CN108082192B - Lane departure early warning method and device - Google Patents

Lane departure early warning method and device Download PDF

Info

Publication number
CN108082192B
CN108082192B CN201611048891.3A CN201611048891A CN108082192B CN 108082192 B CN108082192 B CN 108082192B CN 201611048891 A CN201611048891 A CN 201611048891A CN 108082192 B CN108082192 B CN 108082192B
Authority
CN
China
Prior art keywords
video
lane
theoretical
vehicle
warning
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201611048891.3A
Other languages
Chinese (zh)
Other versions
CN108082192A (en
Inventor
丁赞
徐波
杨青
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BYD Co Ltd
Original Assignee
BYD Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by BYD Co Ltd filed Critical BYD Co Ltd
Priority to CN201611048891.3A priority Critical patent/CN108082192B/en
Publication of CN108082192A publication Critical patent/CN108082192A/en
Application granted granted Critical
Publication of CN108082192B publication Critical patent/CN108082192B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
    • B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
    • B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
    • B60R2300/804—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for lane monitoring
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B60W2050/143—Alarm means

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Automation & Control Theory (AREA)
  • Multimedia (AREA)
  • Transportation (AREA)
  • Traffic Control Systems (AREA)

Abstract

The disclosure relates to a lane departure early warning method and a lane departure early warning device. The lane departure early warning method is applied to a vehicle provided with a video acquisition device, and comprises the following steps: calculating a theoretical alarm threshold according to the resolution width of the video, the width from the edge of the vehicle to the optical center of the video acquisition device and the actual width of the lower boundary in the video; identifying a lane line distance from a lane line in the video to the edge of the vehicle; and when the distance of the lane line is greater than or equal to the theoretical alarm threshold, performing lane departure early warning. By calculating the theoretical alarm threshold, when the distance from the lane line in the video to the lane line at the edge of the vehicle is greater than or equal to the theoretical alarm threshold, lane departure early warning is carried out, the purpose that the vehicle has the tendency of deviating from the lane is achieved, early warning is sent out before the vehicle presses the lane line or is about to press the lane line is achieved, and the problems that the conventional cross-lane time early warning algorithm easily causes missed warning, late warning or false warning are solved.

