A method and system for identifying and warning abnormal driving of vehicles on highways
By setting up a vehicle trajectory information detection unit on the roadside, collecting and analyzing vehicle trajectory information, and combining semi-supervised learning methods to judge abnormal driving, the problem of difficulty in large-scale promotion and passive management of on-board equipment is solved, and real-time abnormal driving of highway vehicles is achieved Identification and early warning have improved the level of traffic safety management.
Patent Information
- Application Number
- CN202411247793.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-09-06
AI Technical Summary
In the prior art, the identification of abnormal driving behavior of vehicles mainly depends on vehicle-mounted equipment, which is difficult to promote on a large scale, and is passive to road traffic managers and cannot actively manage the driving status of vehicles on the road section in real time.
The vehicle trajectory information detection unit based on the road side is used to collect vehicle trajectory information, calculate driving status, and determine the threshold range in combination with the semi-supervised learning method to determine whether the vehicle is driving abnormally. The communication unit is used to go to the vehicle end, road end and traffic management center. Send warning messages.
It realizes vehicle abnormal driving identification and early warning based on roadside perception data, supports the application of "vehicle-road collaboration", improves the level of highway traffic safety management, reduces the probability of accidents, and promotes the transformation from passive management to active prevention.
Smart Images

Figure CN118762526B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of traffic safety management, and in particular relates to a method and system for identifying and warning abnormal driving of vehicles on highways. Background Art
[0002] Abnormal driving behaviors, such as continuous lane deviation and fatigue driving, not only make the driving state of the vehicle unstable, but also affect the driving of surrounding vehicles, which is the main cause of many traffic accidents, casualties and property losses. Therefore, how to identify the abnormal driving state of the vehicle has always been a research focus in the field of traffic safety.
[0003] At present, the commonly used abnormal driving behavior identification methods are mostly to identify abnormal driving behavior by analyzing the vehicle and driver information collected by the vehicle-mounted equipment. For example, by using the vehicle-mounted camera, fatigue driving behavior can be identified by collecting the driver's facial features, analyzing the changes in the driver's facial expressions, and detecting the driver's physiological and psychological signal characteristics; by using the vehicle-mounted GPS receiver and transponder, abnormal driving behaviors such as frequent turning can be identified by analyzing the vehicle's position, direction, speed and other parameters. This type of method using vehicle-mounted equipment for analysis and identification can be called an "in-vehicle" identification method. On the one hand, it is necessary to configure relevant detection equipment on the vehicle. It is difficult to be widely promoted on vehicles that have already left the factory. It can only be applied to key vehicles such as passenger cars, dangerous goods vehicles, and large trucks, which has certain limitations; on the other hand, road traffic managers hope to actively manage the driving status of vehicles on the road section, and this type of "in-vehicle" identification method is relatively passive for road traffic managers, which is not conducive to managers mastering the operation status of vehicles on the road section. Summary of the invention
[0004] The purpose of the present invention is to provide a method and system for identifying and warning abnormal driving of vehicles on highways, aiming to solve the technical problems existing in the prior art identified in the background technology.
[0005] The present invention is achieved in that:
[0006] S1: Based on the vehicle trajectory information detection unit on the roadside, collect vehicle trajectory information to form a historical vehicle information data set ; Obtain lane boundary line information and lane center line information based on the lane information storage unit.
[0007] S2: Calculate the vehicle driving status information according to the vehicle trajectory information and lane information, including: the lane where the vehicle is located, the vehicle offset distance, the vehicle original offset distance, the vehicle lateral distance, and the vehicle lateral distance change.
[0008] S3: Determine vehicle trajectory information Does it contain lane-changing segments? If so, the lane-changing segments need to be separated first, and then the remaining segments are stored in the new driving behavior set. S new .
[0009] S4: For S new For each trajectory segment in the , two indicators are calculated: the average value of the vehicle's original offset distance and the vehicle's trajectory offset, and then based on S new The average value of the original offset distance of the vehicle in each trajectory segment and the vehicle trajectory offset degree are combined with the semi-supervised learning method to determine the threshold range of the two indicators, which is the threshold range for judging whether the vehicle is driving abnormally.
[0010] S5: The vehicle trajectory information detection unit collects the current vehicle trajectory information, calculates the driving state information, the average value of the original offset distance of the vehicle, and the vehicle trajectory offset degree, and then determines whether the vehicle is driving abnormally based on the determined two types of threshold ranges.
