Lane departure early warning method and system and electronic equipment

By establishing multiple deviation time calculation models in the lane departure warning system, combining vehicle speed and steering conditions, the problem of inaccurate and timely early warning in the existing technology is solved, providing a more accurate and timely lane departure warning, and enhancing driving safety .

CN118928387APending Publication Date: 2024-11-12SINO TRUK JINAN POWER CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411191378.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing lane departure warning system fails to issue a warning in a timely manner when the vehicle is fast or when the distance threshold is not reached, and an error is issued during steering, resulting in inaccurate and untimely warning, affecting driving safety.

Method used

By establishing a calculation model for multiple lane departure warning time, combining vehicle speed, steering conditions and road straightness to calculate the deviation time, and comparing it with the set threshold to determine whether to issue an early warning, the consideration of vehicle speed, steering and road straightness is increased. , select the corresponding model for calculation to provide more accurate and timely early warning.

Benefits of technology

It improves the accuracy and timeliness of lane departure warnings, provides warning levels of different risk levels, helps drivers make predictions early, and enhances driving safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928387A_ABST
    Figure CN118928387A_ABST
Patent Text Reader

Abstract

The invention provides a lane departure early warning method and system and electronic equipment, and relates to the field of stirring lane departure early warning, and the scheme is that the method comprises the following steps: S01, road bending and straight, lane line identification and self-vehicle front wheel steering angle delta f determination; s02, calculating the distance yll from the left front wheel to the left lane line, the distance yrl from the right front wheel to the left lane line, the distance ylr from the left front wheel to the right lane line and the distance yrr from the right front wheel to the right lane line; s03, selecting a lane departure early warning time calculation model according to whether the road is a curve or not and the condition of a front wheel steering angle delta f; s04, lane departure early warning time TLC is calculated; and S05, lane departure judgment: comparing the lane departure early warning time TLC with a set lane departure time threshold value, and performing lane departure early warning when the lane departure early warning time TLC is smaller than the lane departure time threshold value. Deviation pre-judgment can be carried out by combining the vehicle running speed, the steering condition and the road bending condition, and the accuracy and timeliness of lane departure pre-warning are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of lane departure warning, and in particular to a lane departure warning method, system and electronic equipment. Background Art

[0002] Lane Departure Warning System is one of the advanced driver assistance systems and is a car driving safety assistance system. When the sensor element detects that the vehicle has deviated from the lane, if the driver fails to turn on the turn signal to change lanes due to fatigue or negligence, the system will issue a warning signal to remind the driver to return to the lane. The Lane Departure Warning (LDW) system currently uses cameras as the main sensor, detects and tracks lane lines based on machine vision technology, and determines whether the vehicle is in danger of deviating from the lane based on the driver's characteristics. In case of danger, it provides sound, light and vibration warnings to the driver.

[0003] In the prior art, a Chinese invention patent with a patent application publication number of CN109271959A discloses a vehicle deviation warning method and device, which obtains a collected road image to be detected, performs grayscale processing on the road image to be detected to obtain a corresponding grayscale image, determines a target lane line in the grayscale image, and determines a first distance between the vehicle and the target lane line according to the target lane line. When the first distance meets a first threshold distance condition, a vehicle deviation warning is issued. The second distance between the vehicle and the target entity is determined according to the target entity information. When the second distance meets a second threshold distance condition, a vehicle deviation warning is issued.

[0004] In the above technical scheme, whether to issue a warning is determined only based on whether the distance between the vehicle and the target lane line or target entity reaches a set threshold, without considering the vehicle's driving speed, turning and other conditions. For example, when the vehicle speed is fast, the lane departure warning system does not generate a warning when the distance does not reach the threshold, but when the threshold is reached and a warning is generated, the vehicle is already too close to the lane line or the target, and the best opportunity to control the vehicle is lost. For example, when the vehicle turns, the distance between the vehicle and the lane line or the target object gradually approaches and reaches the threshold. At this time, the lane departure warning system generates a warning, but due to the turning of the vehicle, the distance from the lane line or the target object will gradually increase with the turning, and it will not deviate from the lane or hit the target. It can be seen that with the above technical scheme, the lane departure warning has the problem of inaccuracy and untimeliness in some cases, affecting driving safety and vehicle control. Summary of the invention

[0005] In order to solve the technical problem that the lane departure warning method in the above-mentioned prior art cannot guarantee accurate and timely lane departure warning in a variety of situations, the present invention provides a lane departure warning method, system and electronic equipment, which calculates and predicts departure based on the vehicle driving conditions and the curvature of the road, thereby improving the accuracy and timeliness of lane departure warning.

