[0071] For example, the following Figure 2 The method flow chart shown in FIG1 illustrates the vehicle trajectory compression method in detail.

[0072] Figure 2 This is a schematic flowchart of a vehicle trajectory compression method provided in an embodiment of the present application.

[0073] For example, Figure 2The method 200 shown can be executed by the vehicle; or can be executed by the vehicle's onboard terminal (for example, the vehicle's onboard computer or intelligent gateway, etc.), or can be executed by a cloud server (or cloud computing platform).

[0074] like Figure 2 As shown, the vehicle trajectory compression method 200 includes S210 to S240 , which will be described in detail below.

[0075] S210: Acquire feature information of each of a plurality of trajectory points of the vehicle's driving trajectory.

[0076] Among them, the characteristic information includes first characteristic information and second characteristic information. The first characteristic information is characteristic information that is not related to the starting point and end point of the driving trajectory, and the first characteristic information includes the direction angle and speed difference; the second characteristic information is characteristic information that is related to the starting point and end point of the driving trajectory, and the second characteristic information includes distance.

[0077] Exemplarily, the real-time position of the vehicle and the timestamp information corresponding to the real-time position are obtained by receiving satellite signals, and the driving trajectory of the vehicle is obtained based on the real-time position collected during the driving process of the vehicle.

[0078] Optionally, the vehicle's driving data (for example, speed, rotation speed, fuel consumption, etc.) is obtained based on sensors in the vehicle, and the vehicle's driving trajectory is determined in combination with the vehicle's driving data, timestamp and mileage information; or the vehicle's real-time position and status data are uploaded through the on-board terminal, and the vehicle's driving trajectory is determined based on the real-time position collected by the on-board terminal.

[0079] S220: Determine a first trajectory point among the plurality of trajectory points, the first characteristic information of which satisfies a first preset condition.

[0080] The first trajectory point represents a reserved trajectory point and the driving trajectory is not segmented at the first trajectory point; that is, the first trajectory point represents a reserved trajectory point that needs to be retained during the trajectory compression process, and the driving trajectory is not segmented at the first trajectory point during the trajectory compression process.

[0081] In one implementation, the first feature information includes a direction angle and a speed difference; a trajectory point having a direction angle greater than a preset angle or a speed difference greater than a preset difference among the multiple trajectory points is determined as the first trajectory point.

[0082] It can be understood that since the direction angle and speed difference are not related to the starting point and end point of the driving trajectory, and the direction angle and speed difference contain important information in the driving trajectory (the direction angle reflects the change in direction of the vehicle during driving, and the speed difference reflects the change in speed during driving), when planning the path based on the compressed trajectory, it is necessary to retain trajectory points with larger speed differences or larger direction angles; therefore, the first feature information includes the direction angle and speed difference.

[0083] For example, when the first characteristic information includes a direction angle and a speed difference, the first preset condition corresponding to the first characteristic information is that the direction angle is greater than a preset angle or the speed difference is greater than a preset difference. If a trajectory point exists among the multiple trajectory points where the direction angle is greater than the preset angle or the speed difference is greater than the preset difference, the trajectory point is determined as the first trajectory point that meets the first preset condition.

[0084] For example, the process of determining the first trajectory point is schematically illustrated using a preset angle of 20°, a preset differential of 20 km / h, and a driving trajectory of [P1, P2, P3, P4]. If trajectory point P2 has a direction angle of 30° and a speed differential of 10 km / h, and trajectory point P3 has a direction angle of 10° and a speed differential of 40 km / h, since the direction angle of trajectory point P2 is greater than the preset angle, the speed differential of trajectory point P3 is greater than the preset differential. Therefore, trajectory point P2 and trajectory point P3 are both determined as the first trajectory point.

[0085] It should be noted that the above is an example of the preset angle, preset difference and driving trajectory, which is used to describe the process of determining the first trajectory point; this application does not limit the specific values of the preset angle and the preset difference.

[0086] In an embodiment of the present application, a trajectory point whose direction angle is greater than a preset angle or whose speed difference is greater than a preset difference among multiple trajectory points is determined as a first trajectory point; ensuring that the influence of the direction angle and speed difference on the driving trajectory is considered when compressing the driving trajectory; in addition, in order to avoid segmenting the driving trajectory at this trajectory point, which may cause a change in the second feature, this trajectory point is determined as the first trajectory point.

[0087] Exemplarily, the method for determining the direction angle and speed difference is further explained: the direction angle of a trajectory point represents the angle between a first vector and a second vector, wherein the first vector is a vector formed by the previous trajectory point of the current trajectory point and the current trajectory point, and the second vector is a vector formed by the current trajectory point and the next trajectory point of the current trajectory point; the speed difference of a trajectory point represents the speed difference between the current trajectory point and the previous trajectory point of the current trajectory point.

[0088] The direction angle of a trajectory point is the angle between the vector with the trajectory point as the end point (i.e., the first vector) and the vector with the trajectory point as the starting point (i.e., the second vector); Figure 4 As shown, Figure 4 This is a schematic diagram of the directional characteristics of a trajectory point provided in an embodiment of the present application. The driving trajectory is [P1, P2, P3, P4]. Taking trajectory point P3 as an example, the first vector corresponding to P3 is the vector composed of P2 and P3, and the second vector corresponding to P3 is the vector composed of P3 and P4; therefore, the direction angle α1 of trajectory point P3 is the angle formed by the first vector composed of P2 and P3 and the second vector composed of P3 and P4.

[0089] Optionally, the preset angle is determined based on the compression rate of the trajectory compression; wherein the compression rate represents the ratio of the original data volume to the compressed data volume, which is used to reflect the efficiency of data reduction; the larger the compressed data volume (i.e., the more trajectory points retained), the smaller the corresponding compression rate; the preset angle is positively correlated with the compression rate, and if the compression rate is higher, the corresponding preset angle is higher, and the fewer first trajectory points need to be retained according to the direction angle; if the compression rate is lower, the corresponding preset angle is lower, and the more first trajectory points need to be retained according to the direction angle.

