Vehicle lane change detection method, device, computer equipment and medium

Abstract

The present invention discloses a vehicle lane change detection method, device, computer equipment and medium, the steps include: S01. Acquire road boundary data, lane line data and historical driving data of the detected vehicle around the detected vehicle; S02. Determine the boundary range according to the road boundary data; S03. Based on the determined boundary range, extract the lane line trend curve around the detected vehicle according to the lane line data, and extract the vehicle's historical driving trajectory according to the historical driving data; S04. Determine whether the vehicle has changed lanes according to the distance change trend between the lane line trend curve and the historical driving trajectory. The present invention can detect and predict the lane change behavior of the vehicle, and has the advantages of simple implementation method, low cost, high detection accuracy and efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle behavior detection, and in particular to a vehicle lane change detection method, device, computer equipment and medium. Background Art

[0002] In urban roads, for autonomous vehicles, accurately identifying the vehicle's lane change behavior is not only helpful in avoiding collision risks, but also can provide guidance for path planning, thereby planning a smooth driving route, avoiding jams during driving, and improving the smoothness of autonomous driving.

[0003] In the prior art, the detection of vehicle lane change behavior is usually achieved by detecting whether the vehicle is turning, that is, by detecting the inclination of the front of the vehicle or the inclination of the driving direction. If the inclination is large, it is considered that the vehicle has changed lanes. For example, Chinese patent application CN109344704A discloses a vehicle lane change behavior detection method based on the angle between the driving direction and the lane line. This solution uses the angle between the driving direction and the road line as an indicator to measure the lane change behavior.

[0004] However, the above solution for detecting lane change behavior based on vehicle inclination will have a large number of false alarms. For example, when a vehicle is driving in its own lane, in order to prevent the vehicle from getting too close to the neighboring vehicle in the left and right directions, it may turn the vehicle's head direction briefly. The purpose is only to make a short distance adjustment in the lane so that there is a certain safety distance between the vehicle and the vehicle in the leading lane in the left and right directions, rather than turning around. That is, the vehicle has made a head-turning adjustment action so that the head direction of the vehicle deviates from the lane to a certain extent, but it is very likely that the vehicle is not changing lanes.

[0005] Lane changing behavior is actually the continuous behavior of the vehicle trajectory shifting continuously until the lane change is completed. That is, after the lane change action occurs, the vehicle will continuously change its trajectory from one lane until it successfully changes to another lane. Therefore, the vehicle's driving trajectory can reflect whether the vehicle has changed lanes. The above-mentioned traditional vehicle lane change behavior detection method fails to fully utilize the vehicle's historical driving trajectory information. However, simply based on the vehicle's driving trajectory, it is not possible to accurately judge whether the vehicle has changed lanes. There may still be false alarms. For example, in order to prevent the vehicle from being too close to the neighboring vehicle in the left and right directions, the vehicle will shift its driving direction. When the offset distance is long, the vehicle's driving trajectory is also constantly shifted, similar to the trajectory that needs to change lanes. Therefore, it is necessary to wait for the vehicle's driving trajectory to cross the lane line before it can finally determine whether there is a lane change. At this time, the vehicle's lane change behavior is already in progress, and it is impossible to pre-judge the vehicle's lane change behavior and provide a warning to the vehicle. Summary of the invention

[0006] The technical problem to be solved by the present invention is: in response to the technical problems existing in the prior art, the present invention provides a vehicle lane change detection method, device, computer equipment and medium that are simple to implement and low in cost, can not only detect and predict the lane change behavior of the vehicle, but also has high detection accuracy and efficiency.

[0007] In order to solve the above technical problems, the technical solution proposed by the present invention is:

[0008] A vehicle lane change detection method, comprising the steps of:

[0009] S01. Obtain road boundary data, lane line data and historical driving data of the vehicle under inspection around the vehicle under inspection;

[0010] S02. Determine the boundary range according to the road boundary data;

[0011] S03. Based on the determined boundary range, respectively extracting the lane line change trend curve around the inspected vehicle according to the lane line data, and extracting the vehicle's historical driving trajectory according to the historical driving data;

[0012] S04. Determine whether the vehicle has lane-changing behavior based on the distance change trend between the lane line change trend curve and the historical driving trajectory.

