A vehicle trajectory generation method and system based on smoothed vehicle motion data

Abstract

The application discloses a vehicle trajectory generation method and system based on smooth vehicle motion data, relates to the field of intelligent management of intersections, and comprises the following steps: firstly, filtering the vehicle target data collected and processed by the radar and visual integrated machine, so that the motion trajectory of the vehicle is smoothed; then, the vehicle target data at intervals is used to calculate the heading angle, the accuracy of the calculation of the heading angle is improved, and the jerk feeling of the target motion when the platform trajectory is displayed is reduced; meanwhile, when the heading angle of the vehicle target is obtained, the motion state of the vehicle target is divided into different categories of motion states such as straight driving, static and turning, and according to different interval times set, the distance threshold is adaptively set to determine the driving state of the target, so that the calculation accuracy of the heading angle is ensured, and then the motion trajectory of the vehicle target is determined according to the heading angle, and the accuracy of the acquisition of the motion trajectory of the vehicle target can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent management of intersection vehicles, and in particular to a vehicle trajectory generation method and system based on smoothed vehicle motion data. BACKGROUND

[0002] In the current application in the field of traffic, there are many needs to show the vehicle motion trajectory: in the software of taking a car or real-time bus, the trajectory of the vehicle needs to be drawn on the platform side to facilitate users to read the position information and driving information of the order vehicle or intended vehicle; the motion trajectory of the vehicle needs to be recorded during the driving process of the automatic driving vehicle and the automatic parking vehicle, and the heading angle at the current time needs to be determined to determine the driving direction of the vehicle; in the application of holographic intersection, the motion trajectory of the vehicle needs to be counted on the platform side for subsequent signal control flow statistics and analysis decision, etc. The data collection scene of the holographic intersection is shown in Figure 3 The vehicle motion information shown on the signal control platform is obtained from the target position and speed data collected by different sensors, and the data usually has certain error, making it difficult to show stable motion trajectory information.

[0003] At present, when generating the vehicle motion trajectory, the classical trajectory of the vehicle is usually stored as a trajectory library, and then the Douglas algorithm is used to judge the actual trajectory, calculate the matching part and similarity of the classical trajectory and the real-time trajectory, and output the trajectory result. However, the similar trajectory matching method only applies to the regular travel activity and the stable target motion trajectory, and is not suitable for the output trajectory of the irregular motion traffic target, resulting in low generation accuracy of the vehicle motion trajectory for the holographic intersection. SUMMARY

[0004] To solve the above technical problems, the present application provides a vehicle trajectory generation method and system based on smoothed vehicle motion data, which can solve the problem of low generation accuracy of the vehicle motion trajectory for the holographic intersection.

[0005] To achieve the above purpose, in one aspect, the present application provides a vehicle trajectory generation method based on smoothed vehicle motion data, which comprises:

[0006] The vehicle target data collected and processed by the radar and visual integrated machine is subjected to preset filtering processing;

[0007] According to the vehicle target data subjected to the preset filtering processing in different preset time intervals, the offset corresponding to the vehicle target in different motion states in different preset time intervals is obtained;

[0008] acquire vehicle target distance thresholds corresponding to different preset time intervals according to offsets corresponding to different motion states of the vehicle target in the different preset time intervals;

[0009] acquire a heading angle of the vehicle target according to the preset filtered vehicle target data in different preset time intervals and the vehicle target distance thresholds corresponding to the different preset time intervals, and output a motion trajectory of the vehicle target according to the heading angle of the vehicle target.

[0010] Further, the step of acquiring vehicle target distance thresholds corresponding to different preset time intervals according to offsets corresponding to different motion states of the vehicle target in the different preset time intervals comprises:

[0011] perform Gaussian function fitting on distributions of offsets of the vehicle target in straight and turning states in different preset time intervals;

[0012] select an intersection of the fitted curves as the vehicle target distance threshold.

[0013] Further, the step of acquiring a heading angle of the vehicle target according to the preset filtered vehicle target data in different preset time intervals and the vehicle target distance thresholds corresponding to the different preset time intervals comprises:

[0014] when absolute values of longitudinal distance differences and lateral distance differences of the vehicle target in a preset time interval are both less than the vehicle target distance threshold, determine that the vehicle target is static.