[0006] In a first aspect, the present invention provides a lane departure warning method to solve the above technical problem, comprising the following steps:

[0007] S01: Road curvature, lane line recognition, vehicle longitudinal speed υ and vehicle front wheel steering angle δ f Sure;

[0008] S02: Calculate the distance y between the left front wheel and the left lane line ll , the distance y between the right front wheel and the left lane rl , the distance y between the left front wheel and the right lane lr and the distance y between the right front wheel and the right lane line rr ;

[0009] S03: Based on whether the road is a curve and the front wheel steering angle δ f Situation selection lane departure warning time calculation model;

[0010] S04: Lane departure warning time T LC calculate;

[0011] S05: Lane departure judgment, lane departure warning time T LC Compared with the set lane departure time threshold, when the lane departure warning time T LC When the lane departure time is less than the lane departure time threshold, a lane departure warning is issued.

[0012] The present invention establishes multiple lane departure warning time calculation models, and can select the corresponding model to calculate the deviation time to the corresponding lane according to the vehicle's speed and steering conditions as well as the curvature of the road, and compare it with the set threshold to determine whether to issue a deviation warning. Compared with the prior art that uses distance to determine whether to issue a warning, the present invention adds consideration of vehicle speed, steering and road curvature for lane deviation judgment, and the judgment is more timely and accurate.

[0013] Furthermore, the distance y between the left front wheel and the left lane is ll The distance y between the left front wheel and the left lane line ll for:

[0014]

[0015] The distance y between the right front wheel and the left lane rl for:

[0016]

[0017] The distance y between the left front wheel and the right lane lr for:

[0018]

[0019] The distance y between the right front wheel and the right lane rr for:

[0020]

[0021] in,

[0022] L=y r +y l

[0023] L is the width of the road line;

[0024] y r It is the distance from the center line of the road to the right lane;

[0025] y l The distance from the center line of the road to the left lane;

[0026] ψ is the vehicle yaw angle;

[0027] a is the vehicle wheelbase.

[0028] Further, in S03, the lane departure warning time calculation model includes a straight road self-vehicle non-turning model, a straight road self-vehicle turning model, a curved road self-vehicle non-turning model and a curved road self-vehicle turning model.

[0029] Furthermore, the lane departure warning time T in the straight road self-vehicle no-turn model is LC The calculation formula is:

[0030]

[0031] Among them, υ is the longitudinal velocity of the vehicle.

[0032] Furthermore, on a straight road, the vehicle has a lane departure warning time T LC The calculation formula is:

[0033]

[0034] Among them, the turning radius of the left wheel of the vehicle is R vl for:

[0035]

[0036] l v is the wheelbase of the vehicle;

[0037] is the yaw angular velocity;

[0038] v is the longitudinal velocity of the vehicle;

[0039] a is the wheelbase;

[0040]

[0041] in,

[0042] ψ L =ψ+δ f

[0043] r2=R vl -r1

[0044] Furthermore, the lane departure warning time T in the curve self-vehicle no-turn model is LC The calculation formula is:

[0045]

[0046] in,

[0047] R r is the radius of the curved road;

[0048] v is the longitudinal velocity of the vehicle.

[0049] Furthermore, the vehicle on the curved road has a lane departure warning time T LC The calculation formula is:

[0050] in,

[0051]

[0052] in,

[0053]

[0054] in,

[0055]

[0056] in,

[0057] R r The road radius of the curve;

[0058] R d Turning radius of the vehicle;

[0059] v is the longitudinal velocity of the vehicle.

[0060] Further, in S05, a plurality of lane departure time thresholds are set to form a plurality of warning levels. LC Different levels of warnings are issued in different intervals.

[0061] The present invention defines multiple warning levels to provide warnings of different risk levels to drivers who have experienced lane deviation, thereby providing drivers with more accurate warning reminders and facilitating drivers to make relevant predictions early.