[0090] It is understood that while driving, the driver will adjust the vehicle's direction based on the actual terrain conditions. When the azimuth angle of a trajectory point is large (greater than a preset angle), it indicates that the vehicle (e.g., an off-road vehicle) is turning. This trajectory point is the inflection point of the driving trajectory. That is, the inflection point is the first trajectory point determined based on the azimuth angle. Inflection points play an important role in driving path planning and vehicle control. Specifically, in complex terrain, inflection points connect different driving paths and are important turning points in the vehicle's driving path. Therefore, when planning a driving path, it is necessary to rationally plan and design the path based on the location and number of inflection points. The accuracy of the inflection point location directly affects driving accuracy. If the inflection point location is inaccurate, the planned driving path may deviate from the actual road. The location and number of inflection points also affect driving efficiency. If there are too many inflection points, the vehicle will need to frequently stop and turn, which will reduce driving efficiency. If there are too few inflection points, the vehicle may deviate from the planned driving path during driving, affecting driving performance. Therefore, the appropriate preset angle is determined based on the compression rate of the demand, thereby adjusting the number of inflection points.

[0091] For example, Figure 5 is a schematic diagram of another trajectory compression provided by an embodiment of the present application; Figure 5As shown in (a) in the figure, if the vehicle's driving trajectory is [P1, P2, P3], the driving trajectory contains an inflection point P2 with a sudden change in direction, and the SED distance of P2 is L2; assuming that the distance L2 of P2 is less than the preset distance threshold, and the speed difference of P2 is less than the preset difference, when the trajectory is compressed, the trajectory point P2 will be deleted, and the driving trajectory [P1, P2, P3] will be compressed to [P1, P3]. The compressed trajectory is as follows Figure 5 As shown in (b) in the figure. By comparison Figure 5 The driving trajectory before compression shown in (a) is the same as Figure 5 In the compression trajectory shown in (b), there is a significant difference between the pre-compression trajectory and the compression trajectory. This difference is caused by ignoring the directional changes of the trajectory points, that is, not retaining inflection points with significant directional changes. Therefore, to reduce the difference between the compression trajectory and the driving trajectory, it is necessary to consider directional changes during trajectory compression, and select trajectory points with significant directional changes (trajectory points with directional angles greater than a preset angle) as the first trajectory points to be retained.

[0092] For example, the speed difference of a trajectory point represents the speed difference between the current trajectory point and the trajectory point immediately preceding the current trajectory point. While the vehicle is driving, the IoV data collects the vehicle's instantaneous speed in real time, and the speed difference between the instantaneous speed of the current trajectory point and the instantaneous speed of the trajectory point immediately preceding the current trajectory point is used as the speed difference of the current trajectory point.

[0093] Alternatively, if the vehicle is traveling on complex road conditions and the IoV cannot collect the vehicle's instantaneous speed, the average speed of the current trajectory point and the trajectory point immediately following the current trajectory point is determined as the speed of the current trajectory point; the speed difference of the current trajectory point is obtained based on the speed of the current trajectory point and the speed of the trajectory point immediately following the current trajectory point. For example, the speed difference can be calculated using Formulas 1 to 3:

[0094]

[0095] ΔV i =|V i -V i-1 |; (Formula 3)

[0096] Among them, V i-1 represents the velocity of the i-1th trajectory point, d(P i , P i-1 ) represents the distance from the i-1th trajectory point to the i-th trajectory point; t i represents the time it takes for the vehicle to reach the i-th trajectory point; t i-1 V represents the time it takes for the vehicle to reach the i-1th trajectory point; i represents the velocity of the i-th trajectory point, d(P i+1 , Pi ) represents the distance from the i+1th trajectory point to the ith trajectory point; t i+1 Indicates the time it takes for the vehicle to reach the i+1th trajectory point; ΔV i Represents the velocity difference of the i-th trajectory point.

[0097] For example, the velocity V of the i-1th trajectory point is calculated by the above formula 1: i-1 ; According to formula 2, the i-th trajectory point V is calculated i speed; V i-1 With V i Substitute into formula 3 to calculate the velocity difference ΔV of the i-th trajectory point i ; The velocity difference ΔV of the i-th trajectory point i Compare with the preset difference value to determine whether the i-th trajectory point is the first trajectory point that needs to be retained.

[0098] It is understandable that the speed of a vehicle in a driving trajectory can reflect the type of operation of the vehicle in the driving trajectory; for example, a vehicle will exhibit different speeds when performing different tasks such as transportation, rescue, exploration, and patrol. The speed difference refers to the speed difference between adjacent trajectory points in the driving trajectory (for example, the speed difference between the current trajectory point and the previous trajectory point of the current trajectory point); when the speed difference of the trajectory point is small, it means that the vehicle is operating stably or that the terrain of the trajectory point is relatively flat; when the speed difference is large (greater than the preset difference), it means that the vehicle may have encountered a special situation or that the terrain of the trajectory point is relatively complex; therefore, in the process of trajectory compression, it is necessary to retain trajectory points with large speed differences to ensure that the compressed trajectory can reflect the terrain of the road.

[0099] Optionally, a preset difference is determined based on the compression rate of the trajectory compression; wherein the preset difference is positively correlated with the compression rate. If the compression rate is higher, the corresponding preset difference is larger, and the number of first trajectory points that need to be retained based on the speed difference is smaller; if the compression rate is lower, the corresponding preset difference is smaller, and the number of first trajectory points that need to be retained based on the speed difference is more.