Description

Lane departure early warning method and device
Technical Field
The disclosure relates to the technical field of driving safety assistance, in particular to a lane departure early warning method and a lane departure early warning device.
Background
A Lane Departure Warning (LDW) system is one of Advanced Driver Assistance Systems (ADAS) and is an automobile driving safety Assistance system. When the sensing element detects that the vehicle deviates from the lane, if the driver does not turn off the direction light signal of the lane change due to fatigue or negligence, the system can send out a warning signal to remind the driver to return to the lane. The Lane Departure Warning (LDW) system uses a camera as a main sensor at present, detects and tracks lane lines based on a machine vision technology, judges whether a vehicle has a danger of deviating from a lane or not by combining the characteristics of a driver, and provides sound, light and vibration warning for the driver in case of the danger.
Patent document No. 201310520373.7 describes a lane departure warning method, which includes a video acquisition device installation and parameter calibration step, an image preprocessing step, an edge detection step, a lane line recognition step, and a lane departure warning time determination step, where the lane departure warning time determination step includes: calculating the yaw distance of the vehicle: calculating the yaw distance of the vehicle according to the external parameters, the internal parameters and the coordinate transformation relation calibrated by the video acquisition device; estimating the pre-pressing lane time; a lane departure judging step: and setting a lane departure time threshold, and performing lane departure early warning when the pre-pressing lane time is less than the lane departure time threshold.
However, since the normal lane change time is about 3s, 5s is taken as a large lane crossing time. As shown in fig. 1, in lane change, the accumulated distribution frequency of the lane crossing time is more than 50% in more than 5s, so that the system does not perform early warning in the time corresponding to the accumulated distribution frequency, thereby causing alarm leakage or alarm delay. Similarly, in lane keeping, the lane crossing time has more than 10% of accumulated distribution frequency within a small threshold value below 5s, and when the lane crossing time early warning algorithm is used, the system easily gives a false alarm within the time corresponding to the accumulated distribution frequency.
Disclosure of Invention
The invention aims to provide a lane departure early warning method and a lane departure early warning device, which are used for solving the problem that the conventional lane crossing time early warning algorithm is easy to cause missed warning, late warning or false alarm.
In order to achieve the above object, the present disclosure provides a lane departure warning method applied to a vehicle equipped with a video capture device, the lane departure warning method including:
calculating a theoretical alarm threshold according to the resolution width of the video, the width from the edge of the vehicle to the optical center of the video acquisition device and the actual width of the lower boundary in the video;
identifying a lane line distance from a lane line in the video to the edge of the vehicle;
and when the distance of the lane line is greater than or equal to the theoretical alarm threshold, performing lane departure early warning.
Optionally, the theoretical alarm threshold is calculated according to the following formula:
Figure BDA0001159284850000021
wherein x is a theoretical alarm threshold, w is a resolution width of the video, f is a width from the edge of the vehicle to the optical center of the video acquisition device, and y is an actual width of a lower boundary in the video.
Optionally, the actual width of the lower boundary in the video is calculated according to the following formula:
Figure BDA0001159284850000022
wherein h is the height of the video acquisition device from the ground, α is half of the horizontal angle of view, β is half of the vertical angle of view, and theta is the downward deflection angle of the video acquisition device.
Optionally, before the lane departure warning, the method further includes: acquiring the lateral acceleration of the vehicle;
when the lane line distance is greater than or equal to the theoretical alarm threshold, performing lane departure early warning, including:
correcting the theoretical alarm threshold according to the magnitude of the transverse acceleration;
and when the distance of the lane line is greater than or equal to the corrected theoretical alarm threshold, performing lane departure early warning.
Optionally, the acquiring the lateral acceleration of the vehicle includes:
identifying the positions of the lane lines in different frames in the video;
acquiring the transverse offset of the vehicle according to the positions of the lane lines in different frames in the video;
and calculating the lateral acceleration according to the lateral offset.
Optionally, the modifying the theoretical alarm threshold according to the magnitude of the lateral acceleration includes:
when the transverse acceleration is smaller than a first preset value, increasing the theoretical alarm threshold value by a first theoretical value;
and when the transverse acceleration is larger than a second preset value, reducing the theoretical alarm threshold value by a second theoretical value, wherein the second preset value is larger than the first preset value.
The present disclosure also provides a lane departure warning device, which is applied to a vehicle equipped with a video acquisition device, the lane departure warning device includes:
the calculation module is used for calculating a theoretical alarm threshold according to the resolution width of the video, the width from the edge of the vehicle to the optical center of the video acquisition device and the actual width of the lower boundary in the video;
the identification module is used for identifying the distance from the lane line in the video to the lane line of the vehicle edge; and
and the early warning module is used for carrying out lane departure early warning when the distance between the lane lines is greater than or equal to the theoretical warning threshold value.
