粒度Hough变换及其在遥感影像直线检测中的应用  

Line Detection in Remote Sensing Images Using Hough Transform Based on Granular Computing

作　　者：巫兆聪[1] 万茜婷[1] 梁静[1] 周正[1] 

机构地区：[1]武汉大学遥感信息工程学院,武汉市珞喻路129号430079

出　　处：《武汉大学学报（信息科学版）》2007年第10期860-863,共4页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目(40771157);国家863计划资助项目(2007AA12Z143)

摘　　要：在基于Hough变换的遥感影像直线检测的过程中引入粒度计算的概念,利用粒度计算具有多角度、多层次观察问题的能力,对遥感影像中的直线边缘特征进行不同粗细的粒度分析,建立粒度计算概念下的直线检测算法,实现对不同长短、粗细直线的识别。真实的IKONOS遥感影像机场跑道提取试验证明了该方法的有效性。The concept of granular computing into line detection in remote sensing images using Hough transform is introduced, according to the characteristic of granular computing that it can observe problems at multiple views and levels. An algorithm on line detection based on granular computing is established by analyzing linear edge features with granularity of various sizes. Different quantification interval of corresponding granular level is employed, so as to extract lines with different length and width efficiently. An application on airport runways extraction in the real IKONOS image proves the validity of this algorithm.

关 键 词：遥感影像 直线检测 粒度计算 HOUGH变换 

分 类 号：P237.4[天文地球—摄影测量与遥感]