[0100] In an embodiment of the present application, the first vector represents the vector formed by the previous trajectory point and the current trajectory point, and the second trajectory point represents the vector formed by the current trajectory point and the next trajectory point. The angle between the first and second vectors is determined as the direction angle of the trajectory point, ensuring that the degree of change in the vehicle's driving direction at the current trajectory point can be measured by the direction angle. The speed difference between the current trajectory point and the previous trajectory point is determined as the speed difference of the trajectory point, ensuring that the degree of change in the vehicle's speed at the trajectory point can be measured by the speed difference of the trajectory point.

[0101] S230: Determine a second trajectory point among the plurality of trajectory points, the second characteristic information of which satisfies a second preset condition.

[0102] The second trajectory point represents a retained trajectory point and the driving trajectory is segmented at the second trajectory point; that is, the second trajectory point represents a retained trajectory point in the trajectory compression process, and in the trajectory compression process, the driving trajectory is segmented at the second trajectory point.

[0103] In one implementation, the second feature information includes distance, where the distance represents the distance from each trajectory point to a target line, where the target line is a line connecting the starting point and the end point of the driving trajectory; a target trajectory point having the largest distance from the target line among multiple trajectory points is determined; if the distance between the target trajectory point and the target line is greater than a preset distance threshold, the target trajectory point is determined as the second trajectory point.

[0104] Exemplarily, the second characteristic information represents characteristic information related to the starting point and end point of the driving trajectory. Since the distance of a trajectory point represents the distance from the trajectory point to the target line (the line connecting the starting point and end point of the driving trajectory), the distance is related to the starting point and end point of the driving trajectory. When the starting point and end point are different, the obtained trajectory point distance is different, so the distance is determined as the second characteristic information. When the distance is determined as the second characteristic information, the second preset condition corresponding to the second characteristic information is that the distance is greater than a preset distance threshold.

[0105] It can be understood that whether each trajectory point is a second trajectory point that meets the second preset condition is determined based on the distance; if the distance to the target trajectory point with the largest distance among multiple trajectory points is greater than the preset distance threshold, it means that the distance between the target trajectory point and the line connecting the starting point and the end point is large. If the target trajectory point is deleted, the shape of the compressed trajectory may be significantly different from that of the original trajectory; therefore, the target trajectory point is determined as the second trajectory point that needs to be retained to ensure that the compressed trajectory is relatively similar in shape to the original trajectory.

[0106] For example, Figure 1 As shown in (a), the distance between the trajectory point P3 in the driving trajectory is large. If P3 is deleted, the compressed trajectory is as follows Figure 1 As shown in (c), Figure 1 The compression trajectory shown in (c) is different from the original Figure 1 The trajectory shown in (a) has a large difference in shape; therefore, the compression effect of deleting the trajectory point P3 is poor, and P3 needs to be retained as the second trajectory point.

[0107] In one implementation, the trajectory point with the largest vertical distance from the target line among the multiple trajectory points is determined as the target trajectory point; or, the mapping point of each trajectory point in the target line is determined; and the trajectory point with the largest mapping distance from the mapping point among the multiple trajectory points is determined as the target trajectory point.

[0108] For example, there are two ways to determine the target trajectory point based on distance: one is to determine the target trajectory point based on the vertical distance from each trajectory point to the target line; the other is to determine the target trajectory point based on the mapped distance from the trajectory point to the target line. The mapped distance can be understood as the synchronized Euclidean distance (SED distance) that includes the trajectory time information, that is, the time-synchronized Euclidean distance.

[0109] Figure 3 This is a schematic diagram of the distance feature of a trajectory point provided by an embodiment of the present application; Figure 3 Two determination methods are schematically illustrated.

[0110] For example, the vertical distance from each trajectory point to the target line is as follows: Figure 3 As shown in (a), the starting points P1 and P7 of the driving trajectory are connected to obtain the target line P1P7; the vertical distance between each trajectory point and the target line P1P7 is determined as the vertical distance of each trajectory point. The mapping distance of each trajectory point to the target line is as follows: Figure 3 As shown in (b), the mapping point of each trajectory point on the target line P1P7 is determined; the straight-line distance between each trajectory point and the mapping point corresponding to each trajectory point is determined as the mapping distance.

[0111] For example, the process of calculating the mapping distance (SED distance) is divided into two steps. The first step is to calculate the trajectory point P by formula 5. i Mapping point P' on the target line i The second step is to calculate P according to formula 6 i and P' i The Euclidean distance between .

[0112]

[0113] Where i represents the i-th trajectory point; m represents the starting point of the driving trajectory; n represents the end point of the driving trajectory; x' i Indicates the horizontal coordinate of the mapping point P'i, y' i Indicates the vertical coordinate of the mapping point P'i; x m Indicates the horizontal coordinate of the starting point of the driving trajectory, y m Indicates the vertical coordinate of the starting point of the driving trajectory; x n Indicates the horizontal coordinate of the end point of the driving trajectory, y n Indicates the ordinate of the end point of the driving trajectory; t i represents the time it takes for the vehicle to reach the i-th trajectory point; t m Indicates the time it takes for the vehicle to reach the starting point; t n Indicates the time it takes for the vehicle to reach the destination; SED iIt represents the distance between the mapping points of the i-th trajectory point to the i-th trajectory point, that is, the SED distance of the i-th trajectory point.

[0114] It can be understood that when calculating the mapping distance (SED distance), the mapping point of the trajectory point is determined according to the time ratio; the mapping point of the trajectory point represents the mapping position in the target line at the same time when the vehicle arrives at the trajectory point under uniform motion; for example, the vehicle travels from the starting point to the end point, the total distance is 30km, the time when the vehicle travels to the starting point is 9:00; the time when it travels to the end point is 9:30; then at the time of 9:15, the corresponding position of the vehicle is 15km away from the starting point, which is the position of the mapping point. Therefore, compared with the vertical straight line distance, the time comparison of the SED distance can determine the important change points in the time dimension, that is, it can identify the trajectory points with small spatial distance changes but long time intervals, and retain the trajectory points during the trajectory compression process to improve the accuracy of trajectory compression.

