Urban features classification using 3D hyperspectral data

Michal Shimoni; Mahamadou Idrissa; Dirk Borghys; Trym Haavardsholm; Thomas Olsvik Opsahl; Christiaan Perneel

doi:10.1109/WHISPERS.2013.8080665

Urban features classification using 3D hyperspectral data

Michal Shimoni, Mahamadou Idrissa, Dirk Borghys, Trym Haavardsholm, Thomas Olsvik Opsahl, Christiaan Perneel

Norwegian Defence Research Establishment

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

Abstract

The surface classification of heterogeneous urban areas can be refined using the integration of spectral and 3D information. However, pixel-classification based fusion requires semi-pixel geo-registration accuracy. In this paper the 3D information is obtained from the hyperspectral data set itself. This study presents an adaptation of optimized MRF based stereo matching for the creation of 3D scenes using hyperspectral data. The obtained 3D information is integrated into a SVM classifier procedure. The results obtained in this study show the potential in the creation of 3D scenes using hyperspectral data and the benefit of combining this data with spectral information for better classification of the urban materials.

Original language	English
Title of host publication	2013 5th Workshop on Hyperspectral Image and Signal Processing
Subtitle of host publication	Evolution in Remote Sensing, WHISPERS 2013
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509011193
DOIs	https://doi.org/10.1109/WHISPERS.2013.8080665
Publication status	Published - 28 Jun 2013
Event	5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013 - Gainesville, United States Duration: 26 Jun 2013 → 28 Jun 2013

Publication series

Name	Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
Volume	2013-June
ISSN (Print)	2158-6276

Conference

Conference	5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013
Country/Territory	United States
City	Gainesville
Period	26/06/13 → 28/06/13

Keywords

Disparity map
Hyperspectral
Markov Random Field
Stochastic Expectation Maximization
Support Vector Machine

Access to Document

10.1109/WHISPERS.2013.8080665

Cite this

Shimoni, M., Idrissa, M., Borghys, D., Haavardsholm, T., Opsahl, T. O., & Perneel, C. (2013). Urban features classification using 3D hyperspectral data. In 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013 Article 8080665 (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing; Vol. 2013-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WHISPERS.2013.8080665

Shimoni, Michal ; Idrissa, Mahamadou ; Borghys, Dirk et al. / Urban features classification using 3D hyperspectral data. 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013. Institute of Electrical and Electronics Engineers Inc., 2013. (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing).

@inproceedings{15864aaf17b642958c141e7745c533df,

title = "Urban features classification using 3D hyperspectral data",

abstract = "The surface classification of heterogeneous urban areas can be refined using the integration of spectral and 3D information. However, pixel-classification based fusion requires semi-pixel geo-registration accuracy. In this paper the 3D information is obtained from the hyperspectral data set itself. This study presents an adaptation of optimized MRF based stereo matching for the creation of 3D scenes using hyperspectral data. The obtained 3D information is integrated into a SVM classifier procedure. The results obtained in this study show the potential in the creation of 3D scenes using hyperspectral data and the benefit of combining this data with spectral information for better classification of the urban materials.",

keywords = "Disparity map, Hyperspectral, Markov Random Field, Stochastic Expectation Maximization, Support Vector Machine",

author = "Michal Shimoni and Mahamadou Idrissa and Dirk Borghys and Trym Haavardsholm and Opsahl, {Thomas Olsvik} and Christiaan Perneel",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.; 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013 ; Conference date: 26-06-2013 Through 28-06-2013",

year = "2013",

month = jun,

day = "28",

doi = "10.1109/WHISPERS.2013.8080665",

language = "English",

series = "Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing",

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

booktitle = "2013 5th Workshop on Hyperspectral Image and Signal Processing",

}

Shimoni, M, Idrissa, M, Borghys, D, Haavardsholm, T, Opsahl, TO & Perneel, C 2013, Urban features classification using 3D hyperspectral data. in 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013., 8080665, Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing, vol. 2013-June, Institute of Electrical and Electronics Engineers Inc., 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013, Gainesville, United States, 26/06/13. https://doi.org/10.1109/WHISPERS.2013.8080665

Urban features classification using 3D hyperspectral data. / Shimoni, Michal; Idrissa, Mahamadou; Borghys, Dirk et al.
2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013. Institute of Electrical and Electronics Engineers Inc., 2013. 8080665 (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing; Vol. 2013-June).

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

TY - GEN

T1 - Urban features classification using 3D hyperspectral data

AU - Shimoni, Michal

AU - Idrissa, Mahamadou

AU - Borghys, Dirk

AU - Haavardsholm, Trym

AU - Opsahl, Thomas Olsvik

AU - Perneel, Christiaan

PY - 2013/6/28

Y1 - 2013/6/28

N2 - The surface classification of heterogeneous urban areas can be refined using the integration of spectral and 3D information. However, pixel-classification based fusion requires semi-pixel geo-registration accuracy. In this paper the 3D information is obtained from the hyperspectral data set itself. This study presents an adaptation of optimized MRF based stereo matching for the creation of 3D scenes using hyperspectral data. The obtained 3D information is integrated into a SVM classifier procedure. The results obtained in this study show the potential in the creation of 3D scenes using hyperspectral data and the benefit of combining this data with spectral information for better classification of the urban materials.

AB - The surface classification of heterogeneous urban areas can be refined