Target classification method and device, equipment, medium and product

By obtaining and matching the speed and path information of the target vehicle and environmental vehicles, the target vehicle classification is realized without relying on the road network, and the classification failure problem caused by insufficient roadside unit coverage is solved, ensuring the accuracy of classification and Validity.

CN119025989APending Publication Date: 2024-11-26NEBULA LINK (SHANGHAI) TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411032183.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In actual application, the existing target classification method based on the road network is ineffective due to insufficient road-side unit coverage, and it is impossible to achieve accurate target classification without relying on the road network.

Method used

By obtaining information about the target vehicle and environmental vehicle, including speed and path point information, the historical path point matching is performed, and the relative distance and location are determined, so as to achieve the precise classification of the target vehicle and environmental vehicle.

Benefits of technology

Without relying on the road network, the precise classification of target vehicles and environmental vehicles is achieved, the effectiveness of target classification is ensured, and the classification failure problem caused by insufficient coverage of roadside units is solved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025989A_ABST
    Figure CN119025989A_ABST
Patent Text Reader

Abstract

The invention discloses a target classification method and device, equipment, a medium and a product. The method comprises the following steps: acquiring first vehicle information of a target vehicle and second vehicle information of an environmental vehicle; determining a driving speed state of the target vehicle according to the first vehicle information, and determining a first driving direction state of the target vehicle based on the driving speed state; performing historical path point matching on the target vehicle and the environment vehicle according to the first driving direction state, the first path point information and the second path point information, determining a matching result, and obtaining a relative distance between the target vehicle and the environment vehicle; and when the matching result is successful matching, determining the relative position between the target vehicle and the environment vehicle according to the relative distance, and obtaining a target classification result. According to the technical scheme, the historical path points are utilized, accurate target classification of the target vehicle and the environment vehicle is realized under the condition of not depending on a road network, and the effectiveness of target classification is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a target classification method, device, equipment, medium and product. Background Art

[0002] Vehicle to Everything (V2X) wireless communication technology includes vehicle to vehicle (V2V), vehicle to pedestrian (V2P), vehicle to roadside unit (V2I), and vehicle to network (V2N). To achieve effective warning for V2V scenarios, it is necessary to classify the vehicles around the vehicle, and then enter the corresponding scenario calculation based on the classification results.

[0003] At present, when implementing V2V scene warning based on V2X, the target classification method based on the road network is usually adopted. However, the target classification based on the road network depends on the road network matching results of the vehicle and surrounding vehicles. In actual application scenarios, there will be insufficient coverage of roadside units. Insufficient coverage of roadside units will lead to a lack of road network information, which will further cause the target classification method based on the road network to fail. Summary of the invention

[0004] The present invention provides a target classification method, device, equipment, medium and product, which can achieve accurate target classification without relying on a road network and ensure the effectiveness of target classification.

[0005] In a first aspect, an embodiment of the present disclosure provides a target classification method, including:

[0006] Acquire first vehicle information of a target vehicle and second vehicle information of an environment vehicle, wherein the first vehicle information includes at least first speed and first path point information of the target vehicle, and the second vehicle information includes at least second path point information of the environment vehicle;

[0007] Determine a driving speed state of the target vehicle according to the first vehicle information, and determine a first driving direction state of the target vehicle based on the driving speed state;

[0008] Performing historical path point matching on the target vehicle and the environment vehicle according to the first driving direction state, the first path point information, and the second path point information, determining a matching result, and obtaining a relative distance between the target vehicle and the environment vehicle;

[0009] When the matching result is a successful match, the relative position between the target vehicle and the environment vehicle is determined according to the relative distance to obtain a target classification result.

[0010] In a second aspect, an embodiment of the present disclosure provides a target classification device, including:

[0011] A vehicle information acquisition module, used to acquire first vehicle information of a target vehicle and second vehicle information of an environment vehicle, wherein the first vehicle information at least includes a first speed and first path point information of the target vehicle, and the second vehicle information at least includes second path point information of the environment vehicle;

[0012] a driving direction determination module, configured to determine a driving speed state of the target vehicle according to the first vehicle information, and determine a first driving direction state of the target vehicle based on the driving speed state;

[0013] a matching result determination module, configured to perform historical path point matching on the target vehicle and the environment vehicle according to the first driving direction state, the first path point information, and the second path point information, determine a matching result, and obtain a relative distance between the target vehicle and the environment vehicle;

[0014] The target classification module is used to determine the relative position between the target vehicle and the environment vehicle according to the relative distance when the matching result is a successful match, so as to obtain a target classification result.

[0015] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute a target classification method provided by the above-mentioned first aspect embodiment.

[0019] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement a target classification method provided in the embodiment of the first aspect above when executed.

[0020] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements a target classification method provided by the embodiment of the first aspect above.

[0021] A target classification method, device, equipment, medium and product of an embodiment of the present invention includes obtaining first vehicle information of a target vehicle and second vehicle information of an environment vehicle, wherein the first vehicle information includes at least the first speed and first path point information of the target vehicle, and the second vehicle information includes at least the second path point information of the environment vehicle; determining the driving speed state of the target vehicle according to the first vehicle information, and determining the first driving direction state of the target vehicle based on the driving speed state; matching the target vehicle and the environment vehicle with historical path points according to the first driving direction state, the first path point information and the second path point information, determining the matching result, and obtaining the relative distance between the target vehicle and the environment vehicle; when the matching result is a successful match, determining the relative position between the target vehicle and the environment vehicle according to the relative distance, and obtaining the target classification result. The above technical solution uses historical path points to achieve accurate target classification of the target vehicle and the environment vehicle without relying on the road network, thereby ensuring the effectiveness of target classification.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a target classification method provided by Embodiment 1 of the present invention;

[0025] Figure 2 is a flow chart of a target classification method provided by Embodiment 2 of the present invention;

[0026] Figure 3 This is an example diagram involving path point matching in a target classification method provided in Embodiment 2 of the present invention;

[0027] Figure 4 is a schematic diagram of the structure of a target classification device provided in Embodiment 3 of the present invention;

[0028] Figure 5 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second" and "target" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1 It is a flow chart of a target classification method provided in Example 1 of the present invention. This embodiment can be applied to target classification of environmental vehicles around a target vehicle to determine the relative position between the environmental vehicles and the target vehicle. The method can be executed by a target classification device, which can be implemented in the form of hardware and / or software.