[0115] In an embodiment of the present application, when determining the target trajectory point, the trajectory point with the largest vertical distance from the target line is determined as the target trajectory point, or the trajectory point with the largest mapping distance from the mapping point is determined as the target trajectory point; the distance from the trajectory point to the target line is determined in two different ways, thereby ensuring that the target trajectory point with the largest distance from the target line can be determined.

[0116] In one implementation, the method further includes: segmenting the driving trajectory based on the second trajectory point to obtain two sub-trajectories, the sub-trajectories including a first sub-trajectory and a second sub-trajectory, the first sub-trajectory representing the sub-trajectory from the starting point of the driving trajectory to the second trajectory point, and the second sub-trajectory representing the sub-trajectory from the second trajectory point to the end point of the driving trajectory; for each sub-trajectory, traversing each trajectory point in the sub-trajectory to determine whether the sub-trajectory contains the second trajectory point; if the sub-trajectory contains the second trajectory point, segmenting the sub-trajectory based on the second trajectory point in the sub-trajectory until the second trajectory point no longer exists in the segmented sub-trajectory.

[0117] It can be understood that the process of determining the second trajectory point is a recursive process. First, the driving trajectory is segmented according to the second trajectory point to obtain two sub-trajectories. For each sub-trajectory, the line connecting the starting point and the end point of the sub-trajectory is determined as the target line, and the maximum distance from each trajectory point in the sub-trajectory to the target line is determined. If the maximum distance is greater than a preset distance threshold, the trajectory point with the maximum distance is determined as the second trajectory point. The sub-trajectory is segmented again at this second trajectory point to implement a recursive process. Segmentation stops when the second trajectory point no longer exists in the sub-trajectory. Ensure that each sub-trajectory is recursively processed during the compression process of the driving trajectory so that all second trajectory points that need to be retained can be determined to avoid accidental deletion of second trajectory points in the sub-trajectory.

[0118] For example, taking the preset distance threshold as 8km and the driving trajectory T as [P1, P2, P3, P4, P5] as an example for schematic explanation: determine the distances from trajectory points P2, P3, P4 to the target line (the line between P1 and P5); if the distance from P2 to the target line is 10km, the distance from P3 to the target line is 20km, and the distance from P4 to the target line is 2km; the trajectory point corresponding to the maximum distance among all trajectory points is P3. Since the distance of P3 is greater than 5km, P3 is determined as the second trajectory point. The driving trajectory is segmented at P3, resulting in two sub-trajectories: the first sub-trajectory [P1, P2, P3] and the second sub-trajectory [P3, P4, P5]. For the first sub-trajectory, the distance from P2 to the line connecting P1 and P3 is determined. If this distance is 12 km, P2 is selected as the second trajectory point. For the second sub-trajectory, the distance from P4 to the line connecting P3 and P5 is determined. If this distance is 5 km, P4 is not selected as the second trajectory point. Finally, the second trajectory points of driving trajectory T are determined to include P2 and P3.

[0119] It should be noted that the above is an example of the preset distance threshold and each track point in the driving trajectory, which is used to describe the process of recursive processing to determine the second track point; this application does not specifically limit the second distance threshold.

[0120] Optionally, a preset distance threshold is determined based on the requirement for compression rate; wherein the preset distance threshold is positively correlated with the compression rate; if the compression rate is higher, the preset distance is larger, and fewer second trajectory points are determined.

[0121] It is understood that the higher the compression ratio, the fewer second trajectory points are retained, the lower the similarity between the compressed trajectory and the original trajectory, and the corresponding lower data storage and transmission costs. Therefore, the user can determine the compression ratio based on the compression requirements for the compressed trajectory, and thus determine the appropriate preset distance threshold. For example, if the user's requirement is to retain as many trajectory points as possible so that the compressed trajectory has a high similarity with the original trajectory, a lower compression ratio can be determined, and the preset distance threshold can be appropriately reduced based on this compression ratio. If the user's requirement is to minimize data storage and transmission costs, a higher compression ratio can be determined, and the preset distance threshold can be appropriately increased based on this compression ratio.

[0122] S240 : Compress the driving trajectory based on the first trajectory point and the second trajectory point to obtain a compressed trajectory.

[0123] In one implementation, the starting point, the end point, the first trajectory point, and the second trajectory point in the driving trajectory are determined as retained trajectory points, and the trajectory points other than the retained trajectory points in the driving trajectory are deleted; and the broken line trajectory formed by the retained trajectory points is determined as a compressed trajectory.

[0124] Exemplarily, the starting point, end point, first trajectory point, and second trajectory point of the driving trajectory are determined as retained trajectory points, and trajectory points other than the retained trajectory points are deleted; and the broken line trajectory formed by the retained trajectory points is determined as a compressed trajectory; ensuring that the compressed trajectory only contains trajectory points that need to be retained, reducing the number of trajectory points to reduce data storage and transmission costs.

[0125] It should be noted that since the first trajectory point is derived from the first characteristic information (including speed difference and direction angle), it contains key information about the vehicle's driving process and needs to be retained so that the compressed trajectory retains this key information. The second trajectory point is derived from the second characteristic information (including distance) and reflects the shape characteristics of the vehicle's driving trajectory. Therefore, it is necessary to retain the second trajectory point so that the compressed trajectory is similar in shape to the original trajectory of the vehicle, ensuring high trajectory compression accuracy.