[0013] Furthermore, in step S01, when extracting the lane line data, the position of the target vehicle is used as a reference aiming point to obtain lane line data of a specified length before the position of the target vehicle; when extracting the historical driving data, the current position of the target vehicle is used as an end point to obtain a historical trajectory point set of a specified length of the target vehicle.

[0014] Furthermore, the step S02 includes:

[0015] S201. Extracting a road boundary change trend curve according to the road boundary data;

[0016] S202. Determine the road boundary type according to the road boundary change trend curve;

[0017] S203. Determine the boundary range according to the road boundary type and the road boundary change trend curve.

[0018] Furthermore, in step S202, different types of trend assessment models are selected in turn to match the road boundary change trend curve, and the road boundary type is determined after a successful match. The trend assessment model is used to assess the type of the curve.

[0019] Furthermore, in step S203, when it is determined that the road boundary type is a straight line type, the left and right straight line boundary ranges of the road boundary change trend curve are used as the boundary range; when it is determined that the road boundary type is a curve type, the left and right arc boundary ranges in the road boundary change trend curve are used as the boundary range.

[0020] Furthermore, in step S04, if it is determined that the distance between the historical driving trajectory and the lane line change trend curve gradually decreases within the specified time period and the historical driving trajectory reaches a preset length judgment threshold, that is, the historical driving trajectory keeps gradually approaching the lane line change trend curve within the preset length, it is determined that the inspected vehicle has a lane change behavior, otherwise it is determined that there is no lane change behavior.

[0021] Furthermore, the step S04 also includes dynamically adjusting the preset length judgment threshold according to the starting position where the vehicle's driving trajectory begins to deviate. When the distance between the starting point where the vehicle's driving trajectory begins to deviate and the road boundary is less than a preset range, a first preset length is set as a judgment threshold for judging whether the vehicle changes lanes. When the distance between the starting point where the vehicle's driving trajectory begins to deviate and the lane line is less than a preset range, a second preset length is set as a judgment threshold for judging whether the vehicle changes lanes. The first preset length is greater than the second preset length.

[0022] A vehicle lane change detection device, comprising:

[0023] A data acquisition module is used to acquire road boundary data and lane line data around the inspected vehicle and historical driving data of the inspected vehicle;

[0024] A boundary range determination module, used to determine the boundary range according to the road boundary data;

[0025] A trajectory curve extraction module, based on the determined boundary range, extracts a lane line change trend curve around the inspected vehicle according to the lane line data, and extracts a vehicle historical driving trajectory according to the historical driving data;

[0026] The lane change behavior recognition module is used to determine whether the vehicle has a lane change behavior based on the distance change trend between the lane line change trend curve and the historical driving trajectory.

[0027] A computer device comprises a processor and a memory, wherein the memory is used to store a computer program, the processor is used to execute the computer program, and the processor is used to execute the computer program to perform the above method.

[0028] A computer-readable storage medium storing a computer program, wherein the computer program implements the above method when executed.

[0029] Compared with the prior art, the advantages of the present invention are:

[0030] 1. The present invention extracts the lane line change trend curve and the vehicle's historical driving trajectory, and combines the distance change trend between the lane line change trend curve and the historical driving trajectory to quickly and accurately determine whether the vehicle has changed lanes before the vehicle crosses the lane line, thereby realizing the prediction of the vehicle's lane change behavior. At the same time, it can also avoid false alarms caused by temporary steering actions of the vehicle, effectively improving the stability and robustness of lane change detection.

[0031] 2. The present invention determines the boundary range based on the road boundary data, so that the extracted lane line change trend curve and the historical driving trajectory are limited to the effective boundary range. The comprehensive road boundary, lane line and historical trajectory data can effectively ensure the detection accuracy, and at the same time can reduce unnecessary data processing, thereby improving the detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 Schematic diagram of the implementation process of the vehicle lane change detection method in this embodiment.

[0033] Figure 2 It is a detailed implementation flow diagram of vehicle lane change detection in a specific application embodiment of the present invention.

