基于高分辨率遥感影像的DSM建筑物点的提取研究  

Research on Extracting Building Points from the DSM Data Combining the High-resolution Remote Sensing Image

作　　者：穆超[1] 余洁[1] 许磊[1] 郭培煌[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）》2009年第4期414-417,共4页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目(40523005)

摘　　要：采用基于小面积去除方法的中值SUSAN噪声点平滑方法,结合高分辨率遥感影像,对DSM中房屋点的提取进行了探讨。实验表明,本方法能有效地从DSM中提取绝大部分建筑物点,有助于建筑物的精确三维重建。According to high-resolution remote sensing image and digital surface model （DSM） the three dimensional building models can be automated established. The key of procedure is to obtain the building points from the DSM. Combining high resolution remote sensing image, the small region elimination method and Median-SUSAN filter is discussed for extracting the building points in this paper. The experiment indicats that this method is effectived for obtaining the major part of buitding points from DSM. It is benefit for the building＇s precise three-dimensional reconstruction.

关 键 词：高分辨率遥感影像 数字表面模型 建筑物点 决策树分类 中值SUSAN滤波 

分 类 号：P237.3[天文地球—摄影测量与遥感]