WO2019200937A1 - 一种有效判别车辆压线及预先提示系统 - Google Patents

一种有效判别车辆压线及预先提示系统 Download PDF

Info

Publication number
WO2019200937A1
WO2019200937A1 PCT/CN2018/119028 CN2018119028W WO2019200937A1 WO 2019200937 A1 WO2019200937 A1 WO 2019200937A1 CN 2018119028 W CN2018119028 W CN 2018119028W WO 2019200937 A1 WO2019200937 A1 WO 2019200937A1
Authority
WO
WIPO (PCT)
Prior art keywords
distance
vehicle
lane line
image
line
Prior art date
Application number
PCT/CN2018/119028
Other languages
English (en)
French (fr)
Inventor
陈志峰
郭恩特
范振嘉
裴晨皓
陈雅楠
黄立勤
潘林
Original Assignee
福州大学
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 福州大学 filed Critical 福州大学
Priority to US17/047,743 priority Critical patent/US20210114611A1/en
Publication of WO2019200937A1 publication Critical patent/WO2019200937A1/zh

Links

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
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/10—Path keeping
    • B60W30/12—Lane keeping
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
    • 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
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • 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
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera

Definitions

  • the invention relates to an effective pre-cue system for determining a vehicle pressure line.
  • the camera is installed in advance and the safety distance of the camera and the lane line is calibrated.
  • an effective discrimination vehicle pressing line and a pre-cue system including an image acquisition module, a lane line extraction module, a distance calculation module and an early warning determination module, wherein: the image acquisition The module collects image information through an optical camera and inputs the image information into a lane line extraction module;
  • the lane line extraction module further includes an image preprocessing module and a line extraction module;
  • the image pre-processing module averages the smoothed image after grading the image, extracts the edge in the image by using the Canny operator, and removes the small edge to obtain the pre-processed image information by using an open operation;
  • the line extraction module extracts a straight line within a limited angle according to the preprocessed image information, and uses the original image color feature to determine whether the lane line is a solid yellow line, and judges the virtual solid line through the gray line periodic transformation of the lane line. Obtain lane line information and input to the distance calculation module;
  • the distance calculation module performs processing on the lane line information to calculate a lateral distance between the calculated vehicle and the left and right lanes, and inputs the signal to the early warning determination module;
  • the early warning judging module calculates the lateral distance of the left and right lanes according to the distance calculation module to calculate whether the lateral distance of the left and right lanes exceeds a preset distance warning value, and if so, sends an early warning signal to the driver.
  • the distance calculation module processes the lane line information to calculate the lateral distance between the calculated vehicle and the left and right lanes:
  • Step S1 installing the optical camera at the windshield of the vehicle, the optical axis is parallel to the ground, the horizontal height is h, the distance from the front head a, the distance from the left side of the vehicle is b, and the focal length is f;
  • Step S2 The lane line module processes the image information collected by the optical camera, and the left lane line and the right lane line on the road surface are projected on the plane as the left lane line and the right lane line in the image, and intersect in the image coordinate system.
  • B ( m 3 , m 2 ) falling on the blanking line, the image center line and the hidden line are compared with the point A ( m 1 , m 2 ), and the left lane line and the right lane line intersect the image coordinate system x-axis.
  • ⁇ 1 , ⁇ 2
  • Step S3 Calculate the distance between the optical camera and the left and right lane lines:
  • Step S4 Calculate the distance between the vehicle and the left and right lane lines:
  • Step S5 Calculate the mean value of the distance as the distance value by taking three consecutive frames of images. If dl ⁇ min_ warn _ dist or dr ⁇ min_ warn _ dist , min_ warn _ dist is the preset value of the distance warning, the vehicle pressure line warning The system issues a distance warning reminder.
  • the invention has the following beneficial effects:
  • the vehicle pressure line pre-prompting system of the invention can calculate the lateral distance of the vehicle from the lane line in real time and effectively; and has the advantages of simple design, easy development, high reliability, no need to modify the vehicle, less dependence on the outside world, etc.; The crew brings a convenient and safe driving experience.
  • FIG. 1 is a side view showing the installation of a vehicle pressure line warning camera and a processing system according to the present invention
  • FIG. 2 is a top plan view showing the installation of the vehicle pressure line warning camera and the processing system of the present invention.