[0034] Figure 3 Schematic diagram of the structure of the vehicle lane change detection device in this embodiment. DETAILED DESCRIPTION

[0035] The present invention is further described below in conjunction with the accompanying drawings and specific preferred embodiments, but the protection scope of the present invention is not limited thereby.

[0036] like Figure 1 As shown, the steps of the vehicle lane change detection method in this embodiment include:

[0037] S01. Obtain road boundary data, lane line data and historical driving data of the vehicle under inspection around the vehicle under inspection;

[0038] S02. Determine the boundary range according to the road boundary data;

[0039] S03. Based on the determined boundary range, respectively, extracting the lane line change trend curve around the inspected vehicle according to the lane line data, and extracting the vehicle's historical driving trajectory according to the historical driving data;

[0040] S04. Determine whether the vehicle has lane-changing behavior based on the distance change trend between the lane line change trend curve and the historical driving trajectory.

[0041] Taking into account that the vehicle's driving trajectory is constantly approaching the lane line during the lane change process, that is, the distance between the vehicle's driving trajectory and the lane line is gradually decreasing during the lane change process. If it is a temporary turning behavior, the vehicle's driving trajectory will only be briefly close to the lane line, and then restore parallel or irregular change trends (it is usually difficult for the vehicle to maintain a completely straight driving process, and there will be left and right adjustments). During non-lane change behavior, the vehicle's driving trajectory will not maintain a trend of gradually approaching the lane line for a long time (compared to short-term turning). Therefore, the trend of changes in the distance between the vehicle's historical driving trajectory and the lane line can be used to determine whether the vehicle is changing lanes.

[0042] Based on the above characteristics of the vehicle's lane changing behavior, this embodiment extracts the lane line change trend curve and the vehicle's historical driving trajectory, and combines the distance change trend between the lane line change trend curve and the historical driving trajectory. It can quickly and accurately determine whether the vehicle has a lane changing behavior before the vehicle crosses the lane line, thereby realizing the prediction of the vehicle's lane changing behavior and avoiding false alarms caused by temporary steering actions of the vehicle, thereby effectively improving the stability and robustness of lane change detection.

[0043] When a vehicle is traveling in a lane, the driving range will not exceed the left and right boundaries of the road. This embodiment determines the boundary range based on the road boundary data, so that the extracted lane line change trend curve and the historical driving trajectory are limited to the effective boundary range. Therefore, the comprehensive road boundary, lane line and historical trajectory data can effectively ensure the detection accuracy, and at the same time reduce unnecessary data processing, thereby improving the detection efficiency.

[0044] The target vehicle in this embodiment can specifically be a vehicle traveling in the scene around the current vehicle. That is, after a device that can realize the above-mentioned detection function is arranged in the vehicle, the device can detect whether there are vehicles in the environment around the current vehicle that change lanes, so that when it is identified that the vehicle has changed lanes, an early warning is provided to the current vehicle to avoid collision.

[0045] In step S01 of this embodiment, when extracting lane line data, the position of the target vehicle is used as a reference point to obtain lane line data of a specified length before the position of the target vehicle; when extracting historical vehicle driving data, the current position of the target vehicle is used as the end point to obtain a historical trajectory point set of a specified length of the target vehicle. The acquisition range and length of the lane line data and historical vehicle driving data can be selected and configured according to actual needs.

[0046] In a specific application embodiment, when the lane change detection of the target vehicle is started to acquire data, the current position of the target vehicle is saved in real time as the historical trajectory data of the target vehicle, and it is determined whether the distance between the current position and the last saved position meets a given distance threshold. If it meets the threshold, it is saved. Among them, the given distance threshold can be taken as the minimum distance between the position points in the historical trajectory. The position points in the historical trajectory are sorted in chronological order, that is, the starting point of the historical trajectory is the earliest point saved in the historical trajectory, and the end point is the last saved point. At the same time, based on the current position of the target vehicle, the nearest left and right road boundary points from the target vehicle position are extracted, and the left and right boundary data of the historical road of a given length are extracted with the nearest left and right road boundary points as the end points.

