融合道路图像关键信息的车距视觉测量方法

计算机工程与应用 ›› 2015, Vol. 51 ›› Issue (23): 6-10.

融合道路图像关键信息的车距视觉测量方法

杨炜1，巩建强2，魏朗1

1.长安大学汽车学院，西安 710064
2.交通运输部公路科学研究院，北京 100088

出版日期:2015-12-01 发布日期:2015-12-14

Vehicle distance vision measurement method fusion with road image key information

YANG Wei1, GONG Jianqiang2, WEI Lang1

1.School of Automobile, Chang’an University, Xi’an 710064, China
2.Research?Institute?of?Highway,?Ministry?of?Transport, Beijing 100088, China

Online:2015-12-01 Published:2015-12-14

摘要/Abstract

摘要： 提出了一种融合道路图像关键信息的纵向车距视觉测量方法，在道路成像平面内建立了基于车道平面约束的视觉测距模型，运用边界约束Hough变换采集两侧道路标识线的斜率、聚点坐标以及车道宽度信息，自动求解视觉传感器的高度及俯仰角等测距参数。选取双通道Gabor滤波器提取目标车辆的5尺度8方向特征样本，联合AdaBoost分类器与级联Cascade筛选有效特征，快速精确提取目标特征点的坐标参数。实验结果表明，视觉测量值与实测值的绝对误差平均值为1.37 m，相对误差平均值为2.38%，测距平均耗时32 ms，与传统测距方法相比较，测量精度和实时性均得到了提高，适合于汽车主动防撞安全系统中应用。

关键词: 汽车工程, 视觉测距, 道路关键信息, 边界约束Hough变换, Gabor滤波器, AdaBoost分类器

Abstract: A vehicle distance vision measurement method based on road image key information is proposed, a visual measurement model based on lane plane constraint is established in road image, the slope and vanish point coordinate of road marking line and lane width information collection is finished by boundary constraints Hough transform, automatic calculated height and pitching angle measurement parameters of visual sensor. It selects dual channel Gabor filter to extract 5 scales and 8 direction characteristics samples of the target vehicle, fusion AdaBoost classifier with Cascade screening characteristics effectively, to obtain the coordinates of target feature point parameters accurately. The experimental results show that pitching angle and installation height of visual sensor changes on a small scale have a little influence on measurement results, but the target feature points pixel changes greatly influence measurement results, visual measured values and the measured values of the average absolute error is 1.37 m, the average relative error is 2.38%, average time-consuming 32 ms, compared with traditional method, both of measurement accuracy and real-time are improved, suitable for application in automobile active anti-collision safety system.

Key words: vehicle engineering, vision measurement, lane image information, boundary constraints Hough transform, Gabor filter, AdaBoost classifier

杨炜1，巩建强2，魏朗1. 融合道路图像关键信息的车距视觉测量方法[J]. 计算机工程与应用, 2015, 51(23): 6-10.

YANG Wei1, GONG Jianqiang2, WEI Lang1. Vehicle distance vision measurement method fusion with road image key information[J]. Computer Engineering and Applications, 2015, 51(23): 6-10.

[1]	曹万鹏，罗云彬，史辉. 抗外点干扰的鲁棒AdaBoost分类器构建方法[J]. 计算机工程与应用, 2018, 54(7): 132-137.
[2]	张波彬1，甘宗鑫2，陈伟1. 基于合作模式的目标跟踪方法[J]. 计算机工程与应用, 2018, 54(19): 101-106.
[3]	姜文，刘立康. 基于联合两种特征的手写体维文字符识别[J]. 计算机工程与应用, 2017, 53(5): 192-196.
[4]	陈熙1，2，张戈1. 基于非高斯二维Gabor滤波器的生物特征提取算法[J]. 计算机工程与应用, 2017, 53(18): 170-175.
[5]	依玉峰1，2，田宏1，刘彤宇2. 直方图重建图像细节增强算法[J]. 计算机工程与应用, 2017, 53(13): 29-33.
[6]	薛俊韬，徐少朋，王烨. 基于计算机视觉的智能小车路径规划[J]. 计算机工程与应用, 2016, 52(7): 236-241.
[7]	夏军，裴东，孙瑜欣. 基于局部Gabor自适应三值模式的人脸识别[J]. 计算机工程与应用, 2016, 52(18): 203-207.
[8]	王明景1，吉峰2，白瑞林1. 经编机布匹瑕疵的在线视觉检测[J]. 计算机工程与应用, 2015, 51(9): 185-190.
[9]	王润民. 基于微粒群算法的视网膜血管自动提取方法[J]. 计算机工程与应用, 2015, 51(2): 177-180.
[10]	邱娟，谢昊，张传林. 基于优化Gabor滤波器和GMRF的笔迹特征提取方法[J]. 计算机工程与应用, 2015, 51(17): 145-150.
[11]	景军锋，张赞赞，李鹏飞. 基于Log-Gabor滤波器的织物起球客观评级方法[J]. 计算机工程与应用, 2014, 50(8): 247-250.
[12]	王威1，2，张连峰3，王平2，李元垒3. 一种基于整体区域特征的地面飞机识别方法[J]. 计算机工程与应用, 2014, 50(12): 155-158.
[13]	耿佳佳1，康晓东1，王昊1，2，于文勇1. 基于Gabor滤波器和聚类的图像配准算法[J]. 计算机工程与应用, 2014, 50(10): 193-196.
[14]	仇逊超，王阿川，曹军. 木材彩色图像缺陷分割——基于Gabor滤波的改进C-V彩色模型[J]. 计算机工程与应用, 2013, 49(18): 153-158.
[15]	陈宁，曾勇. 一种新型自适应指纹图像增强算法[J]. 计算机工程与应用, 2011, 47(30): 180-182.