Optionally, the theoretical alarm threshold is calculated according to the following formula:
Figure BDA0001159284850000031
wherein x is a theoretical alarm threshold, w is a resolution width of the video, f is a width from the edge of the vehicle to the optical center of the video acquisition device, and y is an actual width of a lower boundary in the video.
Optionally, the actual width of the lower boundary in the video is calculated according to the following formula:
Figure BDA0001159284850000041
wherein h is the height of the video acquisition device from the ground, α is half of the horizontal angle of view, β is half of the vertical angle of view, and theta is the downward deflection angle of the video acquisition device.
Optionally, the method further comprises: an acquisition module for acquiring a lateral acceleration of the vehicle;
the early warning module includes:
the correction submodule is used for correcting the theoretical alarm threshold according to the magnitude of the transverse acceleration; and
and the early warning submodule is used for carrying out lane departure early warning when the lane line distance is greater than or equal to the corrected theoretical warning threshold.
Optionally, the obtaining module includes:
the identification submodule is used for identifying the positions of the lane lines in different frames in the video;
the obtaining submodule is used for obtaining the transverse offset of the vehicle according to the positions of the lane lines in different frames in the video;
and the calculation submodule is used for calculating the transverse acceleration according to the transverse offset.
Optionally, when the lateral acceleration is smaller than a first preset value, the correction submodule is configured to increase the theoretical alarm threshold by a first theoretical value; and when the transverse acceleration is larger than a second preset value, the correction submodule is used for reducing the theoretical alarm threshold value by a second theoretical value, and the second preset value is larger than the first preset value.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
firstly, by calculating a theoretical alarm threshold, when the distance from a lane line in a video to the lane line at the edge of a vehicle is greater than or equal to the theoretical alarm threshold, lane departure early warning is carried out, so that the vehicle has the tendency of deviating from a lane, and early warning is sent out before the vehicle presses the lane line or is about to press the lane line, and the problems of missing warning, late warning or false warning caused by the conventional cross-lane time early warning algorithm are solved;
the transverse behavior characteristics of the driver are researched, the transverse acceleration and the transverse position of the vehicle are analyzed in lane keeping and lane changing operations, the relative position of the current vehicle and a lane line can be accurately judged, the movement trend of the vehicle can be judged at the same time, early warning is timely carried out when the vehicle deviates from the lane or has the tendency of deviating from the lane, and meanwhile, false warning is avoided when the vehicle is close to the lane but does not deviate.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
fig. 1 is a graph of the frequency distribution of lane-crossing times in lane keeping and lane changing operations for the same driver.
Fig. 2 is a flowchart illustrating a lane departure warning method according to an exemplary embodiment.
Fig. 3 is another flowchart illustrating a lane departure warning method according to an exemplary embodiment.
Fig. 4 is a flowchart illustrating acquisition of a lateral acceleration of a vehicle in steps included in a lane departure warning method according to an exemplary embodiment.
FIG. 5 is a schematic diagram illustrating theoretical alarm thresholds in accordance with an exemplary embodiment.
Fig. 6 is a block diagram illustrating a lane departure warning apparatus according to an exemplary embodiment.
Fig. 7 is another block diagram illustrating a lane departure warning apparatus according to an exemplary embodiment.
Fig. 8 is a block diagram illustrating an early warning module of a lane departure early warning apparatus according to an exemplary embodiment.
Fig. 9 is a block diagram illustrating an acquisition module of a lane departure warning apparatus according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Fig. 2 is a flowchart illustrating a lane departure warning method according to an exemplary embodiment, which is applied to a vehicle equipped with a video capture device, as shown in fig. 1, and includes the following steps.
In step S11, a theoretical alarm threshold is calculated based on the resolution width of the video, the width of the vehicle edge to the optical center of the video capture device, and the actual width of the lower boundary in the video.
In step S12, the lane line distance from the lane line in the video to the edge of the vehicle is identified.
In step S13, when the lane line distance is greater than or equal to the theoretical warning threshold, a lane departure warning is performed.
First, in step S11, the theoretical alarm threshold is calculated according to the following formula:
Figure BDA0001159284850000061
wherein x is a theoretical alarm threshold, w is a resolution width of the video, f is a width from the edge of the vehicle to the optical center of the video acquisition device, and y is an actual width of a lower boundary in the video. It should be noted that x and w are pixels, and f and y are actual length units (such as meters).
The coordinate axes established in the video may be from left edge of the video as an origin, from left to right (i.e., the video width direction) as the X-axis direction, and from bottom to top (i.e., the video height direction) as the Y-axis direction. In the above formula of the theoretical alarm threshold value,
Figure BDA0001159284850000062
may be a theoretical alarm threshold from the left edge of the vehicle to the lane line,
Figure BDA0001159284850000063
may be a theoretical alarm threshold from the right edge of the vehicle to the lane line.
