摘要
针对高分辨率可见光图像中的道路和桥梁目标,提出了一种基于区域生长的道路和桥梁自动识别的方法。利用区域生长对原始图像进行粗分类,有效去除利用Canny算子进行边缘检测后得到的“弱边缘”,然后利用规则去除无效线段,再检测平行线,对不连续的线段进行连接,最后根据目标模型的特征标识出道路和桥梁目标。实验结果表明,在不需要人工干预的条件下,该方法能够快速有效地自动识别出道路和桥梁目标。
In this paper,a method to solve the problem of road and bridge recognition based on region growing from high resolution optical images is presented.First,in order to remove ＂thin edges＂ which are produced by edge detection with Canny operator,we use region growing to classify original image approximately ,then use rules to remove useless segments ,detect parallel and connect discrete segments,and at last identify road and bridge according to target model.Experimental result shows that road and bridge can be recognized fast and efficiently without manual work.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第16期216-218,共3页
Computer Engineering and Applications
基金
国家高技术研究发展计划(863) (the National High- Tech Research and Development Plan of China under Grant No.2002AA783055)
关键词
区域生长
道路识别
桥梁识别
检测平行线
region growing
road recognition
bridge recognition
parallel detection
