高分辨率图像辅助提取高光谱图像端元

崔宾阁; 张杰; 马毅; 任广波

doi:10.11834/jrs.20133067

技术方法 | 浏览量 : 0 下载量: 752 CSCD: 3

PDF
导出
分享
收藏
专辑

高分辨率图像辅助提取高光谱图像端元
High-resolution image-assisted endmember extraction of hyperspectral image
2014年18卷第1期页码：192-205
纸质出版：2014
DOI： 10.11834/jrs.20133067
稿件说明：

移动端阅览

[1]崔宾阁,张杰,马毅,任广波.高分辨率图像辅助提取高光谱图像端元[J].遥感学报,2014,18(01):192-205. DOI： 10.11834/jrs.20133067.

CUI Bin’ge, ZHANG Jie, MA Yi, et al. High-resolution image-assisted endmember extraction of hyperspectral image[J]. Journal of Remote Sensing, 2014, 18(1): 192-205. DOI： 10.11834/jrs.20133067.

摘要

现有的端元提取算法大多是基于凸面单形体假设

对于非单一地物类型

利用这些端元进行丰度反演将会影响混合像元分解精度。本文提出一种利用高分辨率图像判断高光谱像元内是否为同一类型地物的方法。首先

利用图像分割程序对高分辨率图像进行分割

得到光谱均一的斑块矢量图

并叠加到高光谱图像上;然后

通过空间关系分析找出斑块内的高光谱像元

称其为准端元;最后

利用端元提取算法在这些准端元中进行端元提取。实验结果表明

该方法将端元提取结果的误差降低了20%左右。

Abstract

Existing endmember extraction algorithms are mainly based on the convex simplex hypothesis. However

the cover types in certain endmembers are not single

which will affect the unmixing accuracy of mixed pixels when performing abundance inversion. In this paper

we propose to determine the nature of the hyperspectral pixel based on the high-resolution remote sensing image. First

a spectral relatively homogeneous vector diagram of blocks is superimposed on the hyperspectral image after the highresolution image segmentation. Second

spatial relations analysis is performed to find the hyperspectral pixels that are within the blocks

which is called a quasi-endmember. Finally

endmember extraction is performed to find endmembers from the quasi-endmember set. The experimental results demonstrate that our approach can reduce the root mean square error of the extraction results by about 20%.