[0015] Further, the step of acquiring a heading angle of the vehicle target according to the preset filtered vehicle target data in different preset time intervals and the vehicle target distance thresholds corresponding to the different preset time intervals comprises:

[0016] when only an absolute value of a longitudinal distance difference of the vehicle target in a preset time interval is less than a vehicle target distance threshold, determine that the vehicle target is straight in an east-west direction, wherein the vehicle target has a lateral distance difference greater than zero in the preset time interval, and it is determined that the target is moving eastward, or the lateral distance difference is less than zero, and it is determined that the target is moving westward; or

[0017] when only an absolute value of a lateral distance difference of the vehicle target in a preset time interval is less than a vehicle target distance threshold, determine that the vehicle target is straight in a north-south direction, wherein the vehicle target has a longitudinal distance difference greater than zero in the preset time interval, and it is determined that the target is moving northward, or the longitudinal distance difference is less than zero, and it is determined that the target is moving southward; or

[0018] When the absolute value of the longitudinal distance difference and the absolute value of the lateral distance difference of the vehicle target within a preset time interval are both greater than a vehicle target distance threshold, the vehicle is determined to be in a turning state.

[0019] Further, before the step of outputting the motion trajectory of the vehicle target according to the heading angle of the vehicle target, the method further comprises:

[0020] When the change in the heading angle of the adjacent frame vehicle target is greater than a preset abnormal threshold, the heading angle of the previous frame vehicle target is taken as the heading angle of the current frame vehicle target.

[0021] In another aspect, the present application provides a vehicle trajectory generation system based on smoothed vehicle motion data, the system comprising:

[0022] A filtering unit is configured to perform preset filtering processing on the vehicle target data collected and processed by the radar and vision integrated machine;

[0023] An acquisition unit is configured to acquire offset amounts corresponding to different motion states of the vehicle target within different preset time intervals according to the vehicle target data filtered in the preset manner within the different preset time intervals;

[0024] The acquisition unit is further configured to acquire vehicle target distance thresholds corresponding to the different preset time intervals according to the offset amounts corresponding to the different motion states of the vehicle target within the different preset time intervals;

[0025] The acquisition unit is further configured to acquire the heading angle of the vehicle target according to the vehicle target data filtered in the preset manner within the different preset time intervals and the vehicle target distance thresholds corresponding to the different preset time intervals;

[0026] An output unit is configured to output the motion trajectory of the vehicle target according to the heading angle of the vehicle target.

[0027] Further, the acquisition unit is specifically configured to perform Gaussian function fitting on the distribution of the offset amounts of the vehicle target in the straight and turning states within the different preset time intervals; and select the intersection point of the fitted curves as the vehicle target distance threshold.

[0028] Further, the acquisition unit is specifically further configured to determine that the vehicle target is in a stationary state when the absolute value of the longitudinal distance difference and the absolute value of the lateral distance difference of the vehicle target within a preset time interval are both less than the vehicle target distance threshold.

[0029] Further, the acquisition unit is specifically further configured to determine that the vehicle target is straight east-west when only the absolute value of the lateral distance difference of the vehicle target in a preset time interval is less than a vehicle target distance threshold, wherein the vehicle target in the preset time interval has a longitudinal distance difference greater than zero, and the target is determined to be driving east, and the lateral distance difference is less than zero, and the target is determined to be driving west; or determine that the vehicle target is straight north-south when only the absolute value of the lateral distance difference of the vehicle target in a preset time interval is less than a vehicle target distance threshold, wherein the vehicle target in the preset time interval has a longitudinal distance difference greater than zero, and the target is determined to be driving north, and the lateral distance difference is less than zero, and the target is determined to be driving south; or determine that the vehicle is in a turning state when the absolute value of the longitudinal distance difference and the absolute value of the lateral distance difference of the vehicle target in a preset time interval are both greater than the vehicle target distance threshold.

[0030] Further, the output unit is further configured to take the heading angle of the vehicle target of the previous frame as the heading angle of the vehicle target of the current frame when the heading angle change of the vehicle target of the adjacent frame is greater than a preset abnormal threshold.