[0047] In this embodiment, step S02 includes:

[0048] S201. Extracting a road boundary change trend curve according to the road boundary data;

[0049] S202. Determine the road boundary type according to the road boundary change trend curve;

[0050] S203. Determine the boundary range according to the road boundary type and the road boundary change trend curve.

[0051] Road boundaries can be divided into straight and curved types according to different road sections. Curved types include regular arc type and irregular arc type. The types of the left and right boundaries of the road may be the same, that is, the left and right boundaries are both straight or curved. The types of the left and right boundaries may also be different, such as one side boundary is straight and the other side boundary is curved. Different types of road boundaries have different values ​​for the left and right boundaries of the road. For example, for a road boundary with both straight boundaries, the range of the left and right boundaries of the road remains unchanged (fixed value), while for a road boundary with both left and right boundaries being curved, the range of the left and right boundaries of the road changes in a curve. For a road boundary with one side of the left and right boundaries being straight and the other side being curved, the range of the boundary on one side of the road remains unchanged (fixed value), while the range of the boundary on the other side changes in a curve.

[0052] This embodiment determines the road boundary type by extracting the road boundary change trend curve, and determines the boundary range according to the road boundary type and the road boundary change trend curve, that is, the extracted left and right road boundary change trend curves are used as the boundary range, and different types of boundary ranges are determined by different types of road boundaries, so that the accurate boundary range can be flexibly determined according to different road boundary types. Compared with the traditional method of setting a fixed threshold, the robustness and environmental adaptability can be effectively improved, thereby further improving the accuracy of lane change detection.

[0053] In step S203 of this embodiment, when it is determined that the road boundary type is a straight line, the left and right straight line boundary ranges of the road boundary change trend curve are used as the final boundary range, and when it is determined that the road boundary type is a curve, the left and right arc boundary ranges in the road boundary change trend curve are used as the final boundary range. Based on the boundary range determined above, the boundary ranges of the subsequent lane line change trend curve and the vehicle history trajectory curve are determined (the upper and lower boundaries in terms of data point values, and the left and right boundaries in terms of spatial range), that is, if the extracted lane line change trend curve and the vehicle history driving trajectory are within the boundary range, the lane line change trend curve and the vehicle history trajectory curve can be accurately confined within the effective boundary range.

[0054] In step S02 of this embodiment, by selecting different types of trend assessment models in turn to match the road boundary change trend curve, the road boundary type is determined after the match is successful, and the trend assessment model is used to assess the type of the curve. Specifically, a trend assessment model (such as a corresponding linear assessment model) can be selected to match the road boundary change trend curve. If the match is successful, it is determined to be a linear road boundary. If the match is unsuccessful, another trend assessment model (such as a corresponding curve assessment model) is selected to match the road boundary change trend curve until the match is successful.

[0055] It is understandable that the road boundary types may be diverse, and the above-mentioned road boundary type division and identification methods can be configured according to actual needs. The trend assessment model can also adopt various applicable assessment models according to the actual road boundary types that need to be identified.

[0056] In step S04 of this embodiment, if it is determined that the distance between the historical driving trajectory and the lane line change trend curve is gradually decreasing and the historical driving trajectory reaches the preset length judgment threshold, that is, the historical driving trajectory keeps gradually approaching the lane line change trend curve within the specified length, it is determined that the inspected vehicle has a lane change behavior, otherwise it is determined that there is no lane change behavior. The short-term turning behavior of the vehicle will also have a historical driving trajectory deviation and the historical trajectory gradually approaches the lane line, especially when the vehicle turns instead of changing lanes for a long time (such as when the vehicle turns slowly due to vehicle congestion), so directly following the change in the distance between the lane line change trend curves of the historical driving trajectory may still have certain misjudgments, and for turning, although the duration may be long, the vehicle will not travel too long towards the lane line. In view of the above problems, this embodiment further combines the change trend of the distance between the lane line change trend curves of the historical driving trajectory and the length of the historical driving trajectory to comprehensively judge the lane change behavior of the vehicle. Only when the distance between the historical driving trajectory and the lane line change trend curve is gradually reduced, and the historical driving trajectory reaches the preset length judgment threshold at this time, indicating that the vehicle has deviated to the lane line and traveled a long distance, then it is very likely that the vehicle needs to change lanes.