Further, the actual width of the lower boundary in the video is calculated according to the following formula:
Figure BDA0001159284850000064
wherein h is the height of the video acquisition device from the ground, α is half of the horizontal angle of view, β is half of the vertical angle of view, and theta is the downward deflection angle of the video acquisition device.
When the theoretical alarm threshold is obtained through calculation, step S12 is executed to identify the lane line distance from the lane line in the video to the edge of the vehicle. The unit of the lane line distance in the video is also a pixel. The lane lines and the vehicle edges in the video can be identified through the video acquisition device, and then the lane line distance is obtained through image processing. And executing step S13 after the lane line distance is acquired, and when the lane line distance is greater than or equal to the theoretical alarm threshold, performing lane departure early warning.
According to the method and the device, the theoretical alarm threshold value is calculated, when the distance from the lane line in the video to the lane line at the edge of the vehicle is larger than or equal to the theoretical alarm threshold value, lane departure early warning is carried out, the purpose that the vehicle has the tendency of deviating from the lane is achieved, early warning is sent out before the vehicle presses the lane line or is about to press the lane line is achieved, and the problems that the existing cross-lane time early warning algorithm easily causes alarm missing, late warning or false alarm are solved.
Fig. 3 is another flowchart illustrating a lane departure warning method according to an exemplary embodiment, which includes the following steps, as shown in fig. 3.
In step S21, a theoretical alarm threshold is calculated based on the resolution width of the video, the width of the vehicle edge to the optical center of the video capture device, and the actual width of the lower boundary in the video.
In step S22, the lane line distance from the lane line in the video to the edge of the vehicle is identified.
In step S23, the lateral acceleration of the vehicle is acquired.
In step S24, the theoretical alarm threshold is corrected according to the magnitude of the lateral acceleration.
In step S25, when the lane line distance is greater than or equal to the corrected theoretical warning threshold, a lane departure warning is performed.
Reference may be made to fig. 4 for acquiring the lateral acceleration of the vehicle, and fig. 4 is a flowchart illustrating the acquisition of the lateral acceleration of the vehicle in steps included in a lane departure warning method according to an exemplary embodiment. As shown in fig. 4, the acquiring of the lateral acceleration of the vehicle includes the following steps.
In step S231, the positions of the lane lines in different frames in the video are identified.
In step S232, a lateral offset of the vehicle is obtained according to positions of the lane lines in different frames in the video, and a unit of the lateral offset is a pixel.
In step S233, the lateral acceleration is calculated in units of pixels/S based on the lateral shift amount2。
The method for calculating the lateral offset and the lateral acceleration of the vehicle can be summarized as follows: road information in front of the vehicle is photographed by a camera installed in front of the vehicle, and the position of the lane line in the image is identified. When the vehicle transverse offset is different, the positions of lane lines in the image are also different, and the lane departure warning system can obtain the corresponding relation between the positions of the lane lines and the vehicle transverse offset by calibrating the camera, so that the vehicle transverse offset is calculated by identifying the positions of the lane lines. After the lane departure warning system identifies the lane line, the vehicle transverse offset is calculated in each frame of image processing, and the transverse addition of the vehicle is calculated through the change of the transverse offset between adjacent frames.
Next, explanation will be given by way of example:
firstly, assuming that the result of the left lane line identification position is x;
then, x0 represents the position of the lane line of the current frame, and x1, x2, x3, x4, x5, x6, x7, and x8 represent the positions of the lane lines of the first 1, 2, 3, 4, 5, 6, 7, and 8 frames of the current frame, respectively;
then, the value x01 of x0-x1 represents the offset of the current frame from the previous frame, and the offsets are x12, x23, x34, x45, x56, x67 and x 68;
then, filtering processing is carried out for eliminating jitter, and the maximum value and the minimum value are removed from the eight adjacent interframe offset values;
finally, the average of the remaining 6 offsets is used as the lateral acceleration.
And after the lateral acceleration is obtained, executing step S24, and correcting the theoretical alarm threshold according to the magnitude of the lateral acceleration. Wherein, correcting the theoretical alarm threshold value comprises: when the transverse acceleration is smaller than a first preset value, increasing the theoretical alarm threshold value by a first theoretical value; and when the transverse acceleration is larger than a second preset value, reducing the theoretical alarm threshold value by a second theoretical value, wherein the second preset value is larger than the first preset value.
Optionally, the first preset value may be [3, 7], and the first theoretical value may be [15, 25 ]; the second preset value may be [13, 17], and the second theoretical value may be [25, 35 ]. Preferably, the first preset value is 5, and the first theoretical value is 20; the second preset value 15 is the second theoretical value of 30.