[0031] The vehicle trajectory generation method and system based on smoothed vehicle motion data provided by the application first filter the vehicle target data collected and processed by the radar and vision integrated machine, which can smooth the vehicle motion trajectory, then take a certain interval of vehicle target data to calculate the heading angle, improve the accuracy of the heading angle calculation, and reduce the jerk feeling of target motion when the platform trajectory is displayed; At the same time, when the heading angle of the vehicle target is obtained, the motion state of the vehicle target is divided into different categories of motion states such as straight, static and turning, and according to the set different interval time, the distance threshold is set adaptively to determine the target driving state, which can ensure the accuracy of the calculation of the heading angle, and then determine the motion trajectory of the vehicle target according to the heading angle, which can improve the accuracy of the acquisition of the motion trajectory of the vehicle target. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 is a flowchart of a vehicle trajectory generation method based on smoothed vehicle motion data provided by the application;

[0033] Figure 2 is a structural schematic diagram of a vehicle trajectory generation system based on smoothed vehicle motion data provided by the application;

[0034] Figure 3 is a schematic diagram of intersection data radar and vision data collection provided by the application. DETAILED DESCRIPTION

[0035] The technical solutions of the application will be further described in detail below with the help of the drawings and examples.

[0036] As Figure 1As shown, the vehicle trajectory generation method based on smooth vehicle motion data provided by the embodiment of the application comprises the following steps:

[0037] The vehicle target data collected and processed by the radar and vision integrated machine is subjected to preset filtering processing.

[0038] Specifically, for example, the target data output by the radar and vision integrated machine can be subjected to Kalman filtering processing. The data collected by the sensor and the processing result have a certain jitter between frames, so that the detected data has a certain error in the real motion trajectory of the vehicle. The Kalman filtering can smooth the data and remove the influence of noise and interference in the observation data to a certain extent. In the measurement update stage, The prediction update stage is: Wherein, x is a position state vector, ^ represents a predicted value, ~ represents an estimated value of the previous frame. u is an input vector. z is an observation position vector. A is a state transition matrix, B is an input control matrix, K is a Kalman gain, Q is a process noise matrix, R is a measurement error matrix, P is a prediction matrix, H is an observation matrix, and I is a unit matrix.

[0039] According to the vehicle target data in different preset time intervals after the preset filtering processing, the offset corresponding to the vehicle target in different motion states in different preset time intervals is obtained.

[0040] It should be noted that the north direction and the east direction are respectively the Y-axis and the X-axis positive direction of the global coordinate system. When calculating the heading angle frame by frame, the instability of the motion will cause the abnormal jump of the heading angle. For example, a vehicle traveling in the north direction, in theory, the y value at the current time should be greater than the y value at the previous time. The displacement of the x direction should be zero. Due to the jitter error of the detection data, there will be abnormal data that the y value at the current time is less than the y value at the previous time, and in this case, a large difference in the heading angle will be calculated. Therefore, a certain interval of data can be selected, at this time, the motion distance is larger, and the calculated heading angle is more accurate.

[0041] According to the offset corresponding to the vehicle target in different motion states in different preset time intervals, the vehicle target distance threshold corresponding to the different preset time intervals is obtained.

[0042] For the embodiment of the application, step 103 can specifically include: Gaussian function fitting is performed on the distribution of the offsets of the vehicle target in the straight running state and the turning state in different preset time intervals; and the intersection of the fitted curves is selected as the vehicle target distance threshold. For example, for different time intervals Δ t , the distance threshold eps of the object motion is also different, a large number of straight running vehicles and turning vehicles are selected in the straight running area and the turning area of the road respectively, and the distance threshold eps of the object motion is calculated Δt The motion offset of the straight-ahead vehicle and the turning target within a preset time interval is obtained. Gaussian function fitting is performed on the offset distribution of the straight-ahead state and the turning state, and the intersection of the two curves is selected as the position threshold value eps.

[0043] According to the vehicle target data after the preset filtering processing within different preset time intervals and the vehicle target distance threshold corresponding to the different preset time intervals, the heading angle of the vehicle target is obtained, and the motion trajectory of the vehicle target is output according to the heading angle of the vehicle target.

