基于活动轮廓模型的道路障碍物检测算法的研究  

Study of the Obstacle Detection Based on Active Contour Models

作　　者：王磊 钱厚亮[2] 

机构地区：[1]正德职业技术学院机电工程系,江苏南京211106 [2]南京工程学院工业中心,江苏南京211167

出　　处：《控制工程》2013年第S1期202-205,共4页Control Engineering of China

基　　金：南京工程学院青年基金项目(QKJB2011025)

摘　　要：提出了基于活动轮廓模型的智能机器人障碍物检测算法。首先通过对采集得到的道路图像进行道路区域的提取,再针对提取目标区域确定初始轮廓线,采用简化的Mum-ford-Shah模型进行有限范围的图像分割,获得障碍物信息。由于该算法预先进行了道路区域的分割,将背景复杂的图像转换为单一背景的二值图像,弥补了活动轮廓模型本身算法对于多目标复杂背景分割效果不理想的不足,大大提高了障碍物检测的准确性;同时,由于将检测的范围缩小在道路区域,也极大的提高了运算的速率。This paper proposed a new algorithm of robot obstacle detection that based on the active contour models.The images that acquired by the camera are firstly processed to extract the road areas from which determine the initial contour lines,and then Mumford Shah are applied to carry out the segmentations.As the extraction of the road areas,the background has been changed from complex to simple,which remedies the poor results that due to segmentation based on the active contour models under multiple aims and complex background.The results of the experiment show that the algorithm can improve the correctness of the obstacle detection and strengthen the timeliness by the accelerated arithmetic speed that completes in a limited area.

关 键 词：活动轮廓模型 障碍物检测 道路提取 图像分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]