由于高分辨率遥感影像中道路信息的复杂性及其与其他地物光谱信息的相似性,导致基于像素道路提取方法中的道路特征利用不够充分.针对这个问题,对原始影像进行HIS变换提取光谱饱和度(Saturation,S)分量,运用基于区域邻接图(Region Adjacency Graph,RAG)的优化分割算法,实现道路区域的分割,然后利用基于最小二乘支持向量机(LSSVM)和多数投票原则对道路信息进行提取.实验表明,上述方法能有效地提取遥感影像中的道路信息.%Because of the complexity of road information in the high resolution remote sensing image and the similarity of the spectral information of other features,the road feature extraction method based on the pixel road extraction method is inadequate.To solve this problem,the HIS transform is performed on the original image to extract spectral saturation (Saturation,S) components.To realize road segmentation,we use the optimal segmentation algorithm which based on region adjacency graph (Region Adjacency,Graph,RAG) to realize road segmentation,and then extract road information by the method which based on least squares support vector machine (LSSVM) and majority voting principle.Experimental results show that the method can effectively extract the road information in remote sensing image.
展开▼