摘要
提出了一种遥感图像中机场跑道的自动识别方法。在分析机场结构特征的基础上,首先采用形态学方法提取图像的线结构;然后通过非监督聚类方法将直线段动态分组;最后进行直线段修复和跑道配对,实现对机场的识别定位。计算机仿真验证了该方法的有效性。
Based on analyzing line structure of runway, a new method to automatically detect runways in remote sensing image is presented.Firstly, line structure of the image by mathematical morphology is extracted.Then straight -line is grouped through dynamic clustering.Finally lines are relinked and runway are paired. Through runway's localization, the recognition of airfield is realized.The experimental results show that this method has a perfect performance and usability to identify airfield of remote sensing images.
出处
《红外与激光工程》
EI
CSCD
北大核心
2005年第3期314-318,332,共6页
Infrared and Laser Engineering
基金
国家自然科学基金资助项目(40101019)