[0033] like Figure 1 As shown, the method includes:

[0034] S101. Acquire first vehicle information of a target vehicle and second vehicle information of an environment vehicle, wherein the first vehicle information includes at least first speed and first path point information of the target vehicle, and the second vehicle information includes at least second path point information and a second driving direction state of the environment vehicle.

[0035] In this embodiment, the target vehicle can be understood as the self-vehicle, and the environment vehicle can be understood as other vehicles around the self-vehicle. The first vehicle information can be understood as the relevant information of the target vehicle, including at least the first speed and the first path point information. The first speed can be understood as the real-time speed of the target vehicle during driving, and the first path point information can be understood as the information of several historical path points marked by the target vehicle during the journey. The second vehicle information can be understood as the relevant information of the environment vehicle, including at least the second path point information, and the second path point information can be understood as the information of several historical path points marked by the environment vehicle during the journey. Among them, the first path point information and the second path point information can both be considered as a Global Navigation Satellite System (GNSS) message, including at least the heading angle and path point position of each historical path point, and the path point segment between two adjacent historical path points. Among them, the first path point information and the second path point information are updated based on a specific update frequency. The second driving direction state can understand the driving direction of the environment vehicle at the current moment, including the straight state, the conversion state and the turning state.

[0036] Specifically, the environment vehicle will mark and store the information of the waypoints and the real-time speed information in real time during driving, and aggregate them into the second vehicle information, which will be broadcasted via V2X. The target vehicle will also mark and store the information of the waypoints and the real-time first speed in real time during driving, aggregate them into the first vehicle information, and obtain the second vehicle information broadcasted by the environment vehicle via V2X.

[0037] The data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant regulations. The second vehicle information obtained is de-identified information, and the acquisition of the second vehicle information is based on the premise that the environmental vehicle uses V2X technology, broadcasts the information or has an open access license.

[0038] S102: Determine a driving speed state of the target vehicle according to the first vehicle information, and determine a first driving direction state of the target vehicle based on the driving speed state.

[0039] In this embodiment, the driving speed state can be understood as the state of the target vehicle's driving speed, including at least an idling driving state, a low-speed driving state, and a high-speed driving state. The first driving direction state can be understood as the driving direction of the target vehicle at the current moment, including at least a straight state, a switching state, and a turning state, wherein the switching state is a turn, and the turning state is a curve.

[0040] Specifically, determine whether the target vehicle is in an idling state based on the speed value of the first speed in the first vehicle information; if not, determine whether the number of historical path points in the first path point information is less than a set threshold; if not, determine the type of road on which the target vehicle is traveling based on the first speed; and determine whether the driving speed state of the target vehicle is a high-speed driving state or a low-speed driving state based on different road types.

[0041] If the target vehicle's driving speed state is a low-speed driving state, the first driving direction state of the target vehicle is determined based on the heading angle change rate corresponding to the heading angle of each historical path point in the first path point information and a pre-calculated heading angle change rate threshold. It can be understood that in the low-speed driving state, the first driving direction state can include a straight state, a conversion state and a turning state.

[0042] If the target vehicle's driving speed state is a high-speed driving state, the first driving direction state of the target vehicle is determined based on the heading angle difference between each historical path point in the first path point information, or the heading angle difference between the most recent historical path point and the heading angle of the current positioning point. It can be understood that in the high-speed driving state, the first driving direction state only includes the straight state and the turning state.

[0043] S103. When the first driving direction state or the second driving direction state is a turning state, historical path points are matched between the target vehicle and the environment vehicle according to the first path point information and the second path point information, a matching result is determined, and a relative distance between the target vehicle and the environment vehicle is obtained.

[0044] In this embodiment, the turning state represents the vehicle passing a curve. The matching result can be understood as the result obtained by matching the target vehicle with the environment vehicle based on the current positioning point and the historical path point, including a successful match and a failed match. The relative distance can be understood as the distance between the target vehicle and the environment vehicle, including the lateral distance and the longitudinal distance.

[0045] Specifically, when the first driving direction state is a turning state, or the second driving direction state in the second path point information is a turning state, path point matching is performed between the target vehicle and the environment vehicle based on each historical path point segment in the first path point information or each historical path point segment in the second path point information to obtain a matching result. During the path point matching process, the longitudinal distance and lateral distance between the two vehicles can be calculated.

[0046] S104: When the matching result is successful, the relative position between the target vehicle and the environment vehicle is determined according to the relative distance to obtain a target classification result.

[0047] In this embodiment, the relative position can be understood as the relative position between the target vehicle and the surrounding vehicles in the lateral and longitudinal directions, such as the surrounding vehicle in front of the same lane, in front of the right lane, and behind the left lane of the target vehicle. The target classification result is based on the relative position between the target vehicle and the surrounding vehicles.

[0048] Specifically, when the matching result is a successful match, the lateral lane difference between the target vehicle and the environment vehicle is determined according to the lateral distance in the relative distance and the preset lane width, and the relative position between the target vehicle and the environment vehicle is determined according to the lateral lane difference and the longitudinal distance in the relative distance. For example, when the lateral lane difference is 1, the longitudinal distance is 5m, and the target vehicle is the rear vehicle, the relative position is that the environment vehicle is in front of the left of the target vehicle, separated by 1 lane laterally and 5m longitudinally. The relative position between the target vehicle and the environment vehicle is determined as the target classification result.