[0044] For the embodiment of the application, the step of obtaining the heading angle of the vehicle target according to the preset filtering processed vehicle target data corresponding to different preset time intervals and the vehicle target distance threshold corresponding to the different preset time intervals includes: when the absolute value of the longitudinal distance difference and the absolute value of the lateral distance difference of the vehicle target within a preset time interval are both less than the vehicle target distance threshold, it is determined that the vehicle target is stationary. Gaussian function fitting is performed on the offset distribution of the vehicle target in the straight-ahead state and the turning state within different preset time intervals. The intersection of the fitted curves is selected as the vehicle target distance threshold. Or when only the absolute value of the longitudinal distance difference of the vehicle target within a preset time interval is less than the vehicle target distance threshold, it is determined to be straight-ahead in the east-west direction, wherein the lateral distance difference of the vehicle target within a preset time interval is greater than zero, it is determined that the target is driving east, and the lateral distance difference is less than zero, it is determined that the target is driving west. Or when only the absolute value of the lateral distance difference of the vehicle target within a preset time interval is less than the vehicle target distance threshold, it is determined to be straight-ahead in the north-south direction, wherein the longitudinal distance difference of the vehicle target within a preset time interval is greater than zero, it is determined that the target is driving north, and the longitudinal distance difference is less than zero, it is determined that the target is driving south. Or when the absolute value of the longitudinal distance difference and the absolute value of the lateral distance difference of the vehicle target within a preset time interval are both greater than the vehicle target distance threshold, it is determined that the vehicle is in a turning state.

[0045] For the above-mentioned turning state, the arctangent value of the distance difference can be calculated, theta=arctan(ΔY / ΔX). There are two categories for turning: the first category is north turning east, north turning west, west turning south, and east turning south; the second category is west turning north, east turning north, south turning east, and south turning west. Since the range of the heading angle is 0-360 degrees, the calculation of the arctangent value is generally periodic with pi, and the calculation angle is -pi / 2-pi / 2 or 0-pi. Therefore, according to the coordinate system, the angle value of the four turning conditions in one category needs to be processed by adding or subtracting pi.

[0046] In this embodiment of the invention, to further improve the accuracy of heading angle acquisition, before the step of outputting the motion trajectory of the vehicle target based on its heading angle, the method further includes: when the change in the heading angle of the vehicle target in adjacent frames exceeds a preset anomaly threshold, using the heading angle of the vehicle target in the previous frame as the heading angle of the vehicle target in the current frame. It should be noted that when the target is stationary, the heading angle of the target in the current frame cannot be calculated; the current strategy is to set the target's heading angle to the data from the previous frame. Although a certain distance threshold is set when calculating the heading angle, some sensor position data still become abnormal. To address this, a threshold for abnormal heading angle changes is set based on the time interval. For example, when the heading angle calculation time interval is 0.5 seconds, an anomaly can be determined when the change range between two consecutive frames reaches 90 degrees, and the target heading angle of the previous frame is set as the target heading angle of the current frame.

[0047] This invention provides a vehicle trajectory generation method based on smoothed vehicle motion data. First, the vehicle target data collected and processed by the radar-view integrated machine is filtered to smooth the vehicle's motion trajectory. Then, the heading angle is calculated using vehicle target data at intervals to improve the accuracy of the heading angle calculation and reduce the jerky feeling of the target motion when the platform displays the trajectory. Simultaneously, when acquiring the heading angle of the vehicle target, the vehicle target's motion state is divided into different categories such as straight-ahead, stationary, and turning. Based on different set intervals, a distance threshold is adaptively set to determine the target's driving state, thereby ensuring the accuracy of the heading angle calculation. Finally, the vehicle target's motion trajectory is determined based on the heading angle, improving the accuracy of acquiring the vehicle target's motion trajectory.

[0048] To implement the method provided in the embodiments of the present invention, the embodiments of the present invention provide a vehicle trajectory generation system based on smooth vehicle motion data, such as... Figure 2 As shown, the system includes: a filtering unit 21, an acquisition unit 22, and an output unit 23;

[0049] The filtering unit 21 is used to perform preset filtering processing on the vehicle target data collected and processed by the radar-visual integrated machine.