[0062] In a second aspect, the present invention further provides a lane departure warning system for implementing the lane departure warning method, comprising:

[0063] The image acquisition and analysis module can acquire color images of the detection area, determine the detection area, grayscale the image and perform median filtering to remove noise, binarize the edge image, refine the binarized edge image, and remove noise points to achieve lane line recognition and road curvature judgment;

[0064] The warning module is used to select the lane departure warning time calculation model data and calculate the lane departure warning time T LC And to provide warning, it can be based on the lane departure warning time T LC The corresponding warning level is matched with the size relationship of the set multiple lane departure time thresholds, and a warning prompt is given according to the corresponding warning level.

[0065] In a third aspect, the present invention also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned lane departure warning method.

[0066] It can be seen from the above technical solutions that the present invention has the following advantages:

[0067] The present invention provides a lane departure warning method, system and electronic equipment. By establishing multiple lane departure warning time calculation models, the corresponding model can be selected according to the vehicle's speed and steering conditions and the road curvature to calculate the deviation time to the corresponding lane, and compared with the set threshold to determine whether to issue a deviation warning. Compared with the prior art that uses distance to determine whether to issue a warning, the system adds considerations of vehicle speed, steering and road curvature for lane departure judgment, and the judgment is more timely and accurate; by defining multiple warning levels, warnings of different risk levels are provided to drivers who have already experienced lane deviation, thereby providing drivers with more accurate warning reminders and facilitating drivers to make relevant predictions early. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0069] Figure 1 It is a flowchart of a specific implementation mode 1 of the present invention.

[0070] Figure 2 This is a schematic diagram of the distance calculation principle from the left and right wheels to the corresponding lane lines in the first specific implementation mode of the present invention.

[0071] Figure 3 This is a schematic diagram of calculating the lane departure warning time according to the straight road self-vehicle no-steering model in the first specific implementation mode of the present invention.

[0072] Figure 4 This is a schematic diagram of calculating the lane departure warning time according to the vehicle turning model on a straight road in the first specific implementation mode of the present invention.

[0073] Figure 5 This is a schematic diagram of calculating the lane departure warning time according to the no-steering model of the vehicle on a curved road in the first specific implementation mode of the present invention.

[0074] Figure 6 This is a schematic diagram of calculating the lane departure warning time according to the turning model of the vehicle on a curved road in the first specific implementation mode of the present invention. DETAILED DESCRIPTION

[0075] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in this specific embodiment. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of them. Based on the embodiments in this patent, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this patent. Specific implementation method 1

[0077] like Figure 1 As shown, this specific implementation provides a lane departure warning method, including the following steps:

[0078] S01: Road curvature, lane line recognition, vehicle longitudinal speed υ and vehicle front wheel steering angle δ f Sure;

[0079] S02: Calculate the distance y between the left front wheel and the left lane line ll, the distance y between the right front wheel and the left lane rl , the distance y between the left front wheel and the right lane lr and the distance y between the right front wheel and the right lane line rr ;

[0080] S03: Based on whether the road is a curve and the front wheel steering angle δ f Situation selection lane departure warning time calculation model;

[0081] S04: Lane departure warning time T LC calculate;

[0082] S05: Lane departure judgment, lane departure warning time T LC Compared with the set lane departure time threshold, when the lane departure warning time T LC When the lane departure time is less than the lane departure time threshold, a lane departure warning is issued.

[0083] This specific implementation method establishes multiple lane departure warning time calculation models, and can select the corresponding model to calculate the deviation time from the vehicle to the corresponding lane according to the vehicle's speed and steering conditions as well as the curvature of the road, and compare it with the set threshold to determine whether to issue a deviation warning. Compared with the existing technology that uses distance to determine whether to issue a warning, this technology adds consideration of vehicle speed, steering and road curvature for lane deviation judgment, and the judgment is more timely and accurate.

[0084] like Figure 2 As shown, in S02, the distance y between the left front wheel and the left lane line is ll for:

[0085]

[0086] The distance y between the right front wheel and the left lane rl for:

[0087]

[0088] The distance y between the left front wheel and the right lane lr for:

[0089]

[0090] The distance y between the right front wheel and the right lane rr for:

[0091]

[0092] in,

[0093] L=y r +y l

[0094] L is the width of the road line;

[0095] y r It is the distance from the center line of the road to the right lane;

[0096] y l The distance from the center line of the road to the left lane;

[0097] ψ is the vehicle yaw angle;

[0098] a is the vehicle wheelbase.