[0126] In the above embodiment, a first trajectory point is determined based on a first feature, and a second trajectory point is determined based on a second feature; wherein, the driving trajectory is not segmented at the first trajectory point, and the driving trajectory is segmented at the second trajectory point; and the driving trajectory is compressed based on the two different types of trajectory points. Because the second feature represents points related to the starting point and the end point of the driving trajectory, when the driving trajectory is segmented, the starting point and the end point of the driving trajectory after segmentation may be different from the starting point and the end point of the driving trajectory before segmentation, resulting in a change in the second feature of the trajectory point, which may cause the trajectory point that originally needs to be retained to be deleted, affecting the accuracy of the trajectory compression (for example, before the starting point and the end point change, the trajectory point meets the second preset condition, and the trajectory point needs to be retained; the starting point or the end point changes, resulting in a change in the second feature, and the changed second feature no longer meets the second preset condition, resulting in the trajectory point being mistakenly deleted). Therefore, this solution divides the trajectory points that need to be retained into first trajectory points and second trajectory points; segmentation is not performed at the first trajectory points, but only at the second trajectory points; compared with the existing technology, this solution can avoid the impact of segmentation at the first trajectory point on the second feature, thereby avoiding the mutual influence between different trajectory features and ensuring that the trajectory points that need to be retained will not be deleted by mistake.

[0127] Figure 6 This is a schematic flowchart of another vehicle trajectory compression method provided in an embodiment of the present application.

[0128] For example, Figure 6 The method 600 shown can be executed by the vehicle; or can be executed by the vehicle's onboard terminal (including the vehicle's onboard computer or intelligent gateway, etc.), or can be executed by a cloud server (or cloud computing platform).

[0129] like Figure 6 As shown, the vehicle trajectory compression method 600 includes S601 to S611 , which will be described in detail below.

[0130] S601: Acquire the vehicle's driving trajectory.

[0131] Exemplarily, the real-time position of the vehicle and the timestamp information corresponding to the real-time position are obtained by receiving satellite signals, and the driving trajectory of the vehicle is obtained based on the real-time position collected during the driving process of the vehicle.

[0132] S602: Determine feature information of each of the plurality of trajectory points of the driving trajectory.

[0133] Among them, the characteristic information of the trajectory point includes first characteristic information and second characteristic information. The first characteristic information is characteristic information that is not related to the starting point and end point of the driving trajectory, and the first characteristic information includes the direction angle and speed difference; the second characteristic information is characteristic information that is related to the starting point and end point of the driving trajectory, and the second characteristic information includes distance.

[0134] Exemplarily, the vehicle speed is obtained based on the vehicle's sensors; the speed of the vehicle at different trajectory points is determined in combination with timestamp information; the speed difference of the vehicle is determined based on the speed of the vehicle at different trajectory points; the specific calculation method can be found in the calculation methods shown in Formulas 1 to 3.

[0135] Based on the positions of different trajectory points in the driving trajectory, the mapping distance (SED distance) of the trajectory point to the line connecting the starting point and the end point of the driving trajectory is determined; the driving direction of the vehicle at different trajectory points is determined based on the vehicle's driving trajectory; and the direction angle of the trajectory point is determined based on the vehicle's driving direction.

[0136] Optionally, the implementation of S601 and S602 can be found in Figure 2 The relevant description of S210 is omitted here.

[0137] S603: Determine a trajectory point among the multiple trajectory points whose direction angle is greater than a preset angle or whose speed difference is greater than a preset difference value as a first trajectory point.

[0138] For example, if the direction angle of a trajectory point is greater than a preset angle, it indicates that the direction change of the trajectory point is more significant, and therefore, the trajectory point is determined as the first trajectory point that needs to be retained; if the speed difference of the trajectory point is greater than the preset difference, it indicates that the speed change of the trajectory point is more significant, and therefore, the trajectory point is determined as the first trajectory point that needs to be retained.

[0139] Optionally, the implementation of S603 can refer to Figure 2 The relevant description of S220 is omitted here.

[0140] S604: Determine the target trajectory point with the largest mapping distance among all trajectory points.

[0141] Exemplarily, a mapping distance from each trajectory point to a mapping point corresponding to each trajectory point is determined; and a trajectory point with the largest mapping distance is determined as a target trajectory point.

[0142] S605: Is the mapping distance of the target trajectory point greater than a preset distance threshold? If so, execute S606.

[0143] Exemplarily, it is determined whether the mapping distance of the target trajectory point is greater than a preset distance threshold; if the mapping distance of the target trajectory point is greater than the preset distance threshold, the target trajectory point is determined as the second trajectory point.

[0144] Optionally, if the distance between the target track point and the mapping point is less than or equal to a preset distance threshold, it is determined that the second track point does not exist; if the second track point does not exist, only the first track point, the starting point and the end point are determined as retained track points.

[0145] S606: Determine the target trajectory point as the second trajectory point.

[0146] For example, if the mapping distance of the target trajectory point is greater than a preset distance threshold, it means that the distance between the target trajectory point and the line connecting the starting point and the end point is large. In order to ensure that the shape of the compressed trajectory is relatively similar to the driving trajectory, the target trajectory point is determined as the second trajectory point that needs to be retained.

[0147] S607: Segment the driving trajectory based on the second trajectory point to obtain two sub-trajectories.

[0148] S608, determine whether there is a second track point in each sub-track; if so, execute S607; if not, execute S609.

[0149] Exemplarily, determine whether there is a second trajectory point in each sub-trajectory; if there is a second trajectory point in the sub-trajectory, repeat the process in S607 to segment the trajectory based on the second trajectory point; if there is no second trajectory point in the sub-trajectory; then obtain all the second trajectory points in the driving trajectory.

[0150] S609: Obtain all second track points in the driving track.

[0151] Exemplarily, all second trajectory points include second trajectory points determined in the driving trajectory and second trajectory points determined in the sub-trajectory.