[0050] The acquisition unit 22 is used to acquire the offset of the vehicle target under different motion states in different preset time intervals based on the vehicle target data after preset filtering in different preset time intervals.

[0051] The acquisition unit 22 is also used to acquire the vehicle target distance threshold corresponding to the different preset time intervals based on the offset of the vehicle target under different motion states within different preset time intervals.

[0052] The acquisition unit 22 is further configured to acquire the heading angle of the vehicle target according to the vehicle target data filtered in different preset time intervals and the vehicle target distance threshold corresponding to each of the different preset time intervals.

[0053] The output unit 23 is configured to output the motion trajectory of the vehicle target according to the heading angle of the vehicle target.

[0054] Further, the acquisition unit 22 is specifically configured to perform Gaussian function fitting on the distribution of the offset of the vehicle target in the straight state and the turning state in different preset time intervals; and select the intersection of the fitted curves as the vehicle target distance threshold.

[0055] Further, the acquisition unit 22 is specifically configured to determine that the vehicle target is static when the absolute value of the longitudinal distance difference and the absolute value of the lateral distance difference of the vehicle target in a preset time interval are both less than the vehicle target distance threshold.

[0056] Further, the acquisition unit 22 is specifically configured to determine that the vehicle target is straight in the east-west direction when only the absolute value of the longitudinal distance difference of the vehicle target in a preset time interval is less than the vehicle target distance threshold, and the lateral distance difference of the vehicle target in the preset time interval is greater than zero, the target is determined to travel east, and the lateral distance difference is less than zero, the target is determined to travel west; or determine that the vehicle target is straight in the north-south direction when only the absolute value of the lateral distance difference of the vehicle target in a preset time interval is less than the vehicle target distance threshold, and the longitudinal distance difference of the vehicle target in the preset time interval is greater than zero, the target is determined to travel north, and the longitudinal distance difference is less than zero, the target is determined to travel south; or determine that the vehicle target is in a turning state when the absolute value of the longitudinal distance difference and the absolute value of the lateral distance difference of the vehicle target in a preset time interval are both greater than the vehicle target distance threshold.

[0057] Further, the output unit 23 is further configured to take the heading angle of the vehicle target in the previous frame as the heading angle of the vehicle target in the current frame when the change in the heading angle of the vehicle target in adjacent frames is greater than a preset abnormal threshold.

[0058] The application provides a vehicle trajectory generation method and system based on smooth vehicle motion data, which adopts filtering processing on vehicle target data collected and processed by a radar and vision integrated machine, can smooth the motion trajectory of the vehicle, then adopts vehicle target data at intervals to calculate the heading angle, improves the accuracy of the calculation of the heading angle, and reduces the jerk feeling of target motion when the platform trajectory is displayed; when the heading angle of the vehicle target is obtained, the motion state of the vehicle target is divided into different categories of motion states such as straight driving, static and turning, and according to different interval times set, the distance threshold is adaptively set to determine the target driving state, so that the calculation accuracy of the heading angle can be ensured, and then the motion trajectory of the vehicle target is determined according to the heading angle, so that the accuracy of the acquisition of the motion trajectory of the vehicle target can be improved.

[0059] It should be understood that the particular order or hierarchy of steps in the processes disclosed is an example that can be re-arranged as desired. Based on design choices, the particular order or hierarchy of steps in the processes maybe re-arranged while remaining within the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and as such claims should not be construed as necessarily limited to the particular

[0060] In the detailed description above, various features are grouped together in single embodiments for the purpose of streamlining the disclosure. This disclosed approach is not to be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are expressly recited in each claim. Rather, as the claims below reflect, inventive subject matter lies in fewer than all features of the disclosed single embodiments. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate preferred embodiment.

[0061] The disclosed embodiments are to be considered in all respects as illustrative only and not restrictive in character, as they can be modified within the scope of the appended claims. Accordingly, all junctions are intended to be included within the scope of the present disclosure to protect the disclosed subject matter and any other patentable subject matter.

