适用于多目标遥感自动解译的最佳专题指数筛选

发布时间：2018-02-24 05:28

本文关键词： 植被指数水体指数建筑用地指数面向对象分类指数数量指数组合　出处：《遥感技术与应用》2017年03期 　论文类型：期刊论文

【摘要】：专题指数对遥感影像自动解译至关重要,现有研究多针对单目标信息提取来筛选专题指数,无法得到适用于多目标遥感自动解译的最佳专题指数。以德州市城区及周边地区为例,采用Landsat 5TM影像提取了2个植被、3个水体和3个建筑用地专题指数,基于面向对象分类方法,分析了单个专题指数、指数组合、指数数量对同时提取植被、水体和不透水层信息的精度影响。结果表明:(1)3类地物的最小分类精度基本上随着专题指数增加而增大;(2)从单个专题指数来看,不透水层和植被提取的最佳指数分别是建筑物指数和土壤调整植被指数,而新型水体指数则能显著提高总体分类精度;(3)从专题指数的组合来看,植被分类精度随所用的植被指数数量增加而下降;建筑用地指数越多,不透水层和总体分类效果越好;随着水体指数数量增加,水体分类精度有所提高,而不透水层和总体分类精度则随之下降。
[Abstract]:Thematic indices are very important for automatic interpretation of remote sensing images. The best thematic index for automatic interpretation of multi-target remote sensing can not be obtained. Taking the urban area of Dezhou and its surrounding areas as an example, two vegetation, three water bodies and three thematic indices of construction land were extracted by using Landsat 5TM image. Based on the object oriented classification method, a single thematic index, index combination and index number pairs are analyzed to extract vegetation at the same time. The results show that the minimum classification accuracy of the three types of ground objects increases with the increase of the thematic index.) from the point of view of a single thematic index, the minimum classification accuracy of water bodies and impermeable layers increases with the increase of the thematic index. The best indexes of impermeable layer and vegetation extraction are the building index and the soil adjusted vegetation index, respectively, while the new water body index can significantly improve the overall classification accuracy. The accuracy of vegetation classification decreases with the increase of the number of vegetation indices used; the more the index of building land, the better the classification effect of impermeable layer and overall classification; with the increase of the number of water bodies, the accuracy of water body classification increases. However, the impermeable layer and the overall classification accuracy decreased with it.
【作者单位】：北京师范大学地表过程与资源生态国家重点实验室;北京师范大学地理科学学部;中国科学院地理科学与资源研究所;
【基金】：国家自然科学基金项目(41371186)
【分类号】：TP751

【相似文献】