FIG. 5 is a schematic diagram illustrating theoretical alarm thresholds in accordance with an exemplary embodiment. As shown in fig. 5, when the lateral acceleration is less than 5, it is described that the lateral relative position of the vehicle and the lane line changes slowly, the included angle between the center line of the vehicle and the lane line is small, and the vehicle runs approximately in parallel, at this time, the theoretical alarm threshold needs to be properly amplified, the early warning time needs to be slowed down, the theoretical alarm threshold is increased by 20 according to the empirical value, and the corrected theoretical alarm threshold is T2 in fig. 5. When the lateral acceleration is larger than 5 and smaller than 15, the vehicle is normally deviated from the lane, and early warning is carried out according to a theoretical warning threshold (namely T3 in figure 5). When the lateral acceleration is larger than 15, the vehicle rapidly deviates from the lane, early warning is needed at the moment, the vehicle is prevented from deviating from the lane during early warning, therefore, the theoretical warning threshold needs to be reduced, the threshold reduction 30 is set according to an empirical value, and the corrected theoretical warning threshold is T1 in fig. 5.
According to the method, the transverse behavior characteristics of the driver are researched, the transverse acceleration and the transverse position of the vehicle are analyzed in lane keeping and lane changing operations, the relative position of the current vehicle and a lane line can be accurately judged, the movement trend of the vehicle can be judged at the same time, early warning is timely carried out when the vehicle deviates from the lane or has the tendency of deviating from the lane, and meanwhile, false warning is avoided when the vehicle is close to the lane but does not deviate.
Fig. 6 is a block diagram illustrating a lane departure warning apparatus according to an exemplary embodiment. Referring to fig. 6, the lane departure warning apparatus 400 includes a calculation module 410, a recognition module 420, and a warning module 430.
The calculation module 410 is used for calculating a theoretical alarm threshold according to the resolution width of the video, the width from the edge of the vehicle to the optical center of the video acquisition device, and the actual width of the lower boundary in the video;
the identification module 420 is used for identifying the lane line distance from the lane line to the edge of the vehicle in the video; and
the early warning module 430 is configured to perform lane departure early warning when the lane line distance is greater than or equal to the theoretical warning threshold.
Optionally, the theoretical alarm threshold is calculated according to the following formula:
Figure BDA0001159284850000101
wherein x is a theoretical alarm threshold, w is a resolution width of the video, f is a width from the edge of the vehicle to the optical center of the video acquisition device, and y is an actual width of a lower boundary in the video.
Optionally, the actual width of the lower boundary in the video is calculated according to the following formula:
Figure BDA0001159284850000102
wherein h is the height of the video acquisition device from the ground, α is half of the horizontal angle of view, β is half of the vertical angle of view, and theta is the downward deflection angle of the video acquisition device.
Fig. 7 is another block diagram illustrating a lane departure warning apparatus according to an exemplary embodiment. As shown in fig. 7, the lane departure warning apparatus 400 includes an acquisition module 440, in addition to a calculation module 410, a recognition module 420 and a warning module 430. The obtaining module 440 is configured to obtain a lateral acceleration of the vehicle.
Fig. 8 is a block diagram illustrating an early warning module of a lane departure early warning apparatus according to an exemplary embodiment. As shown in fig. 8, the early warning module 430 includes:
the correction submodule 4301 is used for correcting the theoretical alarm threshold according to the magnitude of the transverse acceleration; and
and the early warning submodule 4302 is used for performing lane departure early warning when the lane line distance is greater than or equal to the corrected theoretical warning threshold.
Optionally, when the lateral acceleration is smaller than a first preset value, the correction submodule is configured to increase the theoretical alarm threshold by a first theoretical value; and when the transverse acceleration is larger than a second preset value, the correction submodule is used for reducing the theoretical alarm threshold value by a second theoretical value, and the second preset value is larger than the first preset value.
Fig. 9 is a block diagram illustrating an acquisition module of a lane departure warning apparatus according to an exemplary embodiment. As shown in fig. 9, the obtaining module 440 includes:
the identification sub-module 4401 is configured to identify positions of the lane lines in different frames in the video;
the obtaining sub-module 4402 is configured to obtain a lateral offset of the vehicle according to positions of the lane lines in different frames in the video;
a calculation sub-module 4403, configured to calculate the lateral acceleration according to the lateral offset.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
firstly, by calculating a theoretical alarm threshold, when the distance from a lane line in a video to the lane line at the edge of a vehicle is greater than or equal to the theoretical alarm threshold, lane departure early warning is carried out, so that the vehicle has the tendency of deviating from a lane, and early warning is sent out before the vehicle presses the lane line or is about to press the lane line, and the problems of missing warning, late warning or false warning caused by the conventional cross-lane time early warning algorithm are solved;
the transverse behavior characteristics of the driver are researched, the transverse acceleration and the transverse position of the vehicle are analyzed in lane keeping and lane changing operations, the relative position of the current vehicle and a lane line can be accurately judged, the movement trend of the vehicle can be judged at the same time, early warning is timely carried out when the vehicle deviates from the lane or has the tendency of deviating from the lane, and meanwhile, false warning is avoided when the vehicle is close to the lane but does not deviate.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, various possible combinations will not be separately described in this disclosure.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.