[0049] A target classification method provided by an embodiment of the present invention includes obtaining first vehicle information of a target vehicle and second vehicle information of an environment vehicle, wherein the first vehicle information includes at least the first speed and first path point information of the target vehicle, and the second vehicle information includes at least the second path point information and the second driving direction state of the environment vehicle; determining the driving speed state of the target vehicle according to the first vehicle information, and determining the first driving direction state of the target vehicle based on the driving speed state; when the first driving direction state or the second driving direction state is a turning state, matching the target vehicle and the environment vehicle with historical path points according to the first path point information and the second path point information, determining the matching result, and obtaining the relative distance between the target vehicle and the environment vehicle; when the matching result is a successful match, determining the relative position between the target vehicle and the environment vehicle according to the relative distance, and obtaining the target classification result. The above technical solution uses historical path points to achieve accurate target classification of the target vehicle and the environment vehicle without relying on the road network, thereby ensuring the effectiveness of target classification.

[0050] Embodiment 2

[0051] Figure 2 It is a flow chart of a target classification method provided in the second embodiment of the present invention. This embodiment is a further optimization of any of the above embodiments, and can be applied to target classification of environmental vehicles around the target vehicle to determine the relative position between the environmental vehicles and the target vehicle. The method can be executed by a target classification device, and the target classification device can be implemented in the form of hardware and / or software.

[0052] like Figure 2 As shown, the method includes:

[0053] S201. Acquire first vehicle information of a target vehicle and second vehicle information of an environment vehicle, wherein the first vehicle information includes at least a first speed and first path point information of the target vehicle, and the second vehicle information includes at least second path point information of the environment vehicle.

[0054] S202. Determine a driving speed state of the target vehicle according to a speed interval in which the first speed is located and the number of historical path points in the first path point information. The driving speed state includes at least a first driving speed state, a second driving speed state, and a third driving speed state.

[0055] In this embodiment, the first speed can be understood as the real-time driving speed of the target vehicle. The first driving speed state is the idle driving state, and the idle speed indicates that the vehicle is started and the vehicle speed is less than the idle speed calibration value, and the idle speed calibration value indicates the maximum speed that the vehicle can reach after starting without stepping on the accelerator pedal. The second driving speed state is the low-speed driving state, and the third driving speed state is the high-speed driving state.

[0056] Specifically, if the first speed is within the speed interval range of the idle calibration interval, the target vehicle's driving speed state is determined to be the first driving speed state. If the first speed is not within the speed interval range of the idle calibration interval, and the number of historical path points in the first path point information is less than the quantity threshold, the target vehicle's driving speed state is determined to be consistent with the historical speed state of the historical time, and the historical speed state includes a low-speed driving state (a second driving speed state) and a high-speed driving state (a third driving speed state). If the first speed is not within the speed interval range of the idle calibration interval, and the number of historical path points in the first path point information is greater than or equal to the quantity threshold, the type of road on which the target vehicle is located is determined directly based on the first speed, and the target vehicle's driving speed state is determined to be the second driving speed state or the third driving speed state based on the road type.

[0057] Optionally, determining the driving speed state of the target vehicle according to the speed interval in which the first speed is located and the number of historical path points in the first path point information includes:

[0058] S2021. When the first speed is within the idle calibration interval, determine that the driving speed state of the target vehicle is the first driving speed state.

[0059] In this embodiment, the idle calibration interval can be understood as the interval between the idle minimum calibration value and the idle maximum calibration value. The idle minimum calibration value indicates the minimum speed at which the vehicle is released from the latched state and enters the idle state. The idle maximum calibration value indicates the maximum speed that the vehicle can reach without stepping on the accelerator pedal after starting. When the vehicle speed is lower than the latched calibration value of 4km / h, the vehicle heading angle will be locked to the last known heading angle that is higher than the latched calibration value of 4km / h. At this time, the vehicle enters the latched state. When the vehicle speed is higher than the idle minimum calibration value of 5km / h, the vehicle is released from the latched state.

[0060] If the first speed is between the idle minimum calibration value and the idle maximum calibration value, it is determined that the driving speed state of the target vehicle is the first driving speed state, that is, the idle driving state.

[0061] S2022: When the first speed is outside the idle calibration interval and the number of historical path points in the first path point information is less than the number threshold, determine that the driving speed state of the target vehicle is consistent with the historical speed state.

[0062] In this embodiment, the quantity threshold can be understood as a preset threshold of the number of historical path points, for example, 30. The historical speed state can be understood as the driving speed state of the historical time, and the historical speed state includes a low-speed driving state (a second driving speed state) and a high-speed driving state (a third driving speed state).

[0063] Specifically, if the first speed is not within the speed range of the idle calibration interval, it indicates that the target vehicle is in a normal driving state, and its driving speed state should be a low-speed driving state (a second driving speed state) or a high-speed driving state (a third driving speed state). At this time, the number of historical path points in the first path point information is compared with the number threshold. If the number of historical path points is less than the number threshold, the number of historical path points cannot guarantee the correctness of the logic processing. Therefore, the driving speed state of the historical time is used to determine that the driving speed state of the target vehicle is consistent with the historical speed state of the historical time.

[0064] For example, if the historical driving state at the last moment is a low-speed driving state, the first speed at the current moment is not within the speed interval of the idle calibration interval, and the number of historical path points in the first path point information is less than 30, then it is determined that the vehicle driving state at the current moment is a low-speed driving state consistent with the historical driving state. Taking the low-speed driving state as an example, the high-speed driving state is the same and will not be described in detail here.

[0065] S2023. When the first speed is outside the idle calibration interval and the number of historical path points in the first path point information is greater than or equal to the number threshold, the current driving road type corresponding to the target vehicle is determined according to the first speed, and the driving speed state of the target vehicle is determined based on the current driving road type.

[0066] In this embodiment, the current driving road type includes at least general roads, urban expressways and highways.

[0067] Specifically, if the first speed is not within the speed range of the idle calibration interval, it indicates that the target vehicle is in a normal driving state, and its driving speed state should be a low-speed driving state (a second driving speed state) or a high-speed driving state (a third driving speed state). At this time, the number of historical path points in the first path point information is compared with the number threshold. If the number of historical path points is greater than or equal to the number threshold, the number of historical path points is sufficient to ensure the correctness of the logic processing. Therefore, based on the real-time first speed, it is determined that the current driving road type of the target vehicle at the current moment is a general road, a city expressway, or a highway.