[0057] The preset length required for the above historical driving trajectory can be specifically configured according to actual needs. At the same time, considering that the distance from the vehicle to the lane line after turning at different starting positions is different, if the vehicle starts close to the left or right boundary of the lane, then a longer distance is required to turn to the lane line at this time, and if the vehicle starts close to the center of the lane, then turning at this time may cross the lane line. Therefore, this embodiment further combines the starting position where the vehicle driving trajectory begins to deviate (the vehicle begins to turn) to dynamically adjust the preset length required for the above historical driving trajectory. When the distance between the starting point where the vehicle driving trajectory begins to deviate and the road boundary is less than the preset range, a first preset length is set as a judgment threshold for determining whether the vehicle changes lanes. When the distance between the starting point where the vehicle driving trajectory begins to deviate and the lane line is less than the preset range, a second preset length is set as a judgment threshold for determining whether the vehicle changes lanes, and the first preset length is greater than the second preset length. That is, if it is detected that the starting point of the vehicle deviation is close to the left or right boundary of the road, a larger preset length is set at this time. When the distance between the vehicle's historical driving trajectory and the lane line change trend curve gradually decreases, and the historical driving trajectory has reached the preset length, it is determined that the vehicle needs to change lanes; if it is detected that the vehicle is close to the lane line, a smaller preset length is set. Because when the vehicle is very close to the lane line, the vehicle still turns at this time, it is very likely that it needs to change lanes. It can also be further set to set the preset length to 0 when the distance between the vehicle and the lane line is less than a certain threshold. That is, when the distance between the vehicle's starting point and the lane line is very small, the vehicle's driving trajectory is still offset, and it can be directly determined that a lane change is needed. The configuration of the above preset length can also be refined according to actual needs to further improve the detection accuracy. The first preset length, the second preset length, and each threshold value can be configured with a specific size according to actual needs.

[0058] In this embodiment, step S04 can also make a preliminary judgment on whether the vehicle has changed lanes based on the distance change trend between the lane line change trend curve and the historical driving trajectory; when it is preliminarily judged that the vehicle has changed lanes, the final judgment on the lane change behavior is made based on the change trend of the road boundary. During the lane change process, the historical driving trajectory of the vehicle will gradually move away from the boundary on one side of the road and approach the boundary on the other side of the road. Considering the distance change trend between the lane line change trend curve and the historical driving trajectory, the preliminary judgment result may still contain false alarms. After the preliminary judgment on the existence of the lane change behavior, this embodiment further combines the distance change trend between the road boundary change trend curve and the historical driving trajectory to finally confirm whether the vehicle has changed lanes, which can reduce the probability of false alarms and the false alarm rate as much as possible.

[0059] In this embodiment, step S04 further includes comparing and analyzing the lane line change trend curve with the historical driving trajectory to ensure that both are within the road boundary.

[0060] The method of the present invention is further described below by taking the implementation of vehicle lane change detection in a specific application embodiment as an example.

[0061] like Figure 2 The detailed process of implementing vehicle lane change detection in this embodiment is as follows:

[0062] Step 1. Save the current position of the target vehicle in real time as the end point of the historical trajectory data of the target vehicle, and determine whether the distance between the current position and the last saved position meets the given distance threshold. If so, save it. The given distance threshold is the minimum distance between the position points in the historical trajectory.

[0063] Step 2. The position points in the historical trajectory are sorted in chronological order, that is, the starting point of the historical trajectory is the earliest point saved in the historical trajectory, and the end point is the last saved point.

[0064] Step 3. Based on the current position of the target vehicle, extract the nearest left and right road boundary points from the target vehicle position, take the nearest left and right road boundary points as the end points, and extract the historical road left and right boundary data of a given length.

[0065] Step 4. Use the first trend evaluation model to evaluate the road boundary type. If the match is successful, save the result. Otherwise, use the second trend evaluation model to evaluate the road boundary type. The first trend evaluation model corresponds to the evaluation straight line model, and the second trend evaluation model corresponds to the evaluation curve model.