  • FIG. 3 is a schematic view of a lane line taken by an optical camera in the present invention.
  • Figure 4 is a diagram showing the vehicle traveling at any position on the road in the present invention.
  • FIG. 5 is a schematic diagram of the present invention
  • the present invention provides an effective method for discriminating a vehicle pressure line and a pre-cue system, including an image acquisition module, a lane line extraction module, a distance calculation module, and an early warning determination module, wherein the image acquisition module passes an optical camera. Acquiring image information and inputting image information into a lane line extraction module;
  • the lane line extraction module processes the image information to extract lane line information and inputs the extracted lane line information into the distance calculation module;
  • the lane line extraction module further includes an image preprocessing module and a line extraction module;
  • the image preprocessing module averages the smoothed image after grayscaled the image, extracts the edge in the image by using the Canny operator, and removes the small edge by using the opening operation;
  • the line extraction module adopts a Hough transform to extract a straight line within a limited angle, and uses the original image color feature to determine whether the lane line is a solid yellow line, and judges the virtual solid line by the gray line periodic transformation of the lane line;
  • the distance calculation module performs processing on the lane line information to calculate a lateral distance between the calculated vehicle and the left and right lanes, and inputs the signal to the early warning determination module;
  • the early warning judging module calculates the lateral distance of the left and right lanes according to the distance calculation module to calculate whether the lateral distance of the left and right lanes exceeds a preset distance warning value, and if so, sends an early warning signal to the driver.
  • the distance calculation module performs processing on the lane line information to calculate a lateral distance between the calculated vehicle and the left and right lanes:
  • Step S1 installing the optical camera at the windshield of the vehicle, the optical axis is parallel to the ground, the horizontal height is h, the distance from the front head a, the distance from the left side of the vehicle is b, and the focal length is f;
  • Step S2 The lane line module processes the image information collected by the optical camera, and the left lane line and the right lane line on the road surface are projected on the plane as the left lane line and the right lane line in the image, and intersect in the image coordinate system.
  • B ( m 3 , m 2 ) falling on the blanking line, the image center line and the hidden line are compared with the point A ( m 1 , m 2 ), and the left lane line and the right lane line intersect the image coordinate system x-axis.
  • ⁇ 1 , ⁇ 2
  • Step S3 Calculate the distance between the optical camera and the left and right lane lines:
  • Step S4 Calculate the distance between the vehicle and the left and right lane lines:
  • Step S5 Calculate the mean value of the distance as the distance value by taking three consecutive frames of images. If dl ⁇ min_ warn _ dist or dr ⁇ min_ warn _ dist , min_ warn_dist is the preset value of the distance warning, the vehicle pressure line warning system issues Distance warning reminder.
  • the camera 30 is mounted behind the windshield of the vehicle 40, the camera is horizontally forward, the optical axis 31 of the camera is parallel to the ground, and the installation height is h , the distance from the head a , the distance The left side of the vehicle is b , the focal length of the calibrated camera is f ; the image is pre-processed before the lane line is extracted, the RGB image is converted to grayscale, the 3 ⁇ 3 mean filtering smoothes the interference, and the Canny operator is used to extract the image.
  • Edge use the open operation to process the image to remove small edges, use Hough transform to extract the straight line as the lane line at a limited angle, extract the color feature at the RGB original image lane line position to determine whether the lane line is yellow or white, according to the lane line grayscale The value brightness periodically changes to determine whether the lane line is a dashed line or a solid line.
  • the vehicle 40 travels in the left lane 34' and the right lane 35'.
  • the lane lines 34 and 35 are detected in the image as the left lane 34' on the road surface.
  • the projection of the right lane 35' in the image is the point A ( m 1 , m 2 )
  • the intersection of the lane lines 34, 35 is B ( m 3 , m 2 ) on the blanking line 33, and the lane line 34
  • the angles of 35 and 35 respectively intersect the image x-axis are ⁇ 1 , ⁇ 2 .
  • B Since the optical axis 31 of the camera 30 is not level with the ground due to bumps or the like of the vehicle, and the intersection of the lane lines 34 and 35 in FIG. 3 is B ( m 3 , m 2 ) does not fall on the blanking line 33, B is not calculated.
  • the average of the distances is calculated as the value of the distance by taking three consecutive frames of images.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)

