[1]于兵,张为公,龚宗洋.基于机器视觉的车道偏离报警系统[J].东南大学学报(自然科学版),2009,39(5):928-932.[doi:10.3969/j.issn.1001-0505.2009.05.012]
 Yu Bing,Zhang Weigong,Gong Zongyang.Lane departure warning system based on machine vision[J].Journal of Southeast University (Natural Science Edition),2009,39(5):928-932.[doi:10.3969/j.issn.1001-0505.2009.05.012]
点击复制

基于机器视觉的车道偏离报警系统()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
39
期数:
2009年第5期
页码:
928-932
栏目:
自动化
出版日期:
2009-09-20

文章信息/Info

Title:
Lane departure warning system based on machine vision
作者:
于兵 张为公 龚宗洋
东南大学仪器科学与工程学院, 南京 210096
Author(s):
Yu Bing Zhang Weigong Gong Zongyang
School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
关键词:
车道偏离报警 方向可调滤波器 卡尔曼跟踪 偏离决策
Keywords:
lane departure warning steerable filter Kalman tracking lane departure decision
分类号:
TP242.62
DOI:
10.3969/j.issn.1001-0505.2009.05.012
摘要:
为了提高基于机器视觉车道偏离报警系统的可靠性和实用性,对基于视觉的车道偏离报警系统各个环节的优化做了研究.介绍了基于视觉的车道偏离报警系统的构成和工作原理,提出了各个环节的实现方法.通过选择直线车道数学模型和限定车道提取的感兴趣区域(ROI)以简化系统复杂度和提高检测精度.首先使用方向可调滤波器进行图像预处理,然后使用Kalman预测器和距离判别法得到车道线有效点集,最后采用抗干扰能力强的Hough变换得出车道线参数.研究并采纳了一种无需对摄像头标定的车道偏离决策方法,通过综合道路图像中2条车道线的斜率值来判断车辆偏离车道的程度.实验表明,该系统具有良好的车道识别能力以及准确的偏离决策能力,能够满足高速公路环境车道偏离报警要求.
Abstract:
Several studies of optimization were carried out to improve the practicability and stability of lane departure warning system(LDWs)based on machine vision.The system configuration and work flow of LDWs are introduced and the realization of each segment is described. The linear lane model and region of interest(ROI)are adopted to simplify the system structure and improve the system accuracy firstly.Then, by means of preprocess of image based on steerable filter,tracking method based on Kalman prediction and gathering lane edge points solution through distance discrimination way, the lane is extracted robustly. Finally, the decision method about lane departure decision without calibrating the camera is studied. Experiments show that the developed system exhibits good performances in recognition reliability, and warning decision,which can satisfy the requirements of lane departure warning system in the structured highway environment.

参考文献/References:

[1] 宁乐然.高速公路交通事故的主要原因[J].交通与运输,2004(2):38-39.
  Ning Leran.Causes of traffic accidents on expressway[J].Traffic & Transportation,2004(2):38-39.(in Chinese)
[2] 王荣本,余天洪,郭烈,等.基于机器视觉的车道偏离警告系统研究综述[J].汽车工程,2005,27(4):463-466.
  Wang Rongben,Yu Tianhong,Guo Lie,et al.A survey on the research of vision-based lane departure warning system[J].Automotive Engineering,2005,27(4):463-466.(in Chinese)
[3] 董因平.高速汽车车道偏离预警系统研究[J].长春理工大学学报,2004,27(1):48-50.
  Dong Yinping.A review of lane departure warning highway system[J].Journal of Changchun Institute of Optics and Fine Mechanics,2004,27(1):48-50.(in Chinese)
[4] Lee Joon Wong.A machine vision system for lane departure detection[J].Computer Vision and Image Understanding,2002,86(1):52-78.
[5] Kwon Woong,Lee Jae-Won,Shin Dongmok,et al.Experiments on decision making strategies for a lane departure warning system[C] //International Conference on Robotics & Automation.Detroit,USA,1999:2596-2601.
[6] Risack R,Möhler N,Enkelmann W.A video-based lane keeping assistant[C] //IEEE Intelligent Vehicles Symposium.Dearborn,USA,2000:356-361.
[7] Jung Cláudio Rosito,Kelber Christian Roberto.A lane departure warning system using lateral offset with uncalibrated camera[C] //IEEE Conference on Intelligent Transportation Systems.Vienna,Austria,2005:102-107.
[8] An Xiangjing,Wu Mo,He Hangen.A novel approach to provide lane departure warning using only one forward-looking camera[C] //International Symposium on Collaborative Technologies and Systems.Las Vegas,USA,2006:356-362.
[9] 李旭,张为公.基于视觉的车道偏离报警系统的研究[J].仪器仪表学报,2008,29(7):1554-1558.
  Li Xu,Zhang Weigong.Research on lane departure warning system based on machine vision [J]. Chinese Journal of Scientific Instrument,2008,29(7):1554-1558.(in Chinese)
[10] Freeman W,Adelsom E H.The design and use of steerable filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(9):891-906.
[11] 张荣,王勇,杨榕.TM图像中道路目标识别方法的研究[J].遥感学报,2005,9(2):220-224.
  Zhang Rong,Wang Yong,Yang Rong.Researches on road recognition in landsat TM images[J].Journal of Remote Sensing,2005,9(2):220-224.(in Chinese)
[12] 邓自立.最优估计理论及其应用——建模、滤波、信息融合估计[M].哈尔滨:哈尔滨工业大学出版社,2005:108-115.

备注/Memo

备注/Memo:
作者简介: 于兵(1979—),男,博士生; 张为公(联系人),男,博士,教授,博士生导师,zhangwg@seu.edu.cn.
基金项目: 江苏省交通科学研究计划资助项目(06C04)、苏州市科技发展计划资助项目(SG0723).
引文格式: 于兵,张为公,龚宗洋.基于机器视觉的车道偏离报警系统[J].东南大学学报:自然科学版,2009,39(5):928-932. [doi:10.3969/j.issn.1001-0505.2009.05.012]
更新日期/Last Update: 2009-09-20