Claims (10)

1. A lane departure early warning method is applied to a vehicle provided with a video acquisition device, and is characterized by comprising the following steps:
calculating a theoretical alarm threshold according to the resolution width of the video, the width from the edge of the vehicle to the optical center of the video acquisition device and the actual width of the lower boundary in the video;
identifying a lane line distance from a lane line in the video to the edge of the vehicle;
when the distance of the lane line is greater than or equal to the theoretical alarm threshold, performing lane departure early warning;
the method further comprises the following steps: acquiring the lateral acceleration of the vehicle;
when the lane line distance is greater than or equal to the theoretical alarm threshold, performing lane departure early warning, including:
correcting the theoretical alarm threshold according to the magnitude of the transverse acceleration;
and when the distance of the lane line is greater than or equal to the corrected theoretical alarm threshold, performing lane departure early warning.
2. The lane departure warning method according to claim 1, wherein the theoretical warning threshold is calculated according to the following formula:
Figure FDA0002404839930000011
wherein x is a theoretical alarm threshold, w is a resolution width of the video, f is a width from the edge of the vehicle to the optical center of the video acquisition device, and y is an actual width of a lower boundary in the video.
3. The lane departure warning method according to claim 2, wherein the actual width of the lower boundary in the video is calculated according to the following formula:
Figure FDA0002404839930000012
wherein h is the height of the video acquisition device from the ground, α is half of the horizontal angle of view, β is half of the vertical angle of view, and theta is the downward deflection angle of the video acquisition device.
4. The lane departure warning method according to claim 1, wherein the acquiring of the lateral acceleration of the vehicle comprises:
identifying the positions of the lane lines in different frames in the video;
acquiring the transverse offset of the vehicle according to the positions of the lane lines in different frames in the video;
and calculating the lateral acceleration according to the lateral offset.
5. The lane departure warning method according to claim 1, wherein the correcting the theoretical warning threshold according to the magnitude of the lateral acceleration comprises:
when the transverse acceleration is smaller than a first preset value, increasing the theoretical alarm threshold value by a first theoretical value;
and when the transverse acceleration is larger than a second preset value, reducing the theoretical alarm threshold value by a second theoretical value, wherein the second preset value is larger than the first preset value.
6. The lane departure early warning device is applied to a vehicle provided with a video acquisition device, and is characterized by comprising:
the calculation module is used for calculating a theoretical alarm threshold according to the resolution width of the video, the width from the edge of the vehicle to the optical center of the video acquisition device and the actual width of the lower boundary in the video;
the identification module is used for identifying the distance from the lane line in the video to the lane line of the vehicle edge; and
the early warning module is used for carrying out lane departure early warning when the distance between the lane lines is greater than or equal to the theoretical warning threshold;
the device further comprises: an acquisition module for acquiring a lateral acceleration of the vehicle;
the early warning module includes:
the correction submodule is used for correcting the theoretical alarm threshold according to the magnitude of the transverse acceleration; and
and the early warning submodule is used for carrying out lane departure early warning when the lane line distance is greater than or equal to the corrected theoretical warning threshold.
7. The lane departure warning apparatus according to claim 6, wherein the theoretical warning threshold is calculated according to the following formula:
Figure FDA0002404839930000031
wherein x is a theoretical alarm threshold, w is a resolution width of the video, f is a width from the edge of the vehicle to the optical center of the video acquisition device, and y is an actual width of a lower boundary in the video.
8. The lane departure warning apparatus according to claim 7, wherein the actual width of the lower boundary in the video is calculated according to the following formula:
Figure FDA0002404839930000032
wherein h is the height of the video acquisition device from the ground, α is half of the horizontal angle of view, β is half of the vertical angle of view, and theta is the downward deflection angle of the video acquisition device.
9. The lane departure warning apparatus according to claim 6, wherein the acquisition module comprises:
the identification submodule is used for identifying the positions of the lane lines in different frames in the video;
the obtaining submodule is used for obtaining the transverse offset of the vehicle according to the positions of the lane lines in different frames in the video;
and the calculation submodule is used for calculating the transverse acceleration according to the transverse offset.
10. The lane departure warning apparatus according to claim 6, wherein the modification sub-module is configured to increase the theoretical alarm threshold by a first theoretical value when the lateral acceleration is less than a first preset value; and when the transverse acceleration is larger than a second preset value, the correction submodule is used for reducing the theoretical alarm threshold value by a second theoretical value, and the second preset value is larger than the first preset value.
CN201611048891.3A 2016-11-22 2016-11-22 Lane departure early warning method and device Active CN108082192B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611048891.3A CN108082192B (en) 2016-11-22 2016-11-22 Lane departure early warning method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611048891.3A CN108082192B (en) 2016-11-22 2016-11-22 Lane departure early warning method and device