[0068] Specifically, the target vehicle is assumed to be traveling on a general road, and the first speed of the target vehicle is determined to exceed the first threshold. If not, the current driving road type is determined to be a general road. If yes, the current driving road type is determined to be an urban expressway, wherein the first threshold may be, for example, 72km / h; after the first speed exceeds the first threshold, the real-time new first speed is used to determine whether the current speed is less than the third threshold or exceeds the second threshold, wherein the second threshold may be 96km / h, and the third threshold may be 48km / h. If the speed is less than the third threshold, the current driving road type is determined to be a general road, and if the speed exceeds the second threshold, the current driving road type is determined to be an expressway; after the first speed exceeds the second threshold, the real-time new first speed is used to determine whether the current speed is less than the third threshold. If the speed is less than the third threshold, the current driving road type is determined to be a general road. It can be understood that the comparison of the first speed with the first threshold, the second threshold, and the third threshold in the above content is used to confirm the change of the current driving road type of the target vehicle during continuous driving. Finally, based on the different types of the current driving roads, the driving speed state of the target vehicle is logically judged to determine the driving speed state of the target vehicle.

[0069] Optionally, determining the driving speed state of the target vehicle based on the current driving road type includes:

[0070] a. When the current driving road type is the first type, the target vehicle is determined to be in the second driving speed state.

[0071] In this embodiment, the first type is general roads, including all urban roads except urban expressways and highways.

[0072] Specifically, when the current driving road type is the first type, that is, a general road, the first speed is less than the third threshold, and the driving speed state of the target vehicle is determined to be the second driving speed state, that is, the low-speed driving state, and participates in the subsequent first driving direction state determination based on the second driving speed state.

[0073] b. When the current driving road type is the second type, determining that the target vehicle is in the second driving speed state or the third driving speed state.

[0074] In this embodiment, the second type is an urban expressway.

[0075] Specifically, when the current driving road type is the second type, that is, an urban expressway, the first speed is greater than the first threshold and less than the second threshold, and is in an intermediate speed state, and the driving speed state of the target vehicle is determined to be the second driving speed state or the third driving speed state, that is, a low-speed driving state or a high-speed driving state, and at the same time participates in the subsequent first driving direction state determination based on the second driving speed state and the third driving speed state.

[0076] c. When the current driving road type is the third type, determining that the target vehicle is in the third driving speed state.

[0077] In this embodiment, the third type is a highway.

[0078] Specifically, when the current driving road type is the third type, i.e., a highway, the first speed is greater than the second threshold, and the driving speed state of the target vehicle is determined to be the third driving speed state, i.e., a high-speed driving state, and participates in the subsequent determination of the first driving direction state based on the third driving speed state.

[0079] S203. When the driving speed state is the first driving speed state or the second driving speed state, the heading angle change rate of each historical path point in the first path point information is compared with a preset change rate threshold, and the first driving direction state of the target vehicle is determined based on the comparison result. The first driving direction state includes at least a straight state, a conversion state and a turning state.

[0080] In this embodiment, the change rate threshold value can be understood as a pre-set value for comparing the heading angle change rate, including at least the minimum heading angle change rate in the straight state, the maximum heading angle change rate in the straight state, the minimum heading angle change rate in the turning state, the maximum heading angle change rate in the turning state, the heading angle accuracy, the allowable error of the heading angle, the minimum angular velocity and the maximum angular velocity. The comparison result can be understood as the result obtained by comparing the heading angle change rate with each change rate threshold value, such as the heading angle change rate in the constant interval is less than the minimum angular velocity and the heading angle change rate in the historical path point time period is less than the maximum heading angle change rate in the straight state.

[0081] Before determining the first driving direction state of the target vehicle, various change rate thresholds are predetermined. Specifically, they are as follows:

[0082] Based on the first speed v, the preset safety distance margin d, the headway t and the preset lane width w, r = (vt + d) 2 / w calculates the maximum turning radius r. The smaller value of r and the maximum curvature radius MAX_RADIUS for urban roads is determined as the maximum recognizable turning radius max_curve_radius. The smaller value of 0.15r and the minimum curvature radius MIN_RADIUS for urban roads is determined as the minimum recognizable turning radius min_curve_radius. Based on the maximum turning radius max_curve_radius and the minimum turning radius min_curve_radius, Calculate the maximum angular velocity yaw_max, minimum angular velocity yaw_min, and angular velocity range (yaw_min, yaw_max) corresponding to the current vehicle speed.

[0083] Considering the heading angle error, the heading angle accuracy is introduced. This value is a calibration value. After the vehicle has been driving at a constant speed on a straight road for a period of time, the standard deviation of the heading angle during this period, heading_error*2, is the heading angle accuracy error at this speed. According to the update frequency f of the historical path points and the number of historical path points n, the allowable error of the heading angle at this speed is calculated by heading_error_threshold=error*I / n. Based on the allowable error heading_error_threshold of the heading angle, the maximum angular velocity yaw_max and the minimum angular velocity yaw_min, through Calculate the heading angle change rate threshold interval, where heading_straight_down_threshold is the minimum heading angle change rate in the straight state, heading_straight_up_threshold is the maximum heading angle change rate in the straight state, heading_curve_down_threshold is the minimum heading angle change rate in the turning state, and heading_curve_up_threshold is the maximum heading angle change rate in the turning state.

[0084] Specifically, the data of the target vehicle's set number (for example, 30) most recent historical path points are counted. If the heading angle fluctuates less than the standard deviation of the heading angle, heading_error, for M consecutive times, the interval is considered to be a constant heading angle interval. If the heading angle changes monotonically for M consecutive times, the interval is considered to be a monotonic heading angle interval. The vehicle driving state is determined based on the average change rate of the heading angle within the set number of historical path points, and the change in the heading angle within the constant and monotonic intervals.

[0085] When the driving speed state is the first driving speed state, that is, the idling driving state, it is assumed that the target vehicle has no historical direction state (the direction state during driving in the historical time, including the straight state, the switching state and the turning state), then the heading angle change rate of the target vehicle within the unchanged heading angle interval, the heading angle change rate within the monotonic heading angle interval, and the heading angle change rate within a set number of all historical path point time periods are compared with each change rate threshold to obtain a comparison result, and the first driving direction state is determined based on the comparison result.

