A machine learning approach for finding hyperspectral endmembers

Amit Banerjee; Philippe Burlina; Joshua Broadwater

doi:10.1109/IGARSS.2007.4423675

A machine learning approach for finding hyperspectral endmembers

Amit Banerjee, Philippe Burlina, Joshua Broadwater

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

18 Scopus citations

Abstract

A support vector algorithm for detecting endmembers in a hyperspectral image is introduced. It is a novel method for finding the spectral convexities in a high-dimensional space which addresses several limitations of previous endmember methods. A new approach for estimating the number of endmembers using rate-distortion theory is also presented. It is based upon the observation that the endmembers form a set of basis vectors for the hyperspectral datacube using the linear mixture model. The result is a fully-automatic method for endmember detection. Experimental results using the Cuprite datacube are presented.

Original language	English (US)
Title of host publication	2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007
Pages	3817-3820
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2007.4423675
State	Published - 2007
Externally published	Yes
Event	2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007 - Barcelona, Spain Duration: Jun 23 2007 → Jun 28 2007

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)

Other

Other	2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007
Country/Territory	Spain
City	Barcelona
Period	6/23/07 → 6/28/07

Keywords

Endmember extraction
Hyperspectral processing
Support vector methods

ASJC Scopus subject areas

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS.2007.4423675

Cite this

A machine learning approach for finding hyperspectral endmembers. / Banerjee, Amit; Burlina, Philippe; Broadwater, Joshua.
2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007. 2007. p. 3817-3820 4423675 (International Geoscience and Remote Sensing Symposium (IGARSS)).

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

Banerjee, A, Burlina, P & Broadwater, J 2007, A machine learning approach for finding hyperspectral endmembers. in 2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007., 4423675, International Geoscience and Remote Sensing Symposium (IGARSS), pp. 3817-3820, 2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007, Barcelona, Spain, 6/23/07. https://doi.org/10.1109/IGARSS.2007.4423675

@inproceedings{10b9e83cbe374baeacf58729fd4269bb,

title = "A machine learning approach for finding hyperspectral endmembers",

abstract = "A support vector algorithm for detecting endmembers in a hyperspectral image is introduced. It is a novel method for finding the spectral convexities in a high-dimensional space which addresses several limitations of previous endmember methods. A new approach for estimating the number of endmembers using rate-distortion theory is also presented. It is based upon the observation that the endmembers form a set of basis vectors for the hyperspectral datacube using the linear mixture model. The result is a fully-automatic method for endmember detection. Experimental results using the Cuprite datacube are presented.",

keywords = "Endmember extraction, Hyperspectral processing, Support vector methods",

author = "Amit Banerjee and Philippe Burlina and Joshua Broadwater",

year = "2007",

doi = "10.1109/IGARSS.2007.4423675",

language = "English (US)",

isbn = "1424412129",

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

pages = "3817--3820",

booktitle = "2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007",

note = "2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007 ; Conference date: 23-06-2007 Through 28-06-2007",

}

TY - GEN

T1 - A machine learning approach for finding hyperspectral endmembers

AU - Banerjee, Amit

AU - Burlina, Philippe

AU - Broadwater, Joshua

PY - 2007

Y1 - 2007

N2 - A support vector algorithm for detecting endmembers in a hyperspectral image is introduced. It is a novel method for finding the spectral convexities in a high-dimensional space which addresses several limitations of previous endmember methods. A new approach for estimating the number of endmembers using rate-distortion theory is also presented. It is based upon the observation that the endmembers form a set of basis vectors for the hyperspectral datacube using the linear mixture model. The result is a fully-automatic method for endmember detection. Experimental results using the Cuprite datacube are presented.

AB - A support vector algorithm for detecting endmembers in a hyperspectral image is introduced. It is a novel method for finding the spectral convexities in a high-dimensional space which addresses several limitations of previous endmember methods. A new approach for estimating the number of endmembers using rate-distortion theory is also presented. It is based upon the observation that the endmembers form a set of basis vectors for the hyperspectral datacube using the linear mixture model. The result is a fully-automatic method for endmember detection. Experimental results using the Cuprite datacube are presented.

KW - Endmember extraction

KW - Hyperspectral processing

KW - Support vector methods

UR - http://www.scopus.com/inward/record.url?scp=82355186673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82355186673&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2007.4423675

DO - 10.1109/IGARSS.2007.4423675

M3 - Conference contribution

AN - SCOPUS:82355186673

SN - 1424412129

SN - 9781424412129

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 3817

EP - 3820

BT - 2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007

T2 - 2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007

Y2 - 23 June 2007 through 28 June 2007

ER -

A machine learning approach for finding hyperspectral endmembers

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this