Abstract

一种有效判别车辆压线及预先提示系统，包括图像采集模块，车道线提取模块，距离计算模块和预警判断模块；图像采集模块通过光学摄像头采集前向图像，经过车道线提取模块处理后提取图像中车道线，距离计算模块计算光学摄像头与左右车道的距离，通过摄像头在车辆中的位置以及车辆的尺寸，计算车辆离左右车道的距离，从而由预警判断模块判断是否预警提醒驾驶员。其有益效果为用单目摄像头采集图像并实时计算车辆与左右车道距离，并对驾驶员做出预警，具有设计简单，开发容易，可靠性高，不需要对车辆进行改装，对外界依赖少等优点。

Description

一种有效判别车辆压线及预先提示系统 技术领域
本发明涉及一种有效判别车辆压线预先提示系统。
 背景技术
随着科学技术的发展，汽车在普通家庭中普及，汽车带来便利交通的同时，日益增长的交通事故对人们的生命安全造成威胁和对财产造成了损失。人们在驾驶车辆过程中并非出于意愿无意识地做出车辆压线行为。车辆压线行驶占用了侧边车道，导致同向后面车辆不能超车或者对向车辆不易避让，从而造成交通事故的发生。或者压线时被交通违规抓拍系统抓拍，被交管部门以违章行为处罚，造成驾驶员经济上的损失并做扣分警告。
 技术问题
目前利用机器视觉的车辆压线预警方法中，多为事先安装好摄像头并对摄像头和车道线的安全距离进行标定。
 技术解决方案
有鉴于此，本发明的目的在于提供一种有效判别车辆压线预先提示系统。
为实现上述目的，本发明采用如下技术方案：一种有效判别车辆压线及预先提示系统,包括图像采集模块，车道线提取模块，距离计算模块和预警判断模块，其特征在于：所述图像采集模块通过光学摄像头采集图像信息并将图像信息输入车道线提取模块；
所述车道线提取模块还包括图像预处理模块和直线提取模块；
所述的图像预处理模块对图像做灰度化之后均值滤波平滑图像，采用Canny算子提取图像中的边缘，用开操作去除小边缘得到预处理的图像信息；
所述的直线提取模块根据预处理的图像信息，采用Hough变换在限定的角度内提取直线，并利用原始图像颜色特征判断车道线是否为黄实线，通过车道线灰度周期性变换判断虚实线得到车道线信息，并输入到距离计算模块；
所述距离计算模块对车道线信息做处理计算得到计算车辆和左右车道的横向距离并输入到预警判断模块；
所述预警判断模块，根据距离计算模块对车道线信息做处理计算得到左右车道的横向距离判断是否超过预设的距离预警值，若超过则对驾驶员发出预警信号。
进一步的，所述距离计算模块对车道线信息做处理计算得到计算车辆和左右车道的横向距离具体为：
步骤S1:将光学摄像头安装在车辆的挡风玻璃处，光轴与地面平行，水平高度为h,距离车头a，距离车辆左侧距离为b，焦距为f;
步骤S2:车道线模块对光学摄像头采集的图像信息进行处理，可以得到路面上的左车道线和右车道线在平面投影为图像中的左车道线和右车道线，在图像坐标系中相交于 B( m 3, m 2)，落于消隐线上，图像中线与消隐线相较于点 A( m 1, m 2)，左车道线和右车道线与图像坐标系x轴相交角度分别为 θ 1, θ 2；
步骤S3:计算光学摄像机与左右车道线的距离：
[根据细则20.5改正17.01.2019]　
光学摄像机与左车道线的距离为：
Figure WO-DOC-FIGURE-1
，
[根据细则20.5改正17.01.2019]　