[0086] Specifically, if the comparison result is any one of the following: the heading angle change rate within the heading angle unchanged interval is less than the minimum angular velocity; the heading angle change within the heading angle unchanged interval is less than the heading angle accuracy; the heading angle change rate within the historical path point time period is less than the maximum value of the heading angle change rate in the straight state, then the first driving direction state at the current moment is determined to be the straight state. If the comparison result is that the heading angle change rate within the heading angle monotonic interval is greater than the minimum value of the heading angle change rate in the turning state, then the first driving direction state at the current moment is determined to be the conversion state. If the comparison result includes both the heading angle change rate within the historical path point time period being greater than the maximum angular velocity; and the minimum angular velocity being greater than the allowable error of the heading angle, then the first driving direction state at the current moment is determined to be the turning state.

[0087] When the driving speed state is the second driving speed state, that is, when driving at a low speed, the target vehicle has a historical direction state. Based on the historical direction state of the target vehicle, the heading angle change rate within the unchanged heading angle interval, the heading angle change rate within the monotonic heading angle interval, and the heading angle change rate within a set number of all historical path point time periods of the target vehicle are compared with each change rate threshold to obtain a comparison result, and the first driving direction state is determined based on the comparison result.

[0088] Specifically, when the historical direction state is the straight state, if the comparison result is any one of the following: the heading angle change amount within the unchanged heading angle interval is less than the heading angle accuracy; the heading angle change rate within the historical path point time period is less than the minimum value of the heading angle change rate in the turning state and the minimum angular velocity is less than the allowable error of the heading angle; the heading angle change rate within the historical path point time period is less than the maximum value of the heading angle change rate in the straight state, it is determined that the first driving direction state at the current moment remains in the straight state. If the comparison result also includes that the heading angle change rate within the historical path point time period is less than the maximum value of the heading angle change rate in the straight state; the heading angle change rate within the heading angle monotonic interval is greater than the maximum value of the heading angle change rate in the turning state, it is determined that the first driving direction state at the current moment is switched from the straight state to the conversion state. If the comparison result also includes that the heading angle change rate within the historical path point time period is less than the minimum value of the heading angle change rate in the turning state; the minimum angular velocity is greater than the allowable error of the heading angle, it is determined that the first driving direction state at the current moment is switched from the straight state to the turning state.

[0089] Specifically, when the historical direction state is a turning state, if the comparison result is that the heading angle change rate within the heading angle monotonic interval is greater than the minimum heading angle change rate in the straight-ahead state (or the heading angle change rate within the historical path point time period is greater than the minimum heading angle change rate in the straight-ahead state) and the heading angle change rate within the unchanged heading angle interval is greater than the minimum angular velocity; the heading angle change rate within the historical path point time period is greater than the minimum angular velocity, it is determined that the first driving direction state at the current moment remains in the turning state. If the comparison result is that the heading angle change rate within the historical path point time period is less than the minimum angular velocity; the heading angle change rate within the historical path point time period is less than the allowable error of the heading angle; the heading angle change rate within the unchanged heading angle interval is less than the minimum angular velocity, it is determined that the first driving direction state at the current moment is switched from the turning state to the straight-ahead state.

[0090] Specifically, when the historical direction state is the conversion state, if the comparison result is that the heading angle change rate in the heading angle monotonic interval is greater than the minimum value of the heading angle change rate in the turning state (or the heading angle change rate in the historical path point time period is greater than the minimum value of the heading angle change rate in the turning state) and the heading angle change rate in the heading angle constant interval is greater than the minimum angular velocity; the heading angle change rate in the historical path point time period is greater than the maximum angular velocity, it is determined that the first driving direction state at the current moment is still maintained in the conversion state. If the comparison result is that the heading angle change rate in the historical path point time period is less than the maximum value of the heading angle change rate in the straight state; the heading angle change amount in the heading angle constant interval is less than the heading angle accuracy; the heading angle change rate in the heading angle constant interval is less than the maximum value of the heading angle change rate in the straight state, it is determined that the first driving direction state at the current moment is switched from the conversion state to the straight state.

[0091] S204. When the driving speed state is the third driving speed state, the angle difference is determined according to the heading angle of the historical path point in the first path point information, the angle difference is obtained, and the first driving direction state of the target vehicle is determined based on the angle difference, and the first driving direction state includes at least a straight state and a turning state.

[0092] In this embodiment, the angle difference value can be understood as the angle difference of the heading angle.

[0093] Specifically, when the driving speed state is the third driving speed state, ie, the high-speed driving state, the state transition between the target vehicles can only be the transition between the straight-ahead state and the turning state.

[0094] When the historical direction state of the target vehicle (the direction state during the historical time, including the straight state and the turning state) is the straight state, the distance dis_len from the historical path point when the target vehicle first entered the straight state to the current positioning point (the path point where the target vehicle is currently located) is determined from the first path point information, and the angle difference dis_dir_diff between the vector formed by connecting the two points and the heading angle of the current point is formed. If the angle difference dis_dir_diff is greater than the maximum value of the heading angle change rate in the straight state heading_straight_up_threshold, and the distance dis_len between the two path points is greater than the set distance (for example, 25m), it is determined that the first driving direction state at the current moment is switched from the straight state to the turning state, otherwise, the first driving direction state remains the straight state unchanged.

[0095] When the historical direction state of the target vehicle is a turning state, traverse each historical path point in the first path point information, and solve the angle difference dis_dir_diff of the vector formed by the connection between every two adjacent historical path points. If the cumulative sum of the angle differences dis_dir_diff is less than the heading angle accuracy error, it is determined that the first driving direction state at the current moment is switched from the turning state to the execution state, otherwise, the first driving direction state maintains the turning state unchanged.

[0096] S205. When the first driving direction state or the second driving direction state is a turning state, vertically match the current positioning point in the first path point information with the historical path point segment in the second path point information to determine a first matching result.