[0011] S6: If the current vehicle is identified as being in an abnormal driving state, the processor will use the communication unit to send an abnormal driving warning message to the vehicle-side warning unit, the road-side warning unit and the road section traffic management center server.
[0012] The beneficial effects of the present invention are:
[0013] (1) The present invention provides a method, system, storage medium and device for identifying and warning abnormal driving of vehicles on highways based on roadside perception data. The method uses a vehicle trajectory information detection unit deployed on the roadside to collect vehicle trajectory data, and transmits the abnormal driving warning information obtained through analysis to the vehicle side. At the same time, a reminder is automatically issued to the abnormal driving vehicle through the roadside warning unit. It is an important application and embodiment of "vehicle-road collaboration" in highway traffic safety, conforms to the current development trend of "vehicle-road-cloud integration", and helps to promote the further development of "vehicle-road collaboration" in improving highway traffic safety.
[0014] (2) The present invention provides a method, system, storage medium and device for identifying and warning abnormal driving of vehicles on highways based on roadside sensing data. The vehicle trajectory information detection unit deployed on the roadside can continuously collect the trajectory information of vehicles passing through the road section around the clock and issue real-time warnings to abnormally driven vehicles on the road section, thereby realizing uninterrupted intelligent traffic safety management and control of highways, especially key sections, such as special sections such as long tunnels or sections with frequent accidents. It can also identify multiple abnormally driven vehicles at the same time, reduce the probability of highway accidents, and significantly improve the level of highway traffic safety.
[0015] (3) The present invention provides a method, system, storage medium and device for identifying and warning abnormal driving of highway vehicles based on roadside sensing data. The real-time abnormal driving warning information obtained by analysis will be synchronously transmitted to the section traffic management center to assist the personnel of the section traffic management center to focus on monitoring abnormal driving vehicles. The center personnel can manually issue warning information through the road-side warning unit to remind the drivers of abnormal vehicles to respond in time, thereby promoting the transformation of highway traffic safety from "passive management after the event" to "active prevention before the event", and further improving the level of highway traffic safety management. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 A flowchart of a method for identifying and warning abnormal driving of vehicles on highways provided by the present invention;
[0017] Figure 2 A schematic diagram of a highway vehicle abnormal driving identification and warning system provided by the present invention;
[0018] Figure 3 A schematic diagram of the layout of a highway vehicle abnormal driving identification and warning system provided by an embodiment of the present invention;
[0019] Figure 4 A sample graph of vehicle trajectories for maintaining normal driving in a lane provided by an embodiment of the present invention;
[0020] Figure 5 A sample graph of vehicle trajectory of abnormal driving provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0021] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0022] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.
[0023] Figure 1 A flowchart of a method for identifying and warning abnormal driving of vehicles on highways provided by the present invention is shown in FIG. Figure 1 As shown, the method includes:
[0024] S1. Collecting vehicle trajectory information based on vehicle trajectory information detection unit , forming a historical vehicle trajectory information dataset ; Based on the lane information storage unit, the lane boundary line information and lane center line information are obtained. Among them, the vehicle trajectory information It is a time series of a certain length. The information fields include vehicle ID, longitude, latitude, and time, expressed as: ,in, , , S i Indicates i Vehicle track information, id Indicates the vehicle ID assigned to the vehicle when the vehicle trajectory information detection unit detects it. k is the number of information points contained in the trajectory information, The table shows the k The longitude and latitude of a point, Indicates k The timestamp of each point is in the format of "year-month-day-hour-minute-second-millisecond". The lane centerline information is composed of continuous lane center points, and the lane boundary line information is composed of continuous lane boundary points. The lane center points and lane boundary points are both expressed in longitude and latitude. The lane centerline information and lane boundary line information are expressed as: ,in, Indicates i Lane center line or lane boundary line, represents a lane center point or lane boundary point, .