光学摄像机与右车道线的距离为：
Figure WO-DOC-FIGURE-2
；
步骤S4：计算车辆与左右车道线的距离：
车辆与左车道线横向最近距离：
[根据细则20.5改正17.01.2019]　
Figure WO-DOC-FIGURE-3
，
车辆与左车道线横向最远距离：
[根据细则20.5改正17.01.2019]　
Figure WO-DOC-FIGURE-4
，
车辆与右车道线横向最近距离：
[根据细则20.5改正17.01.2019]　
Figure WO-DOC-FIGURE-5
，
车辆与右车道线横向最远距离：
[根据细则20.5改正17.01.2019]　
Figure WO-DOC-FIGURE-6
，
其中 w为车辆宽度， l为车辆长度；
步骤S5： 取连续3帧图像计算得到距离的均值作为距离的取值，若 dl＜min_ warn_ dist或者 dr＜min_ warn_ dist, min_ warn_ dist为距离预警的预设值，车辆压线预警系统发出距离预警提醒。
有益效果
本发明与现有技术相比具有以下有益效果：
本发明的车辆压线预先提示系统，实时且有效地计算车辆距离车道线横向距离；具有设计简单，开发容易，可靠性高，不需要对车辆进行改装，对外界依赖少等优点；能够给驾驶员带来便捷和安全的驾驶体验。
 附图说明
图1是本发明车辆压线预警摄像头和处理系统安装侧视示意图
图2是本发明车辆压线预警摄像头和处理系统安装俯视示意图
图3是本发明中光学摄像头采集得到车道线示意图
图4是本发明中车辆行驶在道路任意位置图
图5是本发明原理图
 本发明的实施方式
下面结合附图及实施例对本发明做进一步说明。
请参照图5，本发明提供一种有效判别车辆压线及预先提示系统,包括图像采集模块，车道线提取模块，距离计算模块和预警判断模块，其特征在于：所述图像采集模块通过光学摄像头采集图像信息并将图像信息输入车道线提取模块；
所述车道线提取模块对图像信息做处理提取车道线信息并将提取的车道线信息输入距离计算模块；
所述车道线提取模块还包括图像预处理模块和直线提取模块；
所述的图像预处理模块对图像做灰度化之后均值滤波平滑图像，采用Canny算子提取图像中的边缘，用开操作去除小边缘；
所述的直线提取模块采用Hough变换在限定的角度内提取直线，并利用原始图像颜色特征判断车道线是否为黄实线，通过车道线灰度周期性变换判断虚实线；
所述距离计算模块对车道线信息做处理计算得到计算车辆和左右车道的横向距离并输入到预警判断模块；
所述预警判断模块，根据距离计算模块对车道线信息做处理计算得到左右车道的横向距离判断是否超过预设的距离预警值，若超过则对驾驶员发出预警信号。
在本发明一实施例中，进一步的，所述距离计算模块对车道线信息做处理计算得到计算车辆和左右车道的横向距离具体为：
步骤S1:将光学摄像头安装在车辆的挡风玻璃处，光轴与地面平行，水平高度为h,距离车头a，距离车辆左侧距离为b，焦距为f;
步骤S2:车道线模块对光学摄像头采集的图像信息进行处理，可以得到路面上的左车道线和右车道线在平面投影为图像中的左车道线和右车道线，在图像坐标系中相交于 B( m 3, m 2)，落于消隐线上，图像中线与消隐线相较于点 A( m 1, m 2)，左车道线和右车道线与图像坐标系x轴相交角度分别为 θ 1, θ 2；