[0097] In this embodiment, the current positioning point can be understood as the position of the vehicle at the current moment. The historical path point segment can be understood as the point segment composed of every two adjacent path points in the vehicle's historical path points. The first matching result can be understood as the result of matching the path points of the target vehicle to the environment vehicle, including successful matching and failed matching.

[0098] Specifically, when the first driving direction state or the second driving direction is a turning state, that is, when either the target vehicle or the environment vehicle is turning, the current positioning point in the first path point information of the target vehicle is vertically matched with each historical path point segment in the second path point information of the environment vehicle (that is, path point matching). Figure 3 is an example diagram involving path point matching in a target classification method provided in Embodiment 2 of the present invention; Figure 3 As shown, the historical path points of the environment vehicle are traversed, and a perpendicular line is drawn from the current positioning point of the target vehicle to the historical path points of the environment vehicle. If the foot of the perpendicular line is on the first point segment, or on other points or the extension line of other points (on the left endpoint side), the target vehicle successfully matches the historical path points of the environment vehicle.

[0099] Starting from the point segment where the target vehicle successfully matches the historical path points of the environmental vehicles, the angle sum angle_diff_sum of each two adjacent historical path point segments is calculated. If the angle sum is less than the set threshold angle_diff_sum_threshold, the final match is determined to be successful, that is, the first matching result is determined to be a successful match, and target classification based on historical path points can be performed. Otherwise, the target classification result based on historical path points is considered unreliable, and the second matching result is determined to be a failed match. Other methods are used for target classification, such as target classification based on the specific position of the positioning point.

[0100] S206: When the first driving direction state or the second driving direction state is a turning state, vertically match the current positioning point in the second path point information with the historical path point segment in the first path point information to determine a second matching result.

[0101] In this embodiment, the second matching result can be understood as the result of matching the path point of the environment vehicle to the target vehicle, including a successful match and a failed match.

[0102] Specifically, the current positioning point in the second path point information of the environmental vehicle is matched with each historical path point segment in the first path point information of the target vehicle by a perpendicular line, the historical path point segments of the target vehicle are traversed, and a perpendicular line is drawn from the current positioning point of the environmental vehicle to the historical path point segments of the target vehicle. If the foot of the perpendicular line is on the first point segment, or on other point segments or the extension line of other point segments, the environmental vehicle successfully matches the historical path points of the target vehicle.

[0103] Starting from the point segment where the environmental vehicle successfully matches the historical path point of the target vehicle, the angle sum angle_diff_sum of each two adjacent historical path point segments is calculated. If the angle sum is less than the set threshold angle_diff_sum_threshold, the final match is determined to be successful, that is, the second matching result is determined to be a successful match, and target classification based on historical path points can be performed. Otherwise, the target classification result based on historical path points is considered unreliable, and the second matching result is determined to be a failed match, and other methods are used for target classification.

[0104] S207: When the first matching result or the second matching result is a successful match, determine the relative distance between the target vehicle and the environment vehicle.

[0105] In this embodiment, when the first matching result or the second matching result is a successful match, the relative distance between the target vehicle and the surrounding vehicles is determined according to the positional relationship between the current positioning point and the historical path point segment, such as Figure 3 As shown, lon_dis5 represents the distance from the current position path point of the environmental vehicle to the most recently recorded historical path point, lon_dis2, lon_dis3 and lon_dis4 are all historical path point segments between two adjacent historical path points, lon_dis1 represents the distance between the current positioning point of the target vehicle and the current positioning point of the environmental vehicle and the closest historical path point of the environmental vehicle, the lateral distance from the current positioning point of the environmental vehicle to the historical path point segment of the target vehicle is lat_dis, and the cumulative sum of distances from lon_dis1 to lon_dis5 from the successful matching point segment is the longitudinal distance lon_dis.

[0106] S208: When the matching result is successful, determine the lateral lane difference between the target vehicle and the environment vehicle according to the lateral distance in the relative distance.

[0107] In this embodiment, when the matching result is a successful match, according to the horizontal distance lat_dis in the relative distance, Determine the lateral lane difference lane_gap between the target vehicle and the surrounding vehicle, where lane_width is the lane width. lat_dis<0 means the far vehicle is on the left side of the vehicle's forward direction, lat_dis>0 means the far vehicle is on the right side of the vehicle's forward direction. lon_dis<0 means the far vehicle is in front of the vehicle's forward direction, lon_dis>0 means the far vehicle is behind the vehicle's forward direction.

[0108] S209: Determine the relative position between the target vehicle and the environment vehicle according to the lateral lane difference and the longitudinal distance in the relative distance, and obtain a target classification result.

[0109] In this embodiment, the second driving direction state in the second vehicle information is a turning state, and the historical path matching between the target vehicle and the environment vehicle is successful, indicating that the environment vehicle is located in front of the target vehicle. If the lateral lane difference is 0, it is determined that the environment vehicle is located in front of the same lane of the target vehicle, and the environment vehicle is located in front of the same lane of the target vehicle and the specific longitudinal distance is determined as the target classification result; if the lateral lane difference is -1, it is determined that the environment vehicle is located in front of the left adjacent lane of the target vehicle, and the environment vehicle is located in front of the left adjacent lane of the target vehicle and the specific longitudinal distance is determined as the target classification result; if the lateral lane difference is less than or equal to -2, it is determined that the environment vehicle is located in front of the left far side of the target vehicle, and the environment vehicle is located in front of the left far side of the target vehicle and the specific longitudinal distance is determined as the target classification result. If the lateral lane difference is 1, it is determined that the environment vehicle is located in front of the right adjacent lane of the target vehicle, and the environment vehicle is located in front of the right adjacent lane of the target vehicle and the specific longitudinal distance is determined as the target classification result; if the lateral lane difference is greater than or equal to 2, it is determined that the environment vehicle is located in front of the right far side of the target vehicle, and the environment vehicle is located in front of the right far side of the target vehicle and the specific longitudinal distance is determined as the target classification result.