[0025] S2. Calculate the vehicle driving status information based on the vehicle trajectory information and lane information, including: the lane where the vehicle is located, the vehicle offset distance, the original vehicle offset distance, the vehicle lateral distance, and the change in the vehicle lateral distance. The vehicle offset distance refers to the distance between the vehicle and the center line of the lane where it is located, expressed as d i Indicates that the vehicle is i timestamp (i.e. i If the trajectory point is closer to the outermost lane boundary line than the lane center line, then d is a positive value. If the trajectory point is closer to the innermost lane boundary line than the lane center line, then d The original offset distance of the vehicle refers to the distance between the vehicle and the center line of the original lane. The original lane refers to the distance between the vehicle and the center line of the original lane at the start time frame. t 0 Next, use L i Indicates that the vehicle is i timestamp (i.e. iThe lateral distance of a vehicle refers to the distance between the vehicle and the innermost lane boundary line, expressed as D i Indicates that the vehicle is i timestamp (i.e. i information points) of the vehicle’s lateral distance, , W is the lane width, Lane i For the i The lane number where the vehicle is located at a timestamp, the innermost lane is recorded as lane 1, and the lane numbers increase from the innermost to the outermost.
[0026] Specific:
[0027] S21. Calculate the starting time frame t 0 The vehicle offset distance, the lane where the vehicle is located, the original offset distance of the vehicle, and the lateral distance of the vehicle;
[0028] First, calculate the distance between the vehicle trajectory point and the center line of each lane, and find the minimum value. The lane where the lane center line matches the minimum value is the lane where the vehicle is located, marked as the original lane, recorded as Lane 0 , the minimum value is the vehicle offset distance at the start time frame d 0 and the original offset distance of the vehicle L 0 ;
[0029] According to the vehicle offset distance, lane number, and lane width, the lateral distance of the vehicle is obtained;
[0030] S22: Calculate the vehicle offset distance, the original vehicle offset distance and the vehicle lateral distance in each time frame after the start time frame. If d >0.5 W , recalculate the distance between the vehicle trajectory point and the center line of each lane in the current time frame, find the minimum value, obtain the lane where the vehicle is located in the current time frame, and recalculate the vehicle offset distance in the current lane;
[0031] S23: Calculate the change in the vehicle lateral distance based on the vehicle lateral distance between two adjacent trajectory points .
[0032] S3. Determine vehicle trajectory information Does it contain lane-changing segments? If so, first separate the lane-changing segments and store the remaining segments in a new driving behavior set. S new ;
[0033] Specific:
[0034] S31. If the vehicle trajectory information contains a normal lane change segment, it is necessary to separate the normal lane change segment to avoid identifying the normal lane change as abnormal driving. The characteristics of the vehicle trajectory information of normal lane change are as follows: For a vehicle trajectory information sample containing a normal lane change segment , during normal lane change, the lateral distance of the vehicle D i Continuous increase or decrease, that is, the change in the lateral distance of the vehicle Continuously positive or negative, depending on the direction of the vehicle's lane change; when the vehicle deviates from the distance When the absolute value of starts to increase from close to 0, the lane change start timestamp is recorded. a ; When the vehicle enters the adjacent target lane, record the lane change crossing timestamp c , at this time the vehicle offset distance The absolute value is close to 0.5 W ; After the vehicle crosses the lane line, it gradually approaches the center line of the target lane, and the vehicle offset distance The absolute value of gradually decreases; when the vehicle offsets the distance When it approaches 0 again, record the lane change end timestamp b The lane-changing segment is recorded as .
[0035] S32: If the vehicle trajectory information If a lane number change is detected in the process, the lane change sample is judged based on the vehicle trajectory information characteristics of the normal lane change. If it can be extracted, the lane change segment is separated. , the rest of the fragments and It is stored in the driving behavior collection as an unlabeled sample S new .
[0036] S4. For S new For each trajectory segment in the vehicle, the average original offset distance and the vehicle trajectory offset are calculated, and then based on S new The average value of the original offset distance of the vehicle and the vehicle trajectory offset degree of each trajectory segment are combined with a semi-supervised learning method to determine the threshold range of the average value of the original offset distance of the vehicle and the vehicle trajectory offset degree, and judge whether the vehicle is in the threshold range of abnormal driving;
[0037] Specific:
[0038] S41, based on the original vehicle offset distance of all information points in the vehicle trajectory information L i , calculate the average value of the original offset distance of the vehicleL a :
[0039] ;
[0040] S42: according to the lateral distance of all information points in the vehicle trajectory information D i , calculate the vehicle trajectory deviation :
[0041] ;
[0042] In the formula, is the average value of the vehicle's lateral distance, and k is the number of trajectory points;
[0043] S43, according to S new The average vehicle trajectory deviation distance La and vehicle trajectory deviation degree of each sample in , mark a small number of samples with obvious trajectory characteristics, including: keeping the lane normal driving, significant abnormal driving, the trajectory characteristics are as follows:
[0044] Trajectory characteristics of keeping the lane normal: the vehicle keeps the current lane unchanged and drives steadily near the center line of the lane. If the vehicle deviates, the driver will adjust the vehicle as soon as possible to ensure stable driving. Therefore, the average deviation distance of the vehicle trajectory L a and vehicle trajectory deviation All very small.