[0062] The above description includes examples of one or more embodiments. Of course, not all possible combinations of components or methods described above will be employed to make or use the embodiments nor will all of the following described examples necessarily be realized. One of ordinary skill in the art, however, having the benefit of the present description, can understand how to make and use variations of the embodiments under the teachings and concepts described herein. Thus, the embodiments described herein are intended to embrace all such alterations, modifications, and variations that fall within the scope of the appended claims. Furthermore, the terms "comprises", "comprising", "includes", "including", "has", "having" and the like are to be construed open-ended, as "comprising", "including" and "having" are to be interpreted in the same manner as "consisting of", "consisting essentially of" and "substantially consisting of" under 35 U.S.C. § 112, Paragraph 6, as that terminology is interpreted in the context of the specification as a whole. Additionally, the terms "a" and "an" are to be construed as "one or more" when used in this specification. Moreover, the use of any terms "or" is to be interpreted as "and / or" unless and except the context clearly indicates otherwise.

[0063] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, and steps described in connection with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.

[0064] The various illustrative logical blocks, modules, and steps described in connection with the embodiments disclosed herein can be implemented or performed by a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor can be a microprocessor, but in the alternative, the general purpose processor can be any conventional processor, controller, microcontroller, or state machine. A processor can also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0065] The steps of the methods or algorithms described in the embodiments of this invention can be directly embedded in hardware, a software module executed by a processor, or a combination of both. The software module can be stored in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from and write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and storage medium can be housed in an ASIC, which can be housed in a user terminal. Optionally, the processor and storage medium can also be housed in different components of the user terminal.

[0066] In one or more exemplary designs, the functions described in the embodiments of the present invention can be implemented in hardware, software, firmware, or any combination of these three. If implemented in software, these functions can be stored on a computer-readable medium or transmitted on a computer-readable medium in the form of one or more instructions or code. Computer-readable media include computer storage media and communication media that facilitate the transfer of computer programs from one place to another. Storage media can be any available media that can be accessed by a general-purpose or special-purpose computer. For example, such computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage systems, or any other medium that can be used to carry or store program code in the form of instructions or data structures and other forms that can be read by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Furthermore, any connection can be suitably defined as a computer-readable medium, for example, if the software is transmitted from a website, server, or other remote resource via a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wirelessly, such as infrared, wireless, and microwave, it is also included in the defined computer-readable medium. The disks and discs mentioned include compressed disks, laser discs, optical discs, DVDs, floppy disks, and Blu-ray discs. Disks typically copy data magnetically, while discs typically copy data optically using lasers. Combinations of the above can also be contained in computer-readable media.

[0067] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for generating a vehicle trajectory based on smoothed vehicle motion data, the method comprising: The method comprises: preset filtering processing is performed on vehicle target data collected and processed by the radar and vision integrated machine; offsets corresponding to different motion states of the vehicle target in different preset time intervals are obtained according to the vehicle target data after the preset filtering processing in the different preset time intervals; vehicle target distance thresholds corresponding to the different preset time intervals are obtained according to the offsets corresponding to different motion states of the vehicle target in the different preset time intervals; a heading angle of the vehicle target is obtained according to the vehicle target data after the preset filtering processing in the different preset time intervals and the vehicle target distance thresholds corresponding to the different preset time intervals, and a motion trajectory of the vehicle target is output according to the heading angle of the vehicle target; the step of obtaining the vehicle target distance thresholds corresponding to the different preset time intervals according to the offsets corresponding to different motion states of the vehicle target in the different preset time intervals comprises: Gaussian function fitting is performed on the distribution of the offsets of the vehicle target in the different preset time intervals in the straight and turning states; an intersection point of the fitted curves is selected as the vehicle target distance threshold.

2. The method for generating vehicle trajectory based on smoothed vehicle motion data according to claim 1, wherein, the step of obtaining the heading angle of the vehicle target according to the vehicle target data after the preset filtering processing in the different preset time intervals and the vehicle target distance thresholds corresponding to the different preset time intervals comprises: when the absolute values of the longitudinal distance difference and the lateral distance difference of the vehicle target in a preset time interval are both less than the vehicle target distance threshold, it is determined that the vehicle target is stationary.

