随着WorldView-2卫星的发射,首次出现了8波段多光谱高分辨率商业卫星。高分辨率影像包含丰富的空间结构信息和地理特征信息,采用传统的基于像元的影像分析方法精度明显达不到要求。为了提高精度,本文以西藏那曲为研究区,利用面向对象的方法对那曲的WorldView-2影像进行分类,采用模糊分类法,利用所分地物的特征确定类别,针对西部地区干旱河流的特殊情况,提出了一种基于地物空间轮廓特征的分类方法,分类结果较好。 更多还原
【Abstract】 The WorldView-2 satellite is the first 8-band multi-spectral high-resolution commercial satellite.High-resolution image contains a wealthy information on spatial structure and geographic features,so the precision of traditional classification method based on pixel cannot meet the demand.In this paper,taking Naqu city of Tibet autonomous region as a study area and in order to improve the classification accuracy,the object-oriented method is used to do Naqu WorldView-2 image classification,combini... 更多还原