[0110] The first driving direction state in the first vehicle information is a turning state, and the historical path matching between the environment vehicle and the target vehicle is successful, indicating that the environment vehicle is located behind the target vehicle. If the lateral lane difference is 0, it is determined that the environment vehicle is located behind the same lane of the target vehicle, and the environment vehicle is located behind the same lane of the target vehicle and the specific longitudinal distance is determined as the target classification result; if the lateral lane difference is -1, it is determined that the environment vehicle is located behind the left adjacent lane of the target vehicle, and the environment vehicle is located behind the left adjacent lane of the target vehicle and the specific longitudinal distance is determined as the target classification result; if the lateral lane difference is less than or equal to -2, it is determined that the environment vehicle is located behind the left far side of the target vehicle, and the environment vehicle is located behind the left far side of the target vehicle and the specific longitudinal distance is determined as the target classification result; if the lateral lane difference is 1, it is determined that the environment vehicle is located behind the right adjacent lane of the target vehicle, and the environment vehicle is located behind the right adjacent lane of the target vehicle and the specific longitudinal distance is determined as the target classification result; if the lateral lane difference is greater than or equal to 2, it is determined that the environment vehicle is located behind the right far side of the target vehicle, and the environment vehicle is located behind the right far side of the target vehicle and the specific longitudinal distance is determined as the target classification result.

[0111] A target classification method provided by an embodiment of the present invention includes obtaining first vehicle information of a target vehicle and second vehicle information of an environment vehicle, wherein the first vehicle information includes at least a first speed and first path point information of the target vehicle, and the second vehicle information includes at least second path point information of the environment vehicle; determining a driving speed state of the target vehicle according to a speed interval in which the first speed is located and the number of historical path points in the first path point information, wherein the driving speed state includes at least a first driving speed state, a second driving speed state, and a third driving speed state; when the driving speed state is the first driving speed state or the second driving speed state, comparing a heading angle change rate of each historical path point in the first path point information with a preset change rate threshold, and determining a first driving direction state of the target vehicle based on the comparison result, wherein the first driving direction state includes at least a straight state, a conversion state, and a turning state; when the driving speed state is the third driving speed state, determining a first driving direction state of the target vehicle according to the heading angle change rate of each historical path point in the first path point information The first driving direction state of the target vehicle is determined by determining the angle difference, obtaining the angle difference value and determining the first driving direction state of the target vehicle based on the angle difference value, wherein the first driving direction state includes at least a straight state and a turning state; when the first driving direction state or the second driving direction state is a turning state, the current positioning point in the first path point information is matched with the historical path point segment in the second path point information by a vertical line to determine the first matching result; when the first driving direction state or the second driving direction state is a turning state, the current positioning point in the second path point information is matched with the historical path point segment in the first path point information by a vertical line to determine the second matching result; when the first matching result or the second matching result is successful, the relative distance between the target vehicle and the environment vehicle is determined; when the matching result is a successful match, the lateral lane difference between the target vehicle and the environment vehicle is determined according to the lateral distance in the relative distance; the relative position between the target vehicle and the environment vehicle is determined according to the lateral lane difference and the longitudinal distance in the relative distance to obtain the target classification result. The above technical scheme realizes accurate vehicle target classification under multiple factors such as vehicle driving speed, driving road type and driving direction state, especially for uneven curvature curves.

[0112] Embodiment 3

[0113] Figure 4 Schematic diagram of the structure of a target classification device provided by Embodiment 3 of the present invention. Figure 4 As shown, the device comprises:

[0114] The vehicle information acquisition module 31 is used to acquire first vehicle information of the target vehicle and second vehicle information of the environment vehicle, wherein the first vehicle information at least includes the first speed and first path point information of the target vehicle, and the second vehicle information at least includes the second path point information and the second driving direction state of the environment vehicle;

[0115] A driving direction determination module 32, configured to determine a driving speed state of the target vehicle according to the first vehicle information, and determine a first driving direction state of the target vehicle based on the driving speed state;

[0116] A matching result determination module 33 is used to perform historical path point matching on the target vehicle and the environment vehicle according to the first path point information and the second path point information when the first driving direction state or the second driving direction state is a turning state, determine a matching result, and obtain a relative distance between the target vehicle and the environment vehicle;

[0117] The target classification module 34 is used to determine the relative position between the target vehicle and the environment vehicle according to the relative distance when the matching result is a successful match, so as to obtain a target classification result.

[0118] The target classification device adopted in this technical solution utilizes historical path points to achieve accurate target classification of target vehicles and environmental vehicles without relying on the road network, thereby ensuring the effectiveness of target classification.

[0119] Optionally, the driving direction determination module 32 includes:

[0120] a speed state determining unit, which determines a driving speed state of the target vehicle according to a speed interval in which the first speed is located and the number of historical path points in the first path point information, wherein the driving speed state includes at least a first driving speed state, a second driving speed state and a third driving speed state;

[0121] a first direction determining unit, configured to compare a heading angle change rate of each historical path point in the first path point information with a preset change rate threshold value when the driving speed state is the first driving speed state or the second driving speed state, and determine a first driving direction state of the target vehicle based on the comparison result, wherein the first driving direction state includes at least a straight state, a conversion state, and a turning state;

[0122] The second direction determination unit is used to determine the angle difference according to the heading angle of the historical path point in the first path point information when the driving speed state is the third driving speed state, obtain the angle difference value and determine the first driving direction state of the target vehicle based on the angle difference value, and the first driving direction state at least includes a straight state and a turning state.

[0123] Optionally, the speed state determination unit comprises:

[0124] a first speed determination subunit, configured to determine that the driving speed state of the target vehicle is a first driving speed state when the first speed is within an idle speed calibration interval;

[0125] a second speed determination subunit, configured to determine that the driving speed state of the target vehicle is consistent with the historical speed state when the first speed is outside the idle speed calibration interval and the number of historical path points in the first path point information is less than a number threshold;

[0126] The third speed determination subunit is used to determine the current driving road type corresponding to the target vehicle according to the first speed when the first speed is outside the idle calibration interval and the number of historical path points in the first path point information is greater than or equal to a quantity threshold, and determine the driving speed state of the target vehicle based on the current driving road type.