[0099] In S03, the lane departure warning time calculation model includes a straight road self-vehicle non-turning model, a straight road self-vehicle turning model, a curved road self-vehicle non-turning model and a curved road self-vehicle turning model.

[0100] like Figure 3 As shown in the figure, the lane departure warning time T in the straight road self-vehicle no-turn model LC The calculation formula is:

[0101]

[0102] Among them, υ is the longitudinal velocity of the vehicle.

[0103] like Figure 4 As shown, the lane departure warning time T for the vehicle in a straight road is LC The calculation formula is:

[0104]

[0105] Among them, the turning radius of the left wheel of the vehicle is R vl for:

[0106]

[0107] l v is the wheelbase of the vehicle;

[0108] is the yaw angular velocity;

[0109] v is the longitudinal velocity of the vehicle;

[0110] a is the wheelbase;

[0111]

[0112] in,

[0113]

[0114] r2=R vl -r1

[0115]

[0116] like Figure 5 As shown in the figure, the lane departure warning time T in the curve vehicle no-turn model LC The calculation formula is:

[0117]

[0118] in,

[0119] R r is the radius of the curved road;

[0120] v is the longitudinal velocity of the vehicle.

[0121] like Figure 6 As shown, the lane departure warning time T of the vehicle in the curve is LC The calculation formula is:

[0122] in,

[0123]

[0124] in,

[0125]

[0126] in,

[0127]

[0128] in,

[0129] R r The road radius of the curve;

[0130] R d Turning radius of the vehicle;

[0131] v is the longitudinal velocity of the vehicle.

[0132] In S05 of this specific implementation, multiple lane departure time thresholds are set to form multiple warning levels. LC Different levels of warnings are issued in different intervals; this specific implementation method defines multiple warning levels to provide warnings of different risk levels to drivers who have already drifted from the lane, thereby providing drivers with more accurate warning reminders and facilitating drivers to make relevant predictions early.

[0133] In this specific construction method, vehicle motion information may refer to the information generated by the vehicle during the driving process. The vehicle motion information may include but is not limited to the front wheel steering angle, lateral speed, longitudinal rate, current vehicle speed and yaw angle, etc. During the actual operation process, the vehicle motion information can be obtained through pre-set steering angle sensors, torque sensors, vehicle speed sensors and other sensors. Specific implementation method 2

[0135] This specific embodiment provides a lane departure warning system for implementing the lane departure warning method of specific embodiment 1, including an image acquisition and analysis module and a warning module; the image acquisition and analysis module can acquire a color image of a detection area, determine the detection area, grayscale the image and perform median filtering to remove noise, use the local maximum difference method to extract the image edge gradient, use the maximum between-class variance method to binarize the edge image, refine the binarized edge image, remove noise, detect multiple straight lines through Hough transform, select lane lines that meet the requirements, and realize lane line recognition and road curvature judgment; the warning module is used to select lane departure warning time calculation model data, calculate the lane departure warning time T LC And to provide warning, it can be based on the lane departure warning time T LC The corresponding warning level is matched with the size relationship of the set multiple lane departure time thresholds, and a warning prompt is given according to the corresponding warning level.

[0136] In this specific implementation, five lane departure time thresholds are set, so that this specific implementation provides four different warning levels, and the warning module performs warnings of different degrees according to different warning levels. Specific implementation method three

[0138] This specific embodiment provides an electronic device, which includes: at least one processor, such as a read-only memory (ROM), a random access memory (RAM), etc.; and a memory connected to the at least one processor in communication, the memory storing a computer program that can be executed by the at least one processor, and the processor can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) or the computer program loaded from the storage unit to the random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device can also be stored. The processor, ROM and RAM are connected to each other through a bus, and an input / output (I / O) interface is also connected to the bus. Multiple components in the electronic device are connected to the I / O interface, including: input units, such as keyboards, mice, etc.; output units, such as various types of displays, speakers, etc.; storage units, such as disks, optical disks, etc.; and communication units, such as network cards, modems, wireless communication transceivers, etc. The communication unit allows the electronic device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunication networks. The processor can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of processors include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor executes the various methods and processes described above, such as the lane departure warning method of the first specific implementation.

