Unsupervised Hyperspectral Band Selection Method Based on Low-Rank Representation

Chunyan Yu, Kun Cen, Chein I. Chang, Fang Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In order to reduce the spectral redundancy of hyperspectral remote sensing images and reduce the computational complexity of subsequent processing, an unsupervised hyperspectral image band selection algorithm based on low-rank representation (LRBS) was proposed in this paper. First, a low-rank representation of the hyperspectral image is proposed and a low-rank coefficient matrix is obtained. Then, each column of the low-rank coefficient is used as a vertex of the graph to perform spectral clustering. Lastly, we use the fixed initial k-means cluster centers for clustering to get the salient band of each cluster. The experimental simulation results show that the bands selected by LRBS algorithm can improve the classification accuracy and have better performance than other methods.

Original languageEnglish
Title of host publicationCommunications, Signal Processing, and Systems - Proceedings of the 2018 CSPS Volume 1
Subtitle of host publicationCommunications
EditorsQilian Liang, Xin Liu, Baoju Zhang, Zhenyu Na, Wei Wang, Jiasong Mu
PublisherSpringer Verlag
Pages1053-1061
Number of pages9
ISBN (Print)9789811362637
DOIs
Publication statusPublished - 2019
EventInternational Conference on Communications, Signal Processing, and Systems, CSPS 2018 - Dalian, China
Duration: 2018 Jul 142018 Jul 16

Publication series

NameLecture Notes in Electrical Engineering
Volume515
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Communications, Signal Processing, and Systems, CSPS 2018
Country/TerritoryChina
CityDalian
Period18-07-1418-07-16

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Unsupervised Hyperspectral Band Selection Method Based on Low-Rank Representation'. Together they form a unique fingerprint.

Cite this