基于CART决策树提取高分辨率遥感影像建筑物信息

地震 ›› 2013, Vol. 33 ›› Issue (2): 96-102.

基于CART决策树提取高分辨率遥感影像建筑物信息

李强^1,2, 张景发²

1.中国地质大学武汉地球物理与空间信息学院 430074;
2.中国地震局地壳应力研究所, 北京 100085

收稿日期:2013-01-09 出版日期:2013-04-30 发布日期:2020-09-27
作者简介:李强(1987-), 男, 山东潍坊人, 硕士研究生, 主要从事遥感信息提取研究。
基金资助:
国家高技术研究发展计划(863计划)(2012AA121304)和高分光学卫星遥感地震应急技术研究(E0205/1112/9)

Extraction of Building Information from High Resolution Images Based on CART Decision Tree

LI Qiang^1,2, ZHANG Jing-fa²

1. Institute of Geophysics and Geomatics, China University of Geosciences; Wuhan 430074, China;
2. Institute of Crustal Dynamics, CEA, Beijing 100085, China

Received:2013-01-09 Online:2013-04-30 Published:2020-09-27

摘要/Abstract

摘要： 传统的仅依赖于光谱信息的遥感影像信息提取方法难以满足精度要求, 基于CART算法构建规则集, 利用决策树技术对玉树地区高分辨率影像进行建筑物信息提取, 除了光谱信息外还结合建筑物的纹理特征信息。结果表明, 提取精度较传统的最大似然法有了较明显的提高, 说明此方法对于高分辨率影像建筑物提取具有一定的可行性。

关键词: CART决策树, 高分辨率遥感影像, 建筑物信息提取

Abstract: Traditional information extraction method from remote sensing images depends on spectral information, and is difficult to satisfy accuracy requirement. We combine spectral information with texture feature information to extract building information from high resolution images in Yushu area based on CART algorithm. Results show that comparing with traditional maximum likelihood method, the extraction accuracy has been improved. The method for high resolution image building extraction is feasible.

Key words: CART decision tree, High resolution image, Building information extraction

中图分类号:

P315.9

李强, 张景发. 基于CART决策树提取高分辨率遥感影像建筑物信息[J]. 地震, 2013, 33(2): 96-102.

LI Qiang, ZHANG Jing-fa. Extraction of Building Information from High Resolution Images Based on CART Decision Tree[J]. EARTHQUAKE, 2013, 33(2): 96-102.