[0066] Step 5. Extract the road boundary trend curve based on the road boundary type and determine the upper and lower boundaries of the trend threshold.

[0067] Step 6. Take the current position of the target vehicle as the reference aiming point, filter the lane line data, obtain the lane where the target vehicle is located, extract the fixed-length lane line data at the position of the target vehicle, and extract the lane line change trend curve.

[0068] Step 7. Taking the current position of the target vehicle as the end point, extract a fixed-length historical trajectory point set for the target vehicle; based on the extracted historical trajectory data, extract the historical driving trajectory of the target vehicle.

[0069] Step 8. Compare and analyze the lane line change trend curve with the historical driving trajectory to determine whether the target vehicle has changed lanes.

[0070] Since the vehicle trajectory is relatively stable in the short term, compared with the solution based on real-time behavior (such as based on the vehicle head direction), the present invention realizes vehicle lane change detection by integrating the vehicle's short-term historical trajectory trend and lane line change trend, which can effectively reduce the detection errors caused by temporary behavior of the vehicle and greatly improve the stability and robustness of lane change detection.

[0071] like Figure 3 As shown, the vehicle lane change detection device of this embodiment includes:

[0072] A data acquisition module is used to acquire road boundary data and lane line data around the inspected vehicle and historical driving data of the inspected vehicle;

[0073] A boundary range determination module, used to determine the boundary range according to the road boundary data;

[0074] The trajectory curve extraction module extracts the lane line change trend curve around the inspected vehicle based on the determined boundary range according to the lane line data, and extracts the vehicle's historical driving trajectory according to the historical driving data;

[0075] The lane change behavior recognition module is used to determine whether the vehicle has changed lanes based on the distance change trend between the lane line change trend curve and the historical driving trajectory.

[0076] In this embodiment, the boundary range determination module includes:

[0077] An extraction unit, used for extracting a road boundary change trend curve according to the road boundary data;

[0078] A type evaluation unit, used for determining the road boundary type according to a road boundary change trend curve;

[0079] The boundary determination unit is used to determine the boundary range according to the road boundary type and the road boundary change trend curve.

[0080] In this embodiment, the type assessment unit specifically selects different types of trend assessment models in sequence to match the road boundary change trend curve, and determines the road boundary type after a successful match. The trend assessment model is used to assess the type of the curve.

[0081] Specifically, if the lane change behavior recognition module of this embodiment determines that the distance between the historical driving trajectory and the lane line change trend curve gradually decreases within a specified time period and the historical driving trajectory reaches a preset length judgment threshold, that is, the historical driving trajectory keeps gradually approaching the lane line change trend curve within the preset length, it is determined that the detected vehicle has a lane change behavior, otherwise it is determined that there is no lane change behavior.

[0082] The vehicle lane change detection device of this embodiment corresponds one to one with the above-mentioned vehicle lane change detection method, and will not be described in detail here.

[0083] This embodiment also provides a computer device, including a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the computer program, and the processor is used to execute the computer program to perform the above method.

[0084] This embodiment also provides a computer-readable storage medium storing a computer program, and the above method is implemented when the computer program is executed.

[0085] Those skilled in the art will appreciate that the above description of the computer device is merely an example and does not constitute a limitation on the computer device. The computer device may include more or fewer components than described above, or may combine certain components, or may include different components, such as input and output devices, network access devices, buses, etc. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0086] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMed ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0087] If the module / unit integrated in the computer device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can be executed by the processor to implement the steps of the above-mentioned distributed crawler method embodiments based on template annotation. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, electrical signal and software distribution medium, etc.

[0088] The above is only a preferred embodiment of the present invention, and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment, it is not intended to limit the present invention. Therefore, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the content of the technical solution of the present invention shall fall within the scope of protection of the technical solution of the present invention.