Publications (2)

Publication Number Publication Date
CN108082192A CN108082192A (en) 2018-05-29
CN108082192B true CN108082192B (en) 2020-06-19

Family

ID=62170280

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611048891.3A Active CN108082192B (en) 2016-11-22 2016-11-22 Lane departure early warning method and device

Country Status (1)

Country Link
CN (1) CN108082192B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113538923A (en) 2020-04-20 2021-10-22 深圳富泰宏精密工业有限公司 Warning method for vehicle lane change and vehicle-mounted device
CN112130152B (en) * 2020-09-16 2023-09-05 东风汽车集团有限公司 Method for correcting transverse distance between automobile and target object
CN114475641B (en) * 2022-04-15 2022-06-28 天津所托瑞安汽车科技有限公司 Lane departure warning method, lane departure warning device, lane departure warning control device, and storage medium
CN115249270B (en) * 2022-09-22 2022-12-30 广州市德赛西威智慧交通技术有限公司 Automatic re-labeling method and system for radar-vision all-in-one machine

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105620359A (en) * 2016-02-25 2016-06-01 上海斐讯数据通信技术有限公司 Mobile terminal-based lane departure forewarning method and system

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100394668B1 (en) * 2001-06-12 2003-08-14 현대자동차주식회사 A method for warning getting out of a traffic lane of vehicle
US7561032B2 (en) * 2005-09-26 2009-07-14 Gm Global Technology Operations, Inc. Selectable lane-departure warning system and method
US7388475B2 (en) * 2006-01-19 2008-06-17 Gm Global Technology Operations, Inc. Lane departure warning and avoidance system with warning modification criteria
CN103738243B (en) * 2013-10-29 2015-12-30 惠州华阳通用电子有限公司 A kind of lane departure warning method
CN105599765A (en) * 2015-12-11 2016-05-25 上海卓易科技股份有限公司 Lane departure judging and early warning method
CN105835891A (en) * 2016-01-26 2016-08-10 乐卡汽车智能科技（北京）有限公司 System and method for preventing lane departure

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105620359A (en) * 2016-02-25 2016-06-01 上海斐讯数据通信技术有限公司 Mobile terminal-based lane departure forewarning method and system

Also Published As

Publication number Publication date
CN108082192A (en) 2018-05-29

Similar Documents

Publication Publication Date Title
US9704404B2 (en) Lane detection apparatus and operating method for the same
CN108082192B (en) Lane departure early warning method and device
US8670590B2 (en) Image processing device
JP5375958B2 (en) Image processing apparatus and image processing method
US11205284B2 (en) Vehicle-mounted camera pose estimation method, apparatus, and system, and electronic device
US8611609B2 (en) Lane line estimating apparatus
JP6233345B2 (en) Road surface gradient detector
EP3153356B1 (en) Display device for vehicle and display method for vehicle
JP6278222B2 (en) Display device for vehicle and display method for vehicle
JP6950170B2 (en) Information processing device, imaging device, device control system, information processing method, and program
EP2770478B1 (en) Image processing unit, imaging device, and vehicle control system and program
JP5950196B2 (en) Imaging apparatus, and image analysis apparatus and moving apparatus using the same
JP2014167677A (en) Inter-vehicle distance calculation device and motion controlling method for the same
JP2015219773A (en) Object detection device, driving support device, object detection method, and object detection program
US10810712B2 (en) Apparatus for monitoring surroundings of vehicle and method of calibrating the same
JP5616974B2 (en) In-vehicle camera displacement detection device
WO2013191078A1 (en) Object detection device for area around vehicle
JP2019067150A (en) Surrounding monitoring device and surrounding monitoring method
JP2010020710A (en) Device for detecting road side fixed object
JP2012252501A (en) Traveling path recognition device and traveling path recognition program
JP2018136739A (en) Calibration device
JP2011033594A (en) Distance calculation device for vehicle
CN112784671A (en) Obstacle detection device and obstacle detection method
JP2010006270A (en) Vehicle behavior detecting device
JP6032141B2 (en) Travel road marking detection device and travel road marking detection method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant