A Fast Neighborhood Grouping Method for Hyperspectral Band Selection

Qi Wang, Qiang Li, Xuelong Li

Research output: Contribution to journalArticlepeer-review

127 Scopus citations

Abstract

Hyperspectral images can provide dozens to hundreds of continuous spectral bands, so the richness of information has been greatly improved. However, these bands lead to increasing complexity of data processing, and the redundancy of adjacent bands is large. Recently, although many band selection methods have been proposed, this task is rarely handled through the context information of the whole spectral bands. Moreover, the scholars mainly focus on the different numbers of selected bands to explain the influence by accuracy measures, neglecting how many bands to choose is appropriate. To tackle these issues, we propose a fast neighborhood grouping method for hyperspectral band selection (FNGBS). The hyperspectral image cube in space is partitioned into several groups using coarse-fine strategy. By doing so, it effectively mines the context information in a large spectrum range. Compared with most algorithms, the proposed method can obtain the most relevant and informative bands simultaneously as subset in accordance with two factors, such as local density and information entropy. In addition, our method can also automatically determine the minimum number of recommended bands by determinantal point process. Extensive experimental results on benchmark data sets demonstrate the proposed FNGBS achieves satisfactory performance against state-of-the-art algorithms.

Original languageEnglish
Article number9153939
Pages (from-to)5028-5039
Number of pages12
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume59
Issue number6
DOIs
StatePublished - Jun 2021

Keywords

  • Band selection
  • context information
  • determinantal point process (DPP)
  • hyperspectral image
  • neighborhood grouping

Fingerprint

Dive into the research topics of 'A Fast Neighborhood Grouping Method for Hyperspectral Band Selection'. Together they form a unique fingerprint.

Cite this