[0045] Significant abnormal driving trajectory characteristics: When the driver is tired or distracted, it is difficult to concentrate and the driver's ability to control the vehicle is weakened. If the vehicle trajectory deviates, it is difficult for the driver to correct it quickly, resulting in large fluctuations in the vehicle trajectory. Therefore, the average value of the vehicle trajectory deviation distance L a and vehicle trajectory deviation All are larger;
[0046] S44, using semi-supervised classification learning algorithm, S new The labeled samples and unlabeled samples in the model are trained to obtain the vehicle trajectory deviation threshold and the vehicle's original offset distance threshold .
[0047] S5, the vehicle trajectory information detection unit collects the current vehicle trajectory information, and calculates the driving state information, the average value of the original offset distance of the vehicle, and the vehicle trajectory offset degree, and determines whether the vehicle is driving abnormally based on the determined average value of the original offset distance of the vehicle and the threshold range of the vehicle trajectory offset degree;
[0048] Specific:
[0049] According to the current vehicle trajectory information, the vehicle driving status information is calculated to determine whether the vehicle's lane number has changed, which is divided into the following situations:
[0050] (1) If the lane number remains unchanged:
[0051] ① The vehicle trajectory deviation is greater than the threshold , the average value of the original offset distance of the vehicle is greater than the threshold , indicating that the vehicle trajectory has large fluctuations and is identified as abnormal driving.
[0052] ②The vehicle trajectory deviation is much smaller than the threshold , the average value of the original offset distance of the vehicle is greater than the threshold , indicating that although the vehicle is driving smoothly, the driving route deviates from the center line of the lane, which is identified as abnormal driving;
[0053] ③ The vehicle trajectory deviation is less than but close to the threshold , the average value of the original offset distance of the vehicle is greater than the threshold , indicating that the vehicle is frequently swaying sideways and there are signs of abnormal driving. The personnel of the section traffic management center should pay close attention.
[0054] (2) If the lane number changes and it can be identified as a normal lane change based on the trajectory characteristics of a normal lane change, then it is normal driving.
[0055] (3) If the lane number changes, but it is not a normal lane change:
[0056] ① The vehicle trajectory deviation is greater than the threshold , the average value of the original offset distance of the vehicle is greater than the threshold , indicating that there are abnormal fluctuations in the vehicle trajectory, which is identified as abnormal driving.
[0057] ② The vehicle trajectory deviation is less than the threshold , the average value of the original offset distance of the vehicle is greater than the threshold , indicating that the vehicle swung back and forth near the lane boundary line, and the vehicle occupied two lanes, which was identified as abnormal driving.
[0058] From the calculation formula of the average value of the original vehicle offset distance and the vehicle track deviation, it can be seen that if the vehicle track deviation is large, the average value of the original vehicle offset distance will also be large. Therefore, the vehicle track deviation will not be greater than the threshold. And the average value of the original offset distance of the vehicle is less than the threshold situation.
[0059] S6. If the current vehicle is identified as being in an abnormal driving state, abnormal driving warning information is sent to the vehicle-side warning unit, the road-side warning unit and the section traffic management center server through the communication unit.
[0060] If the current vehicle is identified as being in an abnormal driving state, the processor will send a warning message to the corresponding vehicle through the vehicle-side warning unit, and issue a warning message through the road-side warning unit to remind the abnormally driving vehicle, and transmit the abnormal driving warning information to the section traffic management center server to assist the section traffic management center personnel in receiving the abnormal driving vehicle information through the section traffic management center server and conducting key monitoring.