步骤S3:计算光学摄像机与左右车道线的距离：
[根据细则20.5改正17.01.2019]　
光学摄像机与左车道线的距离为：
Figure WO-DOC-FIGURE-7
，
[根据细则20.5改正17.01.2019]　
光学摄像机与右车道线的距离为：
Figure WO-DOC-FIGURE-8
；
步骤S4：计算车辆与左右车道线的距离：
车辆与左车道线横向最近距离：
[根据细则20.5改正17.01.2019]　
Figure WO-DOC-FIGURE-9
，
车辆与左车道线横向最远距离：
[根据细则20.5改正17.01.2019]　
Figure WO-DOC-FIGURE-10
，
车辆与右车道线横向最近距离：
[根据细则20.5改正17.01.2019]　
Figure WO-DOC-FIGURE-11
，
车辆与右车道线横向最远距离：
[根据细则20.5改正17.01.2019]　
Figure WO-DOC-FIGURE-12
，
其中 w为车辆宽度， l为车辆长度；
步骤S5： 取连续3帧图像计算得到距离的均值作为距离的取值，若 dl＜min_ warn_ dist或者 dr＜min_ warn_ dist, min_ warn_dist为距离预警的预设值，车辆压线预警系统发出距离预警提醒。
为了让一般技术人员更好的理解本发明的技术方案，以下结合附图对本发明进行详细介绍。
参考图1、图2，在本发明一实施例中，摄像头30安装在车辆40内挡风玻璃后面，摄像头水平向前，摄像头光轴31与地面平行，安装高度为 h，距离车头 a，距离车辆左侧为 b，经过标定摄像头焦距为 f；车道线提取之前先对图像进行预处理，将RGB图像转为灰度图，3×3均值滤波平滑去除干扰，使用Canny算子提取图像中的边缘，运用开操作处理图像去除小边缘，采用Hough变换在限定的角度上提取直线作为车道线，在RGB原图像车道线位置提取颜色特征判断车道线为黄线还是白线，根据车道线灰度值亮度周期性变换判断车道线为虚线还是实线。
参考图3、图4所示，车辆40在左车道34’和右车道35’中行驶，摄像头采集图像并提取车道线后在图像中检测得到车道线34和35分别为路面上左车道34’和右车道35’在图像中的投影。图3中消隐线33和图像中线32的交点为点 A( m 1, m 2)，车道线34、35交点为 B( m 3, m 2)落在消隐线33上，车道线34、35分别与图像x轴相交角度为 θ 1, θ 2。由于车辆颠簸等原因造成摄像头30的光轴31与地面不水平，从而造成图3中车道线34、35交点为 B( m 3, m 2)没有落在消隐线33上，则不计算B点落在消隐线±5像素以外时车辆40与左右车道34’、35’的距离。取连续3帧图像计算得到距离的均值作为距离的取值。
参考图4，若 dl＜min_ warn_ dist或者 dr＜min_ warn_ dist时对驾驶员发出警报，其中取min_warn_dist=20cm。
若车辆压白虚线时间time过长， time＞max_ time，其中取max_time=5s，则发出警报通知驾驶员。
以上所述仅为本发明的较佳实施例，凡依本发明申请专利范围所做的均等变化与修饰，皆应属本发明的涵盖范围。

