Hyperspectral Band Selection Based on Matrix CUR Decomposition

Katherine Henneberger; Longxiu Huang; Jing Qin

doi:10.1109/IGARSS52108.2023.10282944

Hyperspectral Band Selection Based on Matrix CUR Decomposition

Katherine Henneberger
, Longxiu Huang
, Jing Qin

Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Band selection is an important technique for eliminating spectral redundancy of hyperspectral imagery (HSI) while preserving critical information. Recently, correlations among neighboring bands or pixels have been exploited in the form of graph regularizations to reduce the data dimensionality efficiently. However, manipulation of graph regularizations typically causes computational bottlenecks. In this work, we propose a robust method for hyperspectral band selection based on spatial/spectral graph Laplacians and matrix CUR decomposition. The efficiency of the proposed method has been shown on two real data sets by comparing with several other state-of-the-art band selection methods.

Original language	English
Title of host publication	IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Pages	7380-7383
Number of pages	4
ISBN (Electronic)	9798350320107
DOIs	https://doi.org/10.1109/IGARSS52108.2023.10282944
State	Published - 2023
Event	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States Duration: Jul 16 2023 → Jul 21 2023

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2023-July

Conference

Conference	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Country/Territory	United States
City	Pasadena
Period	7/16/23 → 7/21/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

The research of K. Henneberger and J. Qin is supported by the National Science Foundation Grant DMS 1941197. L. Huang was partially supported by the AMS Simons Travel Grant.

Funders	Funder number
National Science Foundation Arctic Social Science Program	DMS 1941197
National Science Foundation Arctic Social Science Program

Keywords

Hyperspectral band selection
classification
matrix CUR decomposition
robust PCA

ASJC Scopus subject areas

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS52108.2023.10282944

Cite this

@inproceedings{cba97cea0ee44dd19d4cad50af6acbb3,

title = "Hyperspectral Band Selection Based on Matrix CUR Decomposition",

abstract = "Band selection is an important technique for eliminating spectral redundancy of hyperspectral imagery (HSI) while preserving critical information. Recently, correlations among neighboring bands or pixels have been exploited in the form of graph regularizations to reduce the data dimensionality efficiently. However, manipulation of graph regularizations typically causes computational bottlenecks. In this work, we propose a robust method for hyperspectral band selection based on spatial/spectral graph Laplacians and matrix CUR decomposition. The efficiency of the proposed method has been shown on two real data sets by comparing with several other state-of-the-art band selection methods.",

keywords = "Hyperspectral band selection, classification, matrix CUR decomposition, robust PCA",

author = "Katherine Henneberger and Longxiu Huang and Jing Qin",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 ; Conference date: 16-07-2023 Through 21-07-2023",

year = "2023",

doi = "10.1109/IGARSS52108.2023.10282944",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

pages = "7380--7383",

booktitle = "IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

}

Henneberger, K, Huang, L & Qin, J 2023, Hyperspectral Band Selection Based on Matrix CUR Decomposition. in IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2023-July, pp. 7380-7383, 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023, Pasadena, United States, 7/16/23. https://doi.org/10.1109/IGARSS52108.2023.10282944

Hyperspectral Band Selection Based on Matrix CUR Decomposition. / Henneberger, Katherine; Huang, Longxiu; Qin, Jing.
IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. 2023. p. 7380-7383 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2023-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Hyperspectral Band Selection Based on Matrix CUR Decomposition

AU - Henneberger, Katherine

AU - Huang, Longxiu

AU - Qin, Jing

PY - 2023

Y1 - 2023

N2 - Band selection is an important technique for eliminating spectral redundancy of hyperspectral imagery (HSI) while preserving critical information. Recently, correlations among neighboring bands or pixels have been exploited in the form of graph regularizations to reduce the data dimensionality efficiently. However, manipulation of graph regularizations typically causes computational bottlenecks. In this work, we propose a robust method for hyperspectral band selection based on spatial/spectral graph Laplacians and matrix CUR decomposition. The efficiency of the proposed method has been shown on two real data sets by comparing with several other state-of-the-art band selection methods.

AB - Band selection is an important technique for eliminating spectral redundancy of hyperspectral imagery (HSI) while preserving critical information. Recently, correlations among neighboring bands or pixels have been exploited in the form of graph regularizations to reduce the data dimensionality efficiently. However, manipulation of graph regularizations typically causes computational bottlenecks. In this work, we propose a robust method for hyperspectral band selection based on spatial/spectral graph Laplacians and matrix CUR decomposition. The efficiency of the proposed method has been shown on two real data sets by comparing with several other state-of-the-art band selection methods.

KW - Hyperspectral band selection

KW - classification

KW - matrix CUR decomposition

KW - robust PCA

UR - https://www.scopus.com/pages/publications/85178383617

UR - https://www.scopus.com/pages/publications/85178383617#tab=citedBy

U2 - 10.1109/IGARSS52108.2023.10282944

DO - 10.1109/IGARSS52108.2023.10282944

M3 - Conference contribution

AN - SCOPUS:85178383617

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 7380

EP - 7383

BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023

Y2 - 16 July 2023 through 21 July 2023

ER -

Hyperspectral Band Selection Based on Matrix CUR Decomposition

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this