[0061] The present invention also provides a highway vehicle abnormal driving recognition and warning system, such as Figure 2 As shown, the system comprises:
[0062] Processor, vehicle trajectory information detection unit, lane information storage unit, communication unit, vehicle-side warning unit, road-side warning unit, section traffic management center server, wherein the vehicle trajectory information detection unit, lane information storage unit, vehicle-side warning unit, road-side warning unit, section traffic management center server are all connected to the processor via the communication unit, and the communication unit is used for internal and external communication of the system. Figure 3 It is a schematic diagram of the deployment of an abnormal driving identification and warning system for highway vehicles provided by an embodiment of the present invention.
[0063] The vehicle trajectory information detection unit includes a laser radar and a millimeter wave radar, which are arranged at an unobstructed position outside the road and are arranged at intervals within the road section to collect vehicle trajectory information. The collection frequency is 0.1s, and within a road section of a certain length, a vehicle trajectory information detection unit is arranged at a certain distance to ensure that the trajectory information of the vehicle within the road section can be continuously collected. The lane information storage unit is used to store lane information, and the lane information is uploaded to the processor through the communication unit;
[0064] The lane information storage unit is used to store lane information and upload the lane information to the processor through the communication unit;
[0065] The processor is used to analyze the vehicle driving state based on the collected vehicle trajectory information and the stored lane information, and generate abnormal driving warning information according to the analysis result;
[0066] The roadside warning unit includes a display screen and a roadside broadcast, which are arranged at unobstructed positions on both sides of the road and are connected to the output end of the processor through a communication unit, and are used to receive and publish vehicle abnormal driving warning information generated by the processor;
[0067] The vehicle-side warning unit includes a vehicle-mounted display screen arranged inside the vehicle, connected to the output end of the processor through a communication unit, and used to receive and publish abnormal driving warning information generated by the processor;
[0068] The road section traffic management center server is connected to the output end of the processor through a communication unit, and is used to receive and convey the abnormal driving status of the vehicle.
[0069] In some embodiments of the present invention, the vehicle trajectory information detection unit collects vehicle trajectory information through a laser radar;
[0070] In some embodiments of the present invention, the roadside warning unit uses roadside broadcasting and dynamic information boards.
[0071] In some embodiments of the present invention, the vehicle-side warning unit uses a vehicle-mounted display screen.
[0072] In some embodiments of the present invention, the communication unit is implemented through 4G communication or 5G communication or wired communication.
[0073] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.
[0074] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0075] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0076] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
[0077] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for identifying and warning abnormal driving of vehicles on highways, characterized in that: The method comprises: S1, based on the roadside vehicle trajectory information detection unit, collects vehicle trajectory information and forms a historical vehicle information data set , and obtaining lane boundary line information and lane center line information based on the lane information storage unit; S2. Calculate vehicle driving state information according to the vehicle trajectory information and lane information, wherein the vehicle driving state information includes: the lane where the vehicle is located, the vehicle offset distance, the original vehicle offset distance, the vehicle lateral distance, and the vehicle lateral distance change; S3. Determine vehicle trajectory information Does it contain lane-changing segments? If so, first separate the lane-changing segments and store the remaining segments in a new driving behavior set. S new ; S4. For S new For each trajectory segment in the vehicle, the average original offset distance and the vehicle trajectory offset are calculated, and then based on S new The average value of the original offset distance of the vehicle and the vehicle trajectory offset degree of each trajectory segment are combined with a semi-supervised learning method to determine the threshold range of the average value of the original offset distance of the vehicle and the vehicle trajectory offset degree, and judge whether the vehicle is in the threshold range of abnormal driving; S5, the vehicle trajectory information detection unit collects the current vehicle trajectory information, and calculates the driving state information, the average value of the original offset distance of the vehicle, and the vehicle trajectory offset degree, and determines whether the vehicle is driving abnormally based on the determined average value of the original offset distance of the vehicle and the threshold range of the vehicle trajectory offset degree; S6. If the current vehicle is identified as being in an abnormal driving state, abnormal driving warning information is sent to the vehicle-side warning unit, the road-side warning unit and the road section traffic management center server through the communication unit; In step S1, the vehicle trajectory information is a time series of a certain length, and the information fields include vehicle ID, longitude, latitude, and time. The vehicle trajectory