基于像素点的快速结构化道路元素检测  

Rapid structural road elements detection based on pixels

作　　者：毕建权[1,2] 陆耿[1] 江永亨[1] 王京春[1] 

机构地区：[1]清华大学自动化系,北京100084 [2]洛阳电子装备试验中心,河南洛阳471003

出　　处：《计算机工程与科学》2013年第5期100-105,共6页Computer Engineering & Science

基　　金：群缩微车协同驾驶;交通仿真和评估研究项目(20111081071)

摘　　要：道路元素检测是基于简单视觉的缩微智能车自主驾驶系统的研究基础。针对基于缩微智能车处理能力不足及对检测控制算法实时性的要求,提出了基于像素点数据块快速识别和跟踪算法。为降低光照对检测识别的影响,采用修正OTSU阈值二值化方法。实验检测结果显示,在光照、遮挡、污染等干扰情况下,缩微智能车对车道线、路面标志、斑马线等道路元素能够实现快速提取识别,并分析了速度对道路元素检测率的影响,而车道保持和超车换道实验验证了整个算法的高效性和稳定性。The basis of the autonomous driving system of the micro-vehicles based on simple visual is the road element detection. Based on the lack of the micro-vehicles processing capacity and the real-time requirements of the detection and control algorithms, the paper proposed a new feature extraction and tracking algorithm based on the pixel data blocks. We use the fixed OTSU threshold image binarization to reduce the impact of light. The detection experiments show that the rapid structural road elements detection（RSRED） algorithm can extract the lane markings, road signs, zebra crossings and other road elements against the interference of light, shelter, pollution and the vehicle speed definitely influence over detection rate of road elements. Finally the Lane-kepping and Overtaking experiments show that the algorithm is efficient and stable.

关 键 词：视觉导航 道路检测 道路跟踪 模式识别 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]