Research on detection of lane based on machine vision  

基于机器视觉的车道标志线检测研究(英文)

作　　者：李旭[1] 张为公[1] 卞晓东[1] 

机构地区：[1]东南大学仪器科学与工程系,南京210096

出　　处：《Journal of Southeast University(English Edition)》2004年第2期176-180,共5页东南大学学报（英文版）

摘　　要：To prevent a vehicle from departing the lane in assistant or automatic steering, real-time vision-based detection of lane is studied. The system architecture, detecting principle and lane model are described. Then the detecting algorithm of the lane image is discussed in detail. In this algorithm, several proper sub-windows in one image are first selected as the processing regions. To every sub-window, by means of such steps as appropriate pre-processing, edge detection and Hough transform, etc., the lane description features are extracted. Experimental results reveal that this detection method is of good real-time, high recognition reliability and strong robustness, etc., which can provide the decision-making foundation for the following automatic or assistant steering to some extent.针对车辆辅助驾驶或自主驾驶中的车道保持问题 ,研究了基于视觉的车道标志线实时检测方法 .介绍了系统组成、工作原理和车道模型 ,并着重讨论了车道图像的检测算法 .其主要思想是在图像上选取几个合适的处理区域 ,通过对每个处理区域进行适当的预处理、边缘检测和霍夫变换等过程来提取车道描述特征 .试验结果表明 ,该方法具有实时性好、识别可靠性高等特点 ,在一定程度上能为后续的辅助驾驶或自主驾驶提供决策依据 .

关 键 词：Charge coupled devices Computer vision Decision making Edge detection Hough transforms 

分 类 号：U46[机械工程—车辆工程]