遥感影像上基于特征的道路提取方法  

The Theory of The Road Extraction Based On Road Character

作　　者：吴冰[1] 张占睦[1] 秦志远[1] 杜丹[1] 

机构地区：[1]信息工程大学 测绘学院,河南郑州450052

出　　处：《测绘学院学报》2004年第3期190-192,共3页Journal of Institute of Surveying and Mapping

摘　　要：从遥感影像上提取道路信息是当前遥感技术应用研究的主要方向之一。文中在详细分析航空遥感影像上道路特征及目前国内外关于道路提取技术的前提下,综合考虑各种实际情况,提出了一种新的基于特征的道路提取模型。在算法实现过程中,采用了自适应分块边缘检测、多尺度侦测道路中心点、自适应对比度调整、道路中心点综合判断准则等技术手段,保证了提取结果的稳健性、准确性。实验表明该算法能够快速、稳健地从航空遥感影像上提取道路中心骨架线。The method of extraction the information of the road from remote sensing image is one of the most primary study aspects of the application of Remote Sensing in this days. The paper has studied the character of the road in the aviation remote sensing image and the technique about the extraction of the road in our country and abroad. At the same time, it considers all kinds of cases generally. A new extraction model of the road is raised. During the course of the algorithm realized, self-adaptation block margin detection, multiple scale detecting, the central point of the road self-adaption contrast adjustment and synthetical judging criteria are used in the paper. So it makes the extraction result robust and accurate. The test shows the algorithm can extract the central line of the road from aviation image fast and robust.

关 键 词：道路特征 半自动提取 CANNY算子 自适应 

分 类 号：P237[天文地球—摄影测量与遥感]