[0127] Optionally, the third speed determination subunit is specifically used for:

[0128] When the current driving road type is the first type, determining that the target vehicle is in a second driving speed state;

[0129] When the current driving road type is the second type, determining that the target vehicle is in the second driving speed state or the third driving speed state;

[0130] When the current driving road type is the third type, it is determined that the target vehicle is in a third driving speed state.

[0131] Optionally, the matching result determination module 33 is specifically used to:

[0132] Performing vertical line matching on the current positioning point in the first path point information and the historical path point segments in the second path point information to determine a first matching result;

[0133] Performing vertical line matching on the current positioning point in the second path point information and the historical path point segments in the first path point information to determine a second matching result;

[0134] When the first matching result or the second matching result is a successful match, a relative distance between the target vehicle and the environment vehicle is determined.

[0135] Optionally, the target classification module 34 is specifically used for:

[0136] Determine a lateral lane difference between the target vehicle and the environment vehicle according to the lateral distance in the relative distance;

[0137] The relative position between the target vehicle and the environment vehicle is determined according to the lateral lane difference and the longitudinal distance in the relative distance to obtain a target classification result.

[0138] The target classification device provided in the embodiment of the present invention can execute the target classification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0139] Embodiment 4

[0140] Figure 5 : is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0141] like Figure 5 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0142] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0143] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 41 performs the various methods and processes described above, such as a target classification method.

[0144] In some embodiments, the target classification method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the target classification method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to perform the target classification method in any other appropriate manner (e.g., by means of firmware).

[0145] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0147] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0148] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0149] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0150] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0151] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0152] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A target classification method, characterized in that: include: Acquire first vehicle information of a target vehicle and second vehicle information of an environment vehicle, wherein the first vehicle information includes at least first speed and first path point information of the target vehicle, and the second vehicle information includes at least second path point information and second driving direction state of the environment vehicle; Determine a driving speed state of the target vehicle according to the first vehicle information, and determine a first driving direction state of the target vehicle based on the driving speed state; When the first driving direction state or the second driving direction state is a turning state, historical path point matching is performed on the target vehicle and the environment vehicle according to the first path point information and the second path point information, a matching result is determined, and a relative distance between the target vehicle and the environment vehicle is obtained; When the matching result is a successful match, the relative position between the target vehicle and the environment vehicle is determined according to the relative distance to obtain a target classification result.

2. The method according to claim 1, characterized in that The step of determining the driving speed state of the target vehicle according to the first vehicle information, and determining the first driving direction state of the target vehicle based on the driving speed state, comprises: Determine the driving speed state of the target vehicle according to the speed interval in which the first speed is located and the number of historical path points in the first path point information, wherein the driving speed state includes at least a first driving speed state, a second driving speed state and a third driving speed state; When the driving speed state is the first driving speed state or the second driving speed state, comparing the heading angle change rate of each historical path point in the first path point information with a preset change rate threshold, and determining the first driving direction state of the target vehicle based on the comparison result, wherein the first driving direction state includes at least a straight state, a conversion state, and a turning state; When the driving speed state is the third driving speed state, the angle difference is determined according to the heading angle of the historical path point in the first path point information, the angle difference value is obtained, and the first driving direction state of the target vehicle is determined based on the angle difference value, and the first driving direction state includes at least a straight state and a turning state.

3. The method according to claim 2, characterized in that The determining the driving speed state of the target vehicle according to the speed interval in which the first speed is located and the number of historical path points in the first path point information includes: When the first speed is within the idle calibration interval, determining that the driving speed state of the target vehicle is a first driving speed state; When the first speed is outside the idle speed calibration interval and the number of historical path points in the first path point information is less than a number threshold, determining that the driving speed state of the target vehicle is consistent with the historical speed state; When the first speed is outside the idle calibration interval and the number of historical path points in the first path point information is greater than or equal to a quantity threshold, the current driving road type corresponding to the target vehicle is determined according to the first speed, and the driving speed state of the target vehicle is determined based on the current driving road type.

4. The method according to claim 3, characterized in that The determining the driving speed state of the target vehicle based on the current driving road type includes: When the current driving road type is the first type, determining that the target vehicle is in a second driving speed state; When the current driving road type is the second type, determining that the target vehicle is in the second driving speed state or the third driving speed state; When the current driving road type is the third type, it is determined that the target vehicle is in a third driving speed state.

5. The method according to claim 1, characterized in that The performing historical path point matching on the target vehicle and the environment vehicle according to the first path point information and the second path point information, determining a matching result, and obtaining a relative distance between the target vehicle and the environment vehicle includes: Performing vertical line matching on the current positioning point in the first path point information and the historical path point segments in the second path point information to determine a first matching result; Performing vertical line matching on the current positioning point in the second path point information and the historical path point segments in the first path point information to determine a second matching result; When the first matching result or the second matching result is a successful match, a relative distance between the target vehicle and the environment vehicle is determined.

6. The method according to claim 1, characterized in that The determining the relative position between the target vehicle and the environment vehicle according to the relative distance to obtain a target classification result includes: Determine a lateral lane difference between the target vehicle and the environment vehicle according to the lateral distance in the relative distance; The relative position between the target vehicle and the environment vehicle is determined according to the lateral lane difference and the longitudinal distance in the relative distance to obtain a target classification result.

7. A target classification device, characterized in that: include: A vehicle information acquisition module, used to acquire first vehicle information of a target vehicle and second vehicle information of an environment vehicle, wherein the first vehicle information includes at least first speed and first path point information of the target vehicle, and the second vehicle information includes at least second path point information and second driving direction status of the environment vehicle; a driving direction determination module, configured to determine a driving speed state of the target vehicle according to the first vehicle information, and determine a first driving direction state of the target vehicle based on the driving speed state; a matching result determination module, configured to perform historical path point matching on the target vehicle and the environment vehicle according to the first path point information and the second path point information when the first driving direction state or the second driving direction state is a turning state, determine a matching result, and obtain a relative distance between the target vehicle and the environment vehicle; The target classification module is used to determine the relative position between the target vehicle and the environment vehicle according to the relative distance when the matching result is a successful match, so as to obtain a target classification result.

8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform a target classification method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a target classification method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements a target classification method according to any one of claims 1 to 6.