[0152] Optionally, the implementation of S604 to S609 can refer to Figure 2 The relevant description of S230 is not repeated here.

[0153] S610: Determine the first trajectory point, the second trajectory point, and the starting point and the end point of the driving trajectory as reserved trajectory points.

[0154] S611: Delete the trajectory points other than the retained trajectory points, and determine the broken line trajectory formed by the retained points as the compressed trajectory.

[0155] Exemplarily, the starting point, end point, first trajectory point, and second trajectory point of the driving trajectory are determined as retained trajectory points, and trajectory points other than the retained trajectory points are deleted; and the broken line trajectory formed by the retained trajectory points is determined as a compressed trajectory; ensuring that the compressed trajectory only contains trajectory points that need to be retained, reducing the number of trajectory points to reduce data storage and transmission costs.

[0156] Optionally, the implementation of S610 and S611 can be found in Figure 2 The relevant description of S240 is not repeated here.

[0157] In an embodiment of the present application, the trajectory points that need to be retained are divided into first trajectory points and second trajectory points; segmentation is not performed at the first trajectory points, but only at the second trajectory points; the segmentation at the first trajectory points is avoided from affecting the second feature; thereby avoiding mutual influence between different trajectory features and ensuring that the trajectory points that need to be retained are not deleted by mistake.

[0158] In one implementation, the present application provides a vehicle trajectory compression method, which can be a multi-feature fusion trajectory compression algorithm, and compresses the driving trajectory through the algorithm. For example, the execution steps of the compression algorithm are as follows:

[0159] Step 1: Read the trajectory segment s into the algorithm. When the number of trajectory points contained in the trajectory segment s is less than or equal to 2, the algorithm stops running. When the number of trajectory points contained in the trajectory segment s is greater than 2, the trajectory compression algorithm starts to be executed; the keep array is set to empty. Starting from the second trajectory point, the SED distance of each intermediate trajectory point is calculated in turn (such as Figure 3 The distance of each trajectory point shown in (b) in FIG), the speed difference, and the direction angle, and the trajectory points with a speed difference or direction angle greater than a preset value (the trajectory points with a speed difference greater than a preset difference, or a direction angle greater than a preset angle) are added to the keep array.

[0160] Exemplarily, the point added to the keep array corresponds to the first trajectory point in step S603.

[0161] Step 2: If the maximum SED distance of the intermediate trajectory point is less than the preset distance threshold, all trajectory points outside the keep array are deleted, and the trajectory points in the keep array and the first and last points of the original trajectory form a compressed trajectory.

[0162] Step 3: If the maximum SED distance of the intermediate trajectory point is greater than the preset distance threshold, the trajectory point with the maximum SED distance is retained (the trajectory point with the maximum SED distance corresponds to the second trajectory point in S606), and this point is used as the segmentation point. The original trajectory is divided into two sub-trajectories at this point. The sub-trajectories repeat steps 1 and 2 until there are no trajectory points in the sub-trajectory with a distance greater than the preset distance threshold. The algorithm ends.

[0163] It is understandable that this application considers multiple trajectory features, including speed, direction, and distance, when performing trajectory compression, thus resolving the issue of a single trajectory feature in trajectory compression algorithms. Furthermore, this application only performs segmentation and recursion when the distance exceeds a preset distance threshold. Direction and speed are used only to determine which trajectory points to retain and are not used as a basis for trajectory segmentation. This avoids the impact of segmenting the trajectory based on direction and speed features on the distance feature, thereby resolving the conflicting issues between multiple features in the prior art.

[0164] Figure 7 Schematic diagram of a trajectory compression process provided in an embodiment of the present application.

[0165] For example, Figure 7 The compression process 700 shown is a process of compressing the original trajectory of the vehicle to obtain a compressed trajectory. Figure 7 As shown in (a), including P1 to P 11 There are 11 track points in total; the driving track collected by the positioning terminal is as follows Figure 7 As shown in (b), P2 and P 10 The first trajectory point that meets the first preset condition (for example, the speed difference of P2 is greater than the preset difference, P 10 The direction angle is greater than the preset angle); the SED distance from each trajectory point to the target line connecting the starting point and the end point is represented by a dotted line. The distance from trajectory point P7 to the target line is the largest, and this distance is greater than the preset distance threshold; therefore, P7 is determined to be a retained trajectory point and the original trajectory is segmented at the location of P7 (P7 is the second trajectory point). The segmented driving trajectory is shown as follows Figure 7 As shown in (c) in the figure, the segmented driving trajectory includes two sub-trajectories, namely the sub-trajectory from P1 to P7 and the sub-trajectory from P7 to P 11 The sub-trajectory is obtained and the above algorithm process is recursively executed in the sub-trajectory. If the maximum SED distance in the sub-trajectory is less than or equal to the preset threshold, then there is no second trajectory point in the sub-trajectory; in the recursive process, all the second trajectory points are obtained as P2, P3, P5, P7, and P9; all the trajectory points except the starting point, the end point, the first trajectory point, and the second trajectory point are deleted, that is, P4, P6, and P8 are deleted; the retained trajectory points are P1, P2, P3, P5, P7, P9, and P10 With P 11 ; The broken line trajectory composed of the retained trajectory points is determined as the final compression trajectory. The compression trajectory is as follows Figure 7 As shown in (d) in .

[0166] Combined with the above Figures 1 to 7 The vehicle trajectory compression method provided by the embodiment of the present application is described in detail; Figure 8 and Figure 9 The device embodiments of the present application are described in detail. It should be understood that the devices in the embodiments of the present application can execute the various methods of the aforementioned embodiments of the present application, that is, the specific working processes of the following various products can refer to the corresponding processes in the aforementioned method embodiments.

[0167] Figure 8 It is a structural schematic diagram of a vehicle trajectory compression device provided in an embodiment of the present application.