[0139] From the above specific implementations, it can be seen that the present invention has the following beneficial effects:

[0140] 1. By establishing multiple lane departure warning time calculation models, the corresponding model can be selected according to the vehicle's speed, steering conditions, and road curvature to calculate the deviation time to the corresponding lane, and compared with the set threshold to determine whether to issue a deviation warning. Compared with the existing technology that uses distance to determine whether to issue a warning, the vehicle speed, steering, and road curvature are added to the judgment of lane departure, and the judgment is more timely and accurate;

[0141] 2. By defining multiple warning levels, different risk levels of warnings are provided to drivers who have drifted from their lanes, thereby providing drivers with more accurate warning reminders and facilitating drivers to make relevant predictions early.

[0142] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A lane departure warning method, characterized in that: The following steps are involved: S01: Road curvature, lane line recognition, vehicle longitudinal speed υ and vehicle front wheel steering angle δ f Sure; S02: Calculate the distance y between the left front wheel and the left lane line u , the distance y between the right front wheel and the left lane rl , the distance y between the left front wheel and the right lane lr and the distance y between the right front wheel and the right lane line rr ; S03: Based on whether the road is a curve and the front wheel steering angle δ f Situation selection lane departure warning time calculation model; S04: Lane departure warning time T LC calculate; S05: Lane departure judgment, lane departure warning time T LC Compared with the set lane departure time threshold, when the lane departure warning time T LC When the lane departure time is less than the lane departure time threshold, a lane departure warning is issued.

2. The lane departure warning method according to claim 1, characterized in that: In S02, The distance y between the left front wheel and the left lane ll for: The distance y between the right front wheel and the left lane rl for: The distance y between the left front wheel and the right lane lr for: The distance y between the right front wheel and the right lane rr for: in, Ly r +y l L is the width of the road line; y r It is the distance from the center line of the road to the right lane; y l The distance from the center line of the road to the left lane; ψ is the vehicle yaw angle; a is the vehicle wheelbase.

3. The lane departure warning method according to claim 2, characterized in that: In S03, the lane departure warning time calculation model includes a straight road self-vehicle non-turning model, a straight road self-vehicle turning model, a curved road self-vehicle non-turning model and a curved road self-vehicle turning model.

4. The lane departure warning method according to claim 3, characterized in that: Lane departure warning time T in the straight road self-vehicle no-turn model LC The calculation formula is: Among them, υ is the longitudinal velocity of the vehicle.

5. The lane departure warning method according to claim 4, characterized in that: Lane departure warning time T for a vehicle turning on a straight road LC The calculation formula is: Among them, the turning radius of the left wheel of the vehicle is R vl for: l v is the wheelbase of the vehicle; ψ is the yaw angular velocity; a is the wheelbase; υ is the longitudinal velocity of the vehicle; in, ψ l =ψ+δ f r2=R vl -r1 6. The lane departure warning method according to claim 5, characterized in that: Lane departure warning time T in the curve vehicle no-turn model LC The calculation formula is: in, R r is the radius of the curved road; v is the longitudinal velocity of the vehicle.

7. The lane departure warning method according to claim 6, characterized in that: Lane departure warning time T when the vehicle is turning on a curved road LC The calculation formula is: in, in, in, in, R r The road radius of the curve; R d Turning radius of the vehicle; v is the longitudinal velocity of the vehicle.

8. The lane departure warning method according to claim 1, characterized in that: In S05, a plurality of lane departure time thresholds are set to form a plurality of warning levels. LC Different levels of warnings are issued in different intervals.

9. A lane departure warning system, characterized in that: The method for implementing the lane departure warning method as claimed in claim 8 comprises: The image acquisition and analysis module can acquire color images of the detection area, determine the detection area, grayscale the image and perform median filtering to remove noise, binarize the edge image, refine the binarized edge image, and remove noise points to achieve lane line recognition and road curvature judgment; The warning module is used to select the lane departure warning time calculation model data and calculate the lane departure warning time T LC And to provide warning, it can be based on the lane departure warning time T LC The corresponding warning level is matched with the size relationship of the set multiple lane departure time thresholds, and a warning prompt is given according to the corresponding warning level.

10. An electronic device, characterized in that: The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the lane departure warning method described in any one of claims 1-8.