Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (16): 216-218.
• 工程与应用 • Previous Articles Next Articles
LI Gui-qin,YIN Dong,XUE Chen-rong
Received:
Revised:
Online:
Published:
Contact:
李桂芹,尹 东,薛晨荣
通讯作者:
Abstract: 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.
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。
LI Gui-qin,YIN Dong,XUE Chen-rong. Study of road and bridge recognition based on region growing[J]. Computer Engineering and Applications, 2007, 43(16): 216-218.
李桂芹,尹 东,薛晨荣. 基于区域生长的道路和桥梁识别方法的研究[J]. 计算机工程与应用, 2007, 43(16): 216-218.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://cea.ceaj.org/EN/
http://cea.ceaj.org/EN/Y2007/V43/I16/216