Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep: Overview and Toolbox

Behnood Rasti; Danfeng Hong; Renlong Hang; Pedram Ghamisi; Xudong Kang; Jocelyn Chanussot; Jon Atli Benediktsson

doi:10.1109/MGRS.2020.2979764

Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep: Overview and Toolbox

Behnood Rasti, Danfeng Hong, Renlong Hang, Pedram Ghamisi, Xudong Kang, Jocelyn Chanussot, Jon Atli Benediktsson

University of Iceland

Research output: Contribution to specialist publication › Article

54 Citations (Scopus)

Abstract

Hyperspectral images (HSIs) provide detailed spectral information through hundreds of (narrow) spectral channels (also known as dimensionality or bands), which can be used to accurately classify diverse materials of interest. The increased dimensionality of such data makes it possible to significantly improve data information content but provides a challenge to conventional techniques (the so-called curse of dimensionality) for accurate analysis of HSIs.

Original language	English
Pages	60-88
Number of pages	29
Volume	8
No.	4
Specialist publication	IEEE Geoscience and Remote Sensing Magazine
DOIs	https://doi.org/10.1109/MGRS.2020.2979764
Publication status	Published - Dec 2020

Bibliographical note

Funding Information:
We would like to thank Prof. Melba Crawford for providing the Indian Pines 2010 Data and the National Center for Airborne Laser Mapping, the Hyperspectral Image Analysis Laboratory at the University of Houston, and the IEEE GRSS Image Analysis and Data Fusion Technical Committee. This work is partially supported by an Alexander von Humboldt research grant. We also would like to thank the AXA Research Fund for supporting the work of Prof. Joc-elyn Chanussot and the corresponding author of this paper, Dr. Danfeng Hong.

Publisher Copyright:
© 2013 IEEE.

Access to Document

10.1109/MGRS.2020.2979764

Cite this

@misc{e1a0bfe7c5904070b30529a528d7cc14,

title = "Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep: Overview and Toolbox",

abstract = "Hyperspectral images (HSIs) provide detailed spectral information through hundreds of (narrow) spectral channels (also known as dimensionality or bands), which can be used to accurately classify diverse materials of interest. The increased dimensionality of such data makes it possible to significantly improve data information content but provides a challenge to conventional techniques (the so-called curse of dimensionality) for accurate analysis of HSIs. ",

author = "Behnood Rasti and Danfeng Hong and Renlong Hang and Pedram Ghamisi and Xudong Kang and Jocelyn Chanussot and Benediktsson, {Jon Atli}",

note = "Funding Information: We would like to thank Prof. Melba Crawford for providing the Indian Pines 2010 Data and the National Center for Airborne Laser Mapping, the Hyperspectral Image Analysis Laboratory at the University of Houston, and the IEEE GRSS Image Analysis and Data Fusion Technical Committee. This work is partially supported by an Alexander von Humboldt research grant. We also would like to thank the AXA Research Fund for supporting the work of Prof. Joc-elyn Chanussot and the corresponding author of this paper, Dr. Danfeng Hong. Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2020",

month = dec,

doi = "10.1109/MGRS.2020.2979764",

language = "English",

volume = "8",

pages = "60--88",

journal = "IEEE Geoscience and Remote Sensing Magazine",

issn = "2473-2397",

publisher = "IEEE Geosciene and Remote Sensing Society",

}

TY - GEN

T1 - Feature Extraction for Hyperspectral Imagery

T2 - The Evolution from Shallow to Deep: Overview and Toolbox

AU - Rasti, Behnood

AU - Hong, Danfeng

AU - Hang, Renlong

AU - Ghamisi, Pedram

AU - Kang, Xudong

AU - Chanussot, Jocelyn

AU - Benediktsson, Jon Atli

N1 - Funding Information: We would like to thank Prof. Melba Crawford for providing the Indian Pines 2010 Data and the National Center for Airborne Laser Mapping, the Hyperspectral Image Analysis Laboratory at the University of Houston, and the IEEE GRSS Image Analysis and Data Fusion Technical Committee. This work is partially supported by an Alexander von Humboldt research grant. We also would like to thank the AXA Research Fund for supporting the work of Prof. Joc-elyn Chanussot and the corresponding author of this paper, Dr. Danfeng Hong. Publisher Copyright: © 2013 IEEE.

PY - 2020/12

Y1 - 2020/12

N2 - Hyperspectral images (HSIs) provide detailed spectral information through hundreds of (narrow) spectral channels (also known as dimensionality or bands), which can be used to accurately classify diverse materials of interest. The increased dimensionality of such data makes it possible to significantly improve data information content but provides a challenge to conventional techniques (the so-called curse of dimensionality) for accurate analysis of HSIs.

AB - Hyperspectral images (HSIs) provide detailed spectral information through hundreds of (narrow) spectral channels (also known as dimensionality or bands), which can be used to accurately classify diverse materials of interest. The increased dimensionality of such data makes it possible to significantly improve data information content but provides a challenge to conventional techniques (the so-called curse of dimensionality) for accurate analysis of HSIs.

UR - http://www.scopus.com/inward/record.url?scp=85084241070&partnerID=8YFLogxK

U2 - 10.1109/MGRS.2020.2979764

DO - 10.1109/MGRS.2020.2979764

M3 - Article

AN - SCOPUS:85084241070

SN - 2473-2397

VL - 8

SP - 60

EP - 88

JO - IEEE Geoscience and Remote Sensing Magazine

JF - IEEE Geoscience and Remote Sensing Magazine

ER -

Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep: Overview and Toolbox

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this