Share Email Print

Proceedings Paper

On performance improvement of vertex component analysis based endmember extraction from hyperspectral imagery
Author(s): Qian Du; Nareenart Raksuntorn; Nicolas H. Younan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Spectral mixture analysis is one of the major techniques in hyperspectral remote sensing image analysis. Endmember extraction for spectral mixture analysis is a necessary step when endmember information is unknown. If endmembers are assumed to be pure pixels present in an image scene, endmember extraction is to search the most distinct pixels. Popular algorithms using the criteria of simplex volume maximization (e.g., N-FINDR) and spectral signature similarity (e.g., Vertex Component Analysis) belong to this type. N-FINDR is a parallel-searching method, where all the endmembers are determined simultaneously. VCA is a sequential-searching method, finding endmembers one after another, which can greatly save computational cost. In this paper, we focus on VCA-based endmember extraction. In particular, we propose a new searching approach that makes the extracted endmembers more distinct. Real data experiments show that it can improve the quality of extracted endmembers.

Paper Details

Date Published: 22 May 2014
PDF: 6 pages
Proc. SPIE 9124, Satellite Data Compression, Communications, and Processing X, 91240J (22 May 2014); doi: 10.1117/12.2050701
Show Author Affiliations
Qian Du, Mississippi State Univ. (United States)
Nareenart Raksuntorn, Suan Sunandha Rajabhat Univ. (Thailand)
Nicolas H. Younan, Mississippi State Univ. (United States)

Published in SPIE Proceedings Vol. 9124:
Satellite Data Compression, Communications, and Processing X
Bormin Huang; Chein-I Chang; José Fco. López, Editor(s)

© SPIE. Terms of Use
Back to Top