TY - JOUR
T1 - Adaptive distance-based band hierarchy (ADBH) for effective hyperspectral band selection
AU - Sun, He
AU - Ren, Jinchang
AU - Zhao, Huimin
AU - Sun, Genyun
AU - Liao, Wenzhi
AU - Fang, Zhenyu
AU - Zabalza, Jaime
N1 - © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
PY - 2020/3/24
Y1 - 2020/3/24
N2 - Band selection has become a significant issue for the efficiency of the hyperspectral image (HSI) processing. Although many unsupervised band selection (UBS) approaches have been developed in the last decades, a flexible and robust method is still lacking. The lack of proper understanding of the HSI data structure has resulted in the inconsistency in the outcome of UBS. Besides, most of the UBS methods are either relying on complicated measurements or rather noise sensitive, which hinder the efficiency of the determined band subset. In this article, an adaptive distance-based band hierarchy (ADBH) clustering framework is proposed for UBS in HSI, which can help to avoid the noisy bands while reflecting the hierarchical data structure of HSI. With a tree hierarchy-based framework, we can acquire any number of band subset. By introducing a novel adaptive distance into the hierarchy, the similarity between bands and band groups can be computed straightforward while reducing the effect of noisy bands. Experiments on four datasets acquired from two HSI systems have fully validated the superiority of the proposed framework.
AB - Band selection has become a significant issue for the efficiency of the hyperspectral image (HSI) processing. Although many unsupervised band selection (UBS) approaches have been developed in the last decades, a flexible and robust method is still lacking. The lack of proper understanding of the HSI data structure has resulted in the inconsistency in the outcome of UBS. Besides, most of the UBS methods are either relying on complicated measurements or rather noise sensitive, which hinder the efficiency of the determined band subset. In this article, an adaptive distance-based band hierarchy (ADBH) clustering framework is proposed for UBS in HSI, which can help to avoid the noisy bands while reflecting the hierarchical data structure of HSI. With a tree hierarchy-based framework, we can acquire any number of band subset. By introducing a novel adaptive distance into the hierarchy, the similarity between bands and band groups can be computed straightforward while reducing the effect of noisy bands. Experiments on four datasets acquired from two HSI systems have fully validated the superiority of the proposed framework.
KW - adaptive distance
KW - hierarchy clustering
KW - hyperspectral band selection
KW - unsupervised learing
U2 - 10.1109/TCYB.2020.2977750
DO - 10.1109/TCYB.2020.2977750
M3 - Article
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
SN - 2168-2267
ER -