Claims (2)

  1. 一种有效判别车辆压线及预先提示系统,包括图像采集模块，车道线提取模块，距离计算模块和预警判断模块，其特征在于：所述图像采集模块通过光学摄像头采集图像信息并将图像信息输入车道线提取模块；
    所述车道线提取模块还包括图像预处理模块和直线提取模块；
    所述的图像预处理模块对图像做灰度化之后均值滤波平滑图像，采用Canny算子提取图像中的边缘，用开操作去除小边缘得到预处理的图像信息；
    所述的直线提取模块根据预处理的图像信息，采用Hough变换在限定的角度内提取直线，得到车道线信息；
    所述距离计算模块对车道线信息做处理计算得到计算车辆和左右车道的横向距离并输入到预警判断模块；
    所述预警判断模块，根据距离计算模块对车道线信息做处理计算得到左右车道的横向距离判断是否超过预设的距离预警值，若超过则对驾驶员发出预警信号。
  2. [根据细则20.5改正17.01.2019]　
    根据权利要求1所述的一种有效判别车辆压线及预先提示系统，其特征在于:所述距离计算模块对车道线信息做处理计算得到计算车辆和左右车道的横向距离具体为：
    步骤S1:将光学摄像头安装在车辆的挡风玻璃处，光轴与地面平行，水平高度为h,距离车头a，距离车辆左侧距离为b，焦距为f;
    步骤S2:车道线模块对光学摄像头采集的图像信息进行处理，可以得到路面上的左车道线和右车道线在平面投影为图像中的左车道线和右车道线，在图像坐标系中相交于 B( m 3, m 2)，落于消隐线上，图像中线与消隐线相较于点 A( m 1, m 2)，左车道线和右车道线与图像坐标系x轴相交角度分别为 θ 1, θ 2；
    步骤S3:计算光学摄像机与左右车道线的距离：
    光学摄像机与左车道线的距离为：
    Figure WO-DOC-FIGURE-7
    ，
    光学摄像机与右车道线的距离为：
    Figure WO-DOC-FIGURE-8
    ；
    步骤S4：计算车辆与左右车道线的距离：
    车辆与左车道线横向最近距离：
    Figure WO-DOC-FIGURE-9
    ，
    车辆与左车道线横向最远距离：
    Figure WO-DOC-FIGURE-10
    ，
    车辆与右车道线横向最近距离：
    Figure WO-DOC-FIGURE-11
    ，
    车辆与右车道线横向最远距离：
    Figure WO-DOC-FIGURE-12
    ，
    其中 w为车辆宽度， l为车辆长度；
    步骤S5： 取连续3帧图像计算得到距离的均值作为距离的取值，若 dl＜min_ warn_ dist或者 dr＜min_ warn_ dist, min_ warn_ dist为距离预警的预设值，车辆压线预警系统发出距离预警提醒。
PCT/CN2018/119028 2018-04-18 2019-01-17 一种有效判别车辆压线及预先提示系统 WO2019200937A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/047,743 US20210114611A1 (en) 2018-04-18 2019-01-17 System for performing effective identification of vehicle line pressing and giving early prompt

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810345892.7A CN108776767B (zh) 2018-04-18 2018-04-18 一种有效判别车辆压线及预先提示系统
CN201810345892.7 2019-01-17

Publications (1)

Publication Number Publication Date
WO2019200937A1 true WO2019200937A1 (zh) 2019-10-24

Family

ID=64033788

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/119028 WO2019200937A1 (zh) 2018-04-18 2019-01-17 一种有效判别车辆压线及预先提示系统

Country Status (3)

Country Link
US (1) US20210114611A1 (zh)
CN (1) CN108776767B (zh)
WO (1) WO2019200937A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108776767B (zh) * 2018-04-18 2019-12-17 福州大学 一种有效判别车辆压线及预先提示系统
CN112257539A (zh) * 2020-10-16 2021-01-22 广州大学 车辆与车道线的位置关系检测方法、系统和存储介质
CN113511221B (zh) * 2021-05-20 2022-10-11 重庆长安汽车股份有限公司 一种监控横向控制能力的方法、系统、车辆及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102303609A (zh) * 2011-06-16 2012-01-04 广东铁将军防盗设备有限公司 车道偏离预警系统及方法
CN106355903A (zh) * 2016-09-13 2017-01-25 枣庄学院 基于视频分析的多车道车流量检测方法
CN106981202A (zh) * 2017-05-22 2017-07-25 中原智慧城市设计研究院有限公司 一种基于车道模型的车辆来回变道检测方法
CN108776767A (zh) * 2018-04-18 2018-11-09 福州大学 一种有效判别车辆压线及预先提示系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002319091A (ja) * 2001-04-20 2002-10-31 Fuji Heavy Ind Ltd 後続車両認識装置
JP4992990B2 (ja) * 2010-02-24 2012-08-08 株式会社デンソー 区画線検出装置
CN102288121B (zh) * 2011-05-12 2012-11-07 电子科技大学 一种基于单目视觉的车道偏离距离测量及预警方法
CN102722705B (zh) * 2012-06-12 2014-04-30 武汉大学 一种基于ransac算法的多车道线检测方法
CN104517111B (zh) * 2013-09-27 2018-09-07 比亚迪股份有限公司 车道线检测方法、系统、车道偏离预警方法及系统
CN103738243B (zh) * 2013-10-29 2015-12-30 惠州华阳通用电子有限公司 一种车道偏离预警方法
KR102371587B1 (ko) * 2015-05-22 2022-03-07 현대자동차주식회사 횡단보도 인식 결과를 이용한 안내 정보 제공 장치 및 방법
CN107491722A (zh) * 2017-06-16 2017-12-19 南京栎树交通互联科技有限公司 一种基于车道线图像处理实现驾驶员疲劳判别的方法
EP3503025B1 (en) * 2017-12-19 2021-11-10 Accenture Global Solutions Limited Utilizing artificial intelligence with captured images to detect agricultural failure