Claims

1. A vehicle lane change detection method, characterized in that the steps include: S01. Obtain road boundary data, lane line data and historical driving data of the vehicle under inspection around the vehicle under inspection; S02. Determine the boundary range according to the road boundary data; S03. Based on the determined boundary range, respectively extracting the lane line change trend curve around the inspected vehicle according to the lane line data, and extracting the vehicle's historical driving trajectory according to the historical driving data; S04. judging whether the vehicle has lane change behavior according to the distance change trend between the lane line change trend curve and the historical driving trajectory; In the step S04, if it is determined that the distance between the historical driving trajectory and the lane line change trend curve gradually decreases within a specified time period and the historical driving trajectory reaches a preset length judgment threshold, that is, the historical driving trajectory keeps gradually approaching the lane line change trend curve within the preset length, it is determined that the inspected vehicle has a lane change behavior, otherwise it is determined that there is no lane change behavior; The step S04 also includes dynamically adjusting the preset length judgment threshold according to the starting position where the vehicle's driving trajectory begins to deviate. When the distance between the starting point where the vehicle's driving trajectory begins to deviate and the road boundary is less than a preset range, a first preset length is set as a judgment threshold for judging whether the vehicle changes lanes. When the distance between the starting point where the vehicle's driving trajectory begins to deviate and the lane line is less than a preset range, a second preset length is set as a judgment threshold for judging whether the vehicle changes lanes. The first preset length is greater than the second preset length.

2. The vehicle lane change detection method according to claim 1, characterized in that: In step S01, when extracting the lane line data, the position of the target vehicle is used as a reference aiming point to obtain lane line data of a specified length before the position of the target vehicle; when extracting the historical driving data, the current position of the target vehicle is used as an end point to obtain a historical trajectory point set of a specified length of the target vehicle.

3. The vehicle lane change detection method according to claim 1, characterized in that: The step S02 comprises: S201. Extracting a road boundary change trend curve according to the road boundary data; S202. Determine the road boundary type according to the road boundary change trend curve; S203. Determine the boundary range according to the road boundary type and the road boundary change trend curve.

4. The vehicle lane change detection method according to claim 3, characterized in that: In the step S202, different types of trend assessment models are selected in turn to match the road boundary change trend curve, and the road boundary type is determined after a successful match. The trend assessment model is used to assess the type of the curve.

5. The vehicle lane change detection method according to claim 3, characterized in that: In step S203, when it is determined that the road boundary type is a straight line type, the left and right straight line boundary ranges of the road boundary change trend curve are used as the boundary range; when it is determined that the road boundary type is a curve type, the left and right arc boundary ranges in the road boundary change trend curve are used as the boundary range.

6. A vehicle lane change detection device, characterized in that: include: A data acquisition module is used to acquire road boundary data and lane line data around the inspected vehicle and historical driving data of the inspected vehicle; A boundary range determination module, used to determine the boundary range according to the road boundary data; A trajectory curve extraction module, based on the determined boundary range, extracts a lane line change trend curve around the inspected vehicle according to the lane line data, and extracts a vehicle historical driving trajectory according to the historical driving data; A lane change behavior recognition module, used to determine whether the vehicle has a lane change behavior based on the distance change trend between the lane line change trend curve and the historical driving trajectory; In the lane change behavior recognition module, if it is determined that the distance between the historical driving trajectory and the lane line change trend curve gradually decreases within a specified time period and the historical driving trajectory reaches a preset length judgment threshold, that is, the historical driving trajectory keeps gradually approaching the lane line change trend curve within the preset length, it is determined that the inspected vehicle has a lane change behavior, otherwise it is determined that there is no lane change behavior; The lane-changing behavior recognition module is also used to dynamically adjust the preset length judgment threshold according to the starting position where the vehicle's driving trajectory begins to deviate. When the distance between the starting point where the vehicle's driving trajectory begins to deviate and the road boundary is less than a preset range, a first preset length is set as a judgment threshold for judging whether the vehicle changes lanes. When the distance between the starting point where the vehicle's driving trajectory begins to deviate and the lane line is less than a preset range, a second preset length is set as a judgment threshold for judging whether the vehicle changes lanes. The first preset length is greater than the second preset length.

7. A computer device comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the computer program, wherein: The processor is configured to execute the computer program to perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the method according to any one of claims 1 to 5 is implemented.

Images