Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces

Fadi Kizel; Maxim Shoshany; Nathan S. Netanyahu

doi:10.1109/IGARSS.2015.7326812

Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces

Fadi Kizel, Maxim Shoshany, Nathan S. Netanyahu

Department of Computer Science

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

2 Scopus citations

Abstract

Performing standard unmixing of a hyperspectral image, while taking into account all of the potential endmembers (EMs) in a pixel, is known to be prone to error. Instead, determining first the set of EMs that actually reside in each pixel, leads to enhanced unmixing results. This important insight for achieving higher unmixing accuracy can be exploited efficiently by extracting relevant spatial information from a given image. In this work, we present a new method for spatially adaptive spectral unmixing, called the Gaussian based spatially adaptive unmixing (GBSAU) method. GBSAU takes advantage of the spatial arrangement of the image pixels and their spectral relations in order to determine an actual subset of EMs per pixel. It is based on spatial localization of the EMs by fitting, for each EM, the parameters of the series of spatial Gaussians whose sum represents the EM's fraction surface over the image.

Original language	English
Title of host publication	2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4440-4443
Number of pages	4
ISBN (Electronic)	9781479979295
DOIs	https://doi.org/10.1109/IGARSS.2015.7326812
State	Published - 10 Nov 2015
Event	IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Milan, Italy Duration: 26 Jul 2015 → 31 Jul 2015

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2015-November

Conference

Conference	IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015
Country/Territory	Italy
City	Milan
Period	26/07/15 → 31/07/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Keywords

2D Gaussian fitting
Spatial endmember localization
Spectral unmixing

Access to Document

10.1109/IGARSS.2015.7326812

Cite this

Kizel, F., Shoshany, M., & Netanyahu, N. S. (2015). Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces. In 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings (pp. 4440-4443). Article 7326812 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2015-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2015.7326812

Kizel, Fadi ; Shoshany, Maxim ; Netanyahu, Nathan S. / Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces. 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 4440-4443 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{cddbce92023b4203bc4fa36378a96c6f,

title = "Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces",

abstract = "Performing standard unmixing of a hyperspectral image, while taking into account all of the potential endmembers (EMs) in a pixel, is known to be prone to error. Instead, determining first the set of EMs that actually reside in each pixel, leads to enhanced unmixing results. This important insight for achieving higher unmixing accuracy can be exploited efficiently by extracting relevant spatial information from a given image. In this work, we present a new method for spatially adaptive spectral unmixing, called the Gaussian based spatially adaptive unmixing (GBSAU) method. GBSAU takes advantage of the spatial arrangement of the image pixels and their spectral relations in order to determine an actual subset of EMs per pixel. It is based on spatial localization of the EMs by fitting, for each EM, the parameters of the series of spatial Gaussians whose sum represents the EM's fraction surface over the image.",

keywords = "2D Gaussian fitting, Spatial endmember localization, Spectral unmixing",

author = "Fadi Kizel and Maxim Shoshany and Netanyahu, {Nathan S.}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 ; Conference date: 26-07-2015 Through 31-07-2015",

year = "2015",

month = nov,

day = "10",

doi = "10.1109/IGARSS.2015.7326812",

language = "אנגלית",

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

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4440--4443",

booktitle = "2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings",

address = "ארצות הברית",

}

Kizel, F, Shoshany, M & Netanyahu, NS 2015, Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces. in 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings., 7326812, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2015-November, Institute of Electrical and Electronics Engineers Inc., pp. 4440-4443, IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015, Milan, Italy, 26/07/15. https://doi.org/10.1109/IGARSS.2015.7326812

Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces. / Kizel, Fadi; Shoshany, Maxim; Netanyahu, Nathan S.
2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 4440-4443 7326812 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2015-November).

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

TY - GEN

T1 - Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces

AU - Kizel, Fadi

AU - Shoshany, Maxim

AU - Netanyahu, Nathan S.

PY - 2015/11/10

Y1 - 2015/11/10

N2 - Performing standard unmixing of a hyperspectral image, while taking into account all of the potential endmembers (EMs) in a pixel, is known to be prone to error. Instead, determining first the set of EMs that actually reside in each pixel, leads to enhanced unmixing results. This important insight for achieving higher unmixing accuracy can be exploited efficiently by extracting relevant spatial information from a given image. In this work, we present a new method for spatially adaptive spectral unmixing, called the Gaussian based spatially adaptive unmixing (GBSAU) method. GBSAU takes advantage of the spatial arrangement of the image pixels and their spectral relations in order to determine an actual subset of EMs per pixel. It is based on spatial localization of the EMs by fitting, for each EM, the parameters of the series of spatial Gaussians whose sum represents the EM's fraction surface over the image.

AB - Performing standard unmixing of a hyperspectral image, while taking into account all of the potential endmembers (EMs) in a pixel, is known to be prone to error. Instead, determining first the set of EMs that actually reside in each pixel, leads to enhanced unmixing results. This important insight for achieving higher unmixing accuracy can be exploited efficiently by extracting relevant spatial information from a given image. In this work, we present a new method for spatially adaptive spectral unmixing, called the Gaussian based spatially adaptive unmixing (GBSAU) method. GBSAU takes advantage of the spatial arrangement of the image pixels and their spectral relations in order to determine an actual subset of EMs per pixel. It is based on spatial localization of the EMs by fitting, for each EM, the parameters of the series of spatial Gaussians whose sum represents the EM's fraction surface over the image.

KW - 2D Gaussian fitting

KW - Spatial endmember localization

KW - Spectral unmixing

UR - http://www.scopus.com/inward/record.url?scp=84962583913&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2015.7326812

DO - 10.1109/IGARSS.2015.7326812

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84962583913

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 4440

EP - 4443

BT - 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015

Y2 - 26 July 2015 through 31 July 2015

ER -

Kizel F, Shoshany M, Netanyahu NS. Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces. In 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 4440-4443. 7326812. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2015.7326812

Spatially adaptive hyperspectral unmixing based on sums of 2D Gaussians for modelling endmember fraction surfaces

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this