[0168] For example, Figure 8 As shown, the vehicle trajectory compression device 800 includes:

[0169] An acquisition module 810 is configured to acquire feature information of each of a plurality of trajectory points of a vehicle's driving trajectory, wherein the feature information includes first feature information and second feature information, wherein the first feature information is feature information unrelated to the starting point and the end point of the driving trajectory, and the second feature information is feature information related to the starting point and the end point of the driving trajectory;

[0170] Processing module 820 is used to determine a first trajectory point among multiple trajectory points whose first characteristic information meets a first preset condition, the first trajectory point indicating that the trajectory point is retained and the driving trajectory is not segmented at the first trajectory point; determine a second trajectory point among multiple trajectory points whose second characteristic information meets a second preset condition, the second trajectory point indicating that the trajectory point is retained and the driving trajectory is segmented at the second trajectory point; and compress the driving trajectory based on the first trajectory point and the second trajectory point to obtain a compressed trajectory.

[0171] Optionally, as an embodiment, the processing module 820 is specifically used to: determine a target trajectory point having the largest distance from the target line among multiple trajectory points; if the distance between the target trajectory point and the target line is greater than a preset distance threshold, determine the target trajectory point as the second trajectory point.

[0172] Optionally, as an embodiment, the processing module 820 is specifically used to: determine the trajectory point with the largest vertical distance from the target line among multiple trajectory points as the target trajectory point; or, determine the mapping point of each trajectory point in the target line; determine the trajectory point with the largest mapping distance from the mapping point among multiple trajectory points as the target trajectory point.

[0173] Optionally, as an embodiment, the processing module 820 is further used to: segment the driving trajectory based on the second trajectory point to obtain two sub-trajectories, where the sub-trajectories include a first sub-trajectory and a second sub-trajectory, the first sub-trajectory represents the sub-trajectory from the starting point of the driving trajectory to the second trajectory point, and the second sub-trajectory represents the sub-trajectory from the second trajectory point to the end point of the driving trajectory; for each sub-trajectory, traverse each trajectory point in the sub-trajectory to determine whether the sub-trajectory contains the second trajectory point; if the sub-trajectory contains the second trajectory point, segment the sub-trajectory based on the second trajectory point in the sub-trajectory until the second trajectory point no longer exists in the segmented sub-trajectory.

[0174] Optionally, as an embodiment, the processing module 820 is specifically configured to: determine, among the multiple trajectory points, a trajectory point having a direction angle greater than a preset angle or a speed difference greater than a preset difference as the first trajectory point.

[0175] Optionally, as an embodiment, the processing module 820 is specifically used to: determine the starting point, the end point, the first trajectory point and the second trajectory point in the driving trajectory as retained trajectory points, and delete the trajectory points in the driving trajectory except the retained trajectory points; and determine the broken line trajectory composed of the retained trajectory points as a compressed trajectory.

[0176] It should be noted that the above-mentioned vehicle trajectory compression device is embodied in the form of a functional unit. The term "module" here can be implemented in the form of software and / or hardware, and is not specifically limited to this.

[0177] For example, a "module" may be a software program, a hardware circuit, or a combination of the two that implements the above-described functions. The hardware circuit may include an application-specific integrated circuit (ASIC), an electronic circuit, a processor (e.g., a shared processor, a dedicated processor, or a group processor, etc.) and memory for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functions.

[0178] Therefore, the units of each example described in the embodiments of this application can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0179] Figure 9 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application.

[0180] Exemplarily, vehicle 900 includes a processor 910 , a memory 920 , and executable program code 930 .

[0181] Exemplarily, vehicle 900 includes one or more processors 910, which can support vehicle 900 in implementing the vehicle trajectory compression method in the method embodiment. Processor 910 can be a general-purpose processor or a special-purpose processor. For example, processor 910 can be a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0182] For example, the processor 910 can be used to control the vehicle 900, execute software programs, and process data of the software programs. The vehicle 900 can also include a communication unit to implement signal input (reception) and output (transmission).

[0183] Exemplarily, the vehicle 900 may include one or more memories 920 on which executable program code 930 is stored. The executable program code 930 can be executed by the processor 910 to generate instructions, so that the processor 910 executes the vehicle trajectory compression method described in the above method embodiment according to the instructions.

[0184] Optionally, data may be stored in the memory 920. Optionally, the processor 910 may read data stored in the memory 920. The data may be stored at the same storage address as the executable program code 930, or may be stored at a different storage address from the executable program code 930.

[0185] Exemplarily, the processor 910 and the memory 920 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0186] Exemplarily, the memory 920 can be used to store relevant programs of the vehicle trajectory compression method provided in the embodiment of the present application, and the processor 920 can be used to call the executable program code 930 stored in the memory 920 when controlling the vehicle to execute the vehicle trajectory compression method of the embodiment of the present application; for example, obtain characteristic information of each trajectory point among multiple trajectory points of the vehicle's driving trajectory, the characteristic information includes first characteristic information and second characteristic information, the first characteristic information is characteristic information that is not related to the starting point and end point of the driving trajectory, and the second characteristic information is characteristic information that is related to the starting point and end point of the driving trajectory; determine a first trajectory point among the multiple trajectory points whose first characteristic information meets a first preset condition, the first trajectory point indicates that the trajectory point is retained and the driving trajectory is not segmented at the first trajectory point; determine a second trajectory point among the multiple trajectory points whose second characteristic information meets a second preset condition, the second trajectory point indicates that the trajectory point is retained and the driving trajectory is segmented at the second trajectory point; compress the driving trajectory based on the first trajectory point and the second trajectory point to obtain a compressed trajectory.

[0187] The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle trajectory compression method of any of the aforementioned embodiments.