3. The method of claim 1, wherein, the step of obtaining the heading angle of the vehicle target according to the vehicle target data after the preset filtering processing in the different preset time intervals and the vehicle target distance thresholds corresponding to the different preset time intervals comprises: when only the absolute value of the longitudinal distance difference of the vehicle target in a preset time interval is less than the vehicle target distance threshold, it is determined that the vehicle target is moving east-west, wherein, when the lateral distance difference of the vehicle target in the preset time interval is greater than zero, it is determined that the target is moving east, and when the lateral distance difference is less than zero, it is determined that the target is moving west; or when only the absolute value of the lateral distance difference of the vehicle target in a preset time interval is less than the vehicle target distance threshold, it is determined that the vehicle target is moving north-south, wherein, when the longitudinal distance difference of the vehicle target in the preset time interval is greater than zero, it is determined that the target is moving north, and when the lateral distance difference is less than zero, it is determined that the target is moving south; or when the absolute values of the longitudinal distance difference and the lateral distance difference of the vehicle target in a preset time interval are both greater than the vehicle target distance threshold, it is determined that the vehicle target is in a turning state.

4. The method for generating vehicle trajectory based on smoothed vehicle motion data according to any one of claims 1-3, characterized in that, before the step of outputting the motion trajectory of the vehicle target according to the heading angle of the vehicle target, the method further comprises: when the change in the heading angle of the vehicle target between adjacent frames is greater than a preset abnormal threshold, the heading angle of the vehicle target in the previous frame is taken as the heading angle of the vehicle target in the current frame.

5. A vehicle trajectory generation system based on smoothed vehicle motion data, characterized by, the system comprises: a filtering unit configured to perform preset filtering processing on vehicle target data collected and processed by the radar and vision integrated machine; The acquisition unit is configured to acquire offset amounts corresponding to the vehicle target in different motion states in different preset time intervals according to the vehicle target data after the preset filtering processing in the different preset time intervals. The acquisition unit is further configured to acquire a vehicle target distance threshold corresponding to each of the different preset time intervals according to the offset amounts corresponding to the vehicle target in different motion states in the different preset time intervals. The acquisition unit is further configured to acquire a heading angle of the vehicle target according to the vehicle target data after the preset filtering processing in the different preset time intervals and the vehicle target distance threshold corresponding to each of the different preset time intervals. The output unit is configured to output a motion trajectory of the vehicle target according to the heading angle of the vehicle target. The acquisition unit is specifically configured to perform Gaussian function fitting on distributions of the offset amounts of the vehicle target in a straight state and a turning state in the different preset time intervals, and select an intersection of the fitted curves as the vehicle target distance threshold.

6. The vehicle trajectory generation system based on smoothed vehicle motion data according to claim 5, wherein The acquisition unit is further configured to determine that the vehicle target is static when absolute values of the longitudinal distance difference and the lateral distance difference of the vehicle target in the preset time interval are both less than the vehicle target distance threshold.

7. The vehicle trajectory generation system based on smoothed vehicle motion data according to claim 5, wherein The acquisition unit is further configured to determine that the vehicle target is moving eastward when the absolute value of the longitudinal distance difference of the vehicle target in the preset time interval is less than the vehicle target distance threshold, and the lateral distance difference of the vehicle target in the preset time interval is greater than zero, or determine that the vehicle target is moving westward when the absolute value of the longitudinal distance difference of the vehicle target in the preset time interval is less than the vehicle target distance threshold, and the lateral distance difference of the vehicle target in the preset time interval is less than zero, or determine that the vehicle target is moving northward when the absolute value of the lateral distance difference of the vehicle target in the preset time interval is less than the vehicle target distance threshold, and the longitudinal distance difference of the vehicle target in the preset time interval is greater than zero, or determine that the vehicle target is moving southward when the absolute value of the lateral distance difference of the vehicle target in the preset time interval is less than the vehicle target distance threshold, and the longitudinal distance difference of the vehicle target in the preset time interval is less than zero, or determine that the vehicle target is in a turning state when the absolute values of the longitudinal distance difference and the lateral distance difference of the vehicle target in the preset time interval are both greater than the vehicle target distance threshold.

8. The vehicle trajectory generation system based on smoothed vehicle motion data according to claim 5, wherein The output unit is further configured to take the heading angle of a previous frame of the vehicle target as the heading angle of a current frame of the vehicle target when a change in the heading angle of the vehicle target between adjacent frames is greater than a preset abnormal threshold.

Images