information is expressed as: ,in, , , represents the i-th vehicle trajectory information, id represents the vehicle ID assigned to the vehicle when the vehicle trajectory information detection unit detects it, k is the number of information points contained in the trajectory information, represent the longitude and latitude of the kth point respectively, Indicates the timestamp of the kth point. The timestamp format is "year-month-day-hour-minute-second-millisecond"; The lane centerline information is composed of continuous lane center points, and the lane boundary line information is composed of continuous lane boundary points. The lane center points and lane boundary points are both represented by longitude and latitude. The lane centerline information and lane boundary line information are represented as follows: ,in, represents the center line or lane boundary line of the i-th lane, represents a lane center point or lane boundary point, ; In step S2, the vehicle offset distance is used to refer to the distance between the vehicle and the center line of the lane where it is located. d i Indicates that the vehicle is i The vehicle offset distance at each timestamp; If the trajectory point is closer to the outermost lane boundary line than the lane center line, then d is a positive value, if the trajectory point is closer to the innermost lane boundary line than the lane center line, then d is a negative value; The original vehicle offset distance is used to refer to the distance between the vehicle and the center line of the original lane. The original lane is used to refer to the distance between the vehicle and the center line of the original lane at the start time frame. t 0 Next, use L i Indicates that the vehicle is i The original offset distance of the vehicle at the timestamp; The vehicle lateral distance is used to refer to the distance between the vehicle and the innermost lane boundary line. D i Indicates that the vehicle is i The lateral distance of the vehicle at each time stamp, , W is the lane width, Lane i For the i The lane number where the vehicle is located at each timestamp. The innermost lane is recorded as lane 1, and the lane numbers increase from the innermost to the outermost. S2 specifically includes: S21. Calculate the starting time frame t 0 The vehicle offset distance, the lane where the vehicle is located, the original offset distance of the vehicle, and the lateral distance of the vehicle; First, calculate the distance between the vehicle trajectory point and the center line of each lane, and find the minimum value. The lane where the lane center line matches the minimum value is the lane where the vehicle is located, marked as the original lane, recorded as Lane 0 , the minimum value is the vehicle offset distance at the start time frame d 0 and the original offset distance of the vehicle L 0 ; According to the vehicle offset distance, lane number, and lane width, the lateral distance of the vehicle is obtained; S22: Calculate the vehicle offset distance, the original vehicle offset distance and the vehicle lateral distance in each time frame after the start time frame. If d >0.5 W , recalculate the distance between the vehicle trajectory point and the center line of each lane in the current time frame, find the minimum value, obtain the lane where the vehicle is located in the current time frame, and recalculate the vehicle offset distance in the current lane; S23: Calculate the change in the vehicle lateral distance based on the vehicle lateral distance between two adjacent trajectory points ; S3 specifically includes: S31. If the vehicle trajectory information includes a normal lane-changing segment, separate the normal lane-changing segment; S32: If the vehicle trajectory information If a lane number change is detected in the process, the lane change sample is judged based on the vehicle trajectory information characteristics of the normal lane change. If it can be extracted, the lane change segment is separated. The remaining clips are stored in the driving behavior collection as unlabeled samples. S new; S4 specifically includes: S41, based on the original vehicle offset distance of all information points in the vehicle trajectory information L i , calculate the average value of the original offset distance of the vehicle L a : ; S42: according to the lateral distance of all information points in the vehicle trajectory information D i , calculate the vehicle trajectory deviation : ; In the formula, is the average value of the vehicle's lateral distance, and k is the number of trajectory points; S43, according to S new The average vehicle trajectory offset distance L of each sample a and vehicle trajectory deviation , mark a small number of samples with obvious trajectory features; S44, using semi-supervised classification learning algorithm, S new The labeled samples and unlabeled samples in the model are trained to obtain the vehicle trajectory deviation threshold and the vehicle's original offset distance threshold .
2. The method according to claim 1, characterized in that S5 specifically includes: According to the collected current vehicle trajectory information, the vehicle driving status information is calculated to determine whether the vehicle is changing lanes normally; If the lane change is abnormal, the vehicle trajectory deviation threshold and the vehicle's original offset distance threshold , determine whether the vehicle is driving abnormally.
3. The method according to claim 2, characterized in that S6 specifically includes: If the current vehicle is identified as being in an abnormal driving state, a warning message is sent to the corresponding vehicle through the vehicle-side warning unit, and the warning message is issued through the road-side warning unit to remind the abnormally driving vehicle, and the abnormal driving warning information is transmitted to the section traffic management center server.
Citation Information
Cited By
Vehicle abnormal driving identification early warning method and system
CN119399997A
A method and system for identifying and warning abnormal vehicle driving
CN119399997B
