一种基于消隐点的单目视觉车辆测距方法  

A vehicle distance measurement method with monocular vision based on vanishing point

作　　者：关闯 魏朗[1] 乔洁[1] 杨炜[1] Guan Chuang;Wei Lang;Qiao Jie;Yang Wei(School of Automobile,Chang＇an University,Xi＇an 710064,China)

机构地区：[1]长安大学汽车学院

出　　处：《电子测量技术》2018年第11期83-87,共5页Electronic Measurement Technology

基　　金：国家自然科学基金(51278062);陕西自然科学青年基金(2017JQ6045);中央高校基本科研业务费专项(310822161013)项目资助

摘　　要：为了克服传统单目视觉测距中时变的摄像机外参数对测量结果的影响,利用道路车道标识线平行约束条件,提出了一种基于车道线消隐点的单目视觉自适应车辆测距方法。首先利用概率Hough变换提取结构化道路车道线方程参数,确定车道线消隐点图像像素坐标;然后根据传统的静态单帧测距模型推导出了基于车道线消隐点的单目视觉车辆距离测量方法,并组织了相应的前方车辆测距试验,试验结果表明：该方法能够有效测量前方车辆距离,测距误差不超过10%,测量结果的精确性满足安全行车碰撞预警要求。In order to overcome the time-varying influence of camera parameters on the measurement results in the traditional monocular vision ranging,an adaptive method of monocular vision vehicle distance measurement based on vanishing point of road lines was proposed by using the parallel constraints of road lanes.Firstly,the Progressive Probabilistic Hough Transform is used to extract the parameters of the lane lines equation of the structured roadway to determine the pixel coordinate of the vanishing point. Then,deduced the monocular vision vehicle distance measurement method based on the vanishing point based on the traditional static single frame ranging model,and organized the corresponding front vehicle distance test.The test results show that the method can effectively measure the distance of the vehicle in front and the measurement error didn’t exceed 10%,and the accuracy of the measurement results meets the requirements of early warning of traffic collision.

关 键 词：单目视觉 概率Hough变换 消隐点 车辆距离测量 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] U491[自动化与计算机技术—计算机科学与技术]