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102303609A (zh) * 2011-06-16 2012-01-04 广东铁将军防盗设备有限公司 车道偏离预警系统及方法
CN106355903A (zh) * 2016-09-13 2017-01-25 枣庄学院 基于视频分析的多车道车流量检测方法
CN106981202A (zh) * 2017-05-22 2017-07-25 中原智慧城市设计研究院有限公司 一种基于车道模型的车辆来回变道检测方法
CN108776767A (zh) * 2018-04-18 2018-11-09 福州大学 一种有效判别车辆压线及预先提示系统

Also Published As

Publication number Publication date
US20210114611A1 (en) 2021-04-22
CN108776767A (zh) 2018-11-09
CN108776767B (zh) 2019-12-17

Similar Documents

Publication Publication Date Title
WO2019200938A1 (zh) 一种车辆压线提前预警系统
CN108189838B (zh) 一种融合型自适应巡航弯道控制方法及装置
US9904856B2 (en) Method and apparatus for detecting target object in blind area of vehicle
CN103287372B (zh) 一种基于图像处理的汽车防撞安全保护方法
KR101517181B1 (ko) 차선 이탈 경보 시스템 및 방법
KR102227843B1 (ko) 차선 이탈 경보 시스템의 동작방법
US9591274B2 (en) Three-dimensional object detection device, and three-dimensional object detection method
KR101478258B1 (ko) 차선 인식 방법 및 그 시스템
US20150015384A1 (en) Object Detection Device
WO2019200937A1 (zh) 一种有效判别车辆压线及预先提示系统
CN105047019B (zh) 一种客运车辆防止后车超车后突然变道判断方法及装置
CN102306293A (zh) 基于面部图像识别技术的评判实际道路驾驶员考试的方法
CN107316486A (zh) 基于双摄像头的无人驾驶汽车视觉识别系统
JP2007234019A (ja) 車両画像領域特定装置およびその方法
Katyal et al. Safe driving by detecting lane discipline and driver drowsiness
CN109522847A (zh) 一种基于深度图的轨道和道路障碍物检测方法
US20120212615A1 (en) Far-infrared pedestrian detection device
KR20110001427A (ko) 관심영역 추출에 의한 차선 고속검출 방법
KR20110001425A (ko) 에이치에스아이 색정보의 통계적 모델을 이용한 차선 분류방법
JP4989249B2 (ja) 目検知装置、居眠り検知装置及び目検知装置の方法
CN108021849B (zh) 一种行人预警方法及装置
KR101169338B1 (ko) 차선 인식 장치 및 차선 인식 방법
CN103021179A (zh) 基于实时监控视频中的安全带检测方法
CN105059184A (zh) 客运车辆弯道侧翻早期预警与主动防控装置及其判断方法
JP2009301495A (ja) 画像処理装置及び画像処理方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18915647

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18915647

Country of ref document: EP

Kind code of ref document: A1