[0188] Among them, computer-readable storage media may include, but are not limited to, any type of disk, including floppy disks, optical disks, Digital Video Discs (DVDs), Compact Disc Read-Only Memory (CD-ROMs), microdrives and magneto-optical disks, Read-Only Memory (ROMs), Random Access Memory (RAMs), Erasable Programmable Read-Only Memory (EPROMs), Electrically Erasable Programmable Read-Only Memory (EEPROMs), Dynamic Random Access Memory (DRAMs), Video Random Access Memory (VRAMs), flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0189] The present application also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute the above-mentioned related steps to implement a vehicle trajectory compression method in the above-mentioned embodiment.

[0190] In addition, the vehicle provided in the embodiments of the present application may specifically be a chip, component or module, and the vehicle may include a connected processor and memory; wherein the memory is used to store instructions, and when the vehicle is running, the processor may call and execute the instructions to enable the chip to execute a vehicle trajectory compression method in the above embodiment.

[0191] Among them, the vehicle, computer-readable storage medium, computer program product or chip provided in this application are all used to execute the corresponding vehicle trajectory compression method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding vehicle trajectory compression method provided above, and will not be repeated here.

[0192] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0193] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0194] The above content is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A vehicle trajectory compression method, characterized in that: The method comprises: Acquiring characteristic information of each of a plurality of trajectory points of a vehicle driving trajectory, the characteristic information comprising first characteristic information and second characteristic information, wherein the first characteristic information is characteristic information unrelated to a starting point and an end point of the driving trajectory, and the second characteristic information is characteristic information related to the starting point and the end point of the driving trajectory; Determine a first trajectory point among the plurality of trajectory points, the first feature information of which satisfies a first preset condition, the first trajectory point being a reserved trajectory point and the driving trajectory is not segmented at the first trajectory point; Determine a second trajectory point among the plurality of trajectory points, the second feature information of which satisfies a second preset condition, the second trajectory point being a reserved trajectory point and the driving trajectory being segmented at the second trajectory point; The driving trajectory is compressed based on the first trajectory point and the second trajectory point to obtain a compressed trajectory.

2. The method according to claim 1, characterized in that The second feature information includes a distance, where the distance represents the distance from each track point to a target line, where the target line is a line connecting the starting point and the end point of the driving track; The determining of a second trajectory point among the plurality of trajectory points, wherein the second characteristic information satisfies a second preset condition, includes: Determine a target trajectory point having the largest distance from the target line among the plurality of trajectory points; If the distance between the target trajectory point and the target line is greater than a preset distance threshold, the target trajectory point is determined as the second trajectory point.

3. The method according to claim 2, characterized in that Determining the target trajectory point having the largest distance from the target line among the plurality of trajectory points includes: Determine the trajectory point with the largest vertical distance from the target line among the multiple trajectory points as the target trajectory point; Alternatively, determining a mapping point of each trajectory point in the target line; The trajectory point with the largest mapping distance from the mapping point among the multiple trajectory points is determined as the target trajectory point.

4. The method according to claim 2, characterized in that Also includes: Segmenting the driving trajectory based on the second trajectory point to obtain two sub-trajectories, the sub-trajectories including a first sub-trajectory and a second sub-trajectory, the first sub-trajectory representing a sub-trajectory from the starting point of the driving trajectory to the second trajectory point, and the second sub-trajectory representing a sub-trajectory from the second trajectory point to the end point of the driving trajectory; For each segment of the sub-trajectory, traverse each trajectory point in the sub-trajectory to determine whether the sub-trajectory has the second trajectory point; If the second track point exists in the sub-track, the sub-track is segmented based on the second track point in the sub-track until the second track point no longer exists in the segmented sub-track.

5. The method according to claim 1, wherein The first characteristic information includes a direction angle and a speed difference; The determining of a first trajectory point among the plurality of trajectory points, wherein the first feature information satisfies a first preset condition, includes: A trajectory point having a direction angle greater than a preset angle or a speed difference greater than a preset difference among the multiple trajectory points is determined as the first trajectory point.

6. The method according to claim 5, characterized in that The direction angle of the trajectory point represents the angle between a first vector and a second vector, wherein the first vector is a vector formed by the previous trajectory point of the current trajectory point and the current trajectory point, and the second vector is a vector formed by the current trajectory point and the next trajectory point of the current trajectory point; The speed difference value of the track point represents a speed difference value between the current track point and a track point preceding the current track point.

7. The method according to any one of claims 1 to 6, characterized in that The compressing the driving trajectory based on the first trajectory point and the second trajectory point to obtain a compressed trajectory includes: Determining the starting point, the end point, the first track point, and the second track point in the driving track as reserved track points, and deleting track points in the driving track except the reserved track points; The broken line trajectory formed by the retained trajectory points is determined as the compressed trajectory.

8. A vehicle trajectory compression device, characterized in that: The device comprises: an acquisition module, configured to acquire characteristic information of each of a plurality of trajectory points of a vehicle's driving trajectory, the characteristic information comprising first characteristic information and second characteristic information, the first characteristic information being characteristic information unrelated to a starting point and an end point of the driving trajectory, and the second characteristic information being characteristic information related to the starting point and the end point of the driving trajectory; A processing module is used to determine a first trajectory point among the multiple trajectory points at which the first characteristic information meets a first preset condition, the first trajectory point indicating a retained trajectory point and the driving trajectory is not segmented at the first trajectory point; determine a second trajectory point among the multiple trajectory points at which the second characteristic information meets a second preset condition, the second trajectory point indicating a retained trajectory point and the driving trajectory is segmented at the second trajectory point; and compress the driving trajectory based on the first trajectory point and the second trajectory point to obtain a compressed trajectory.

9. A vehicle, characterized in that: The vehicle comprises: a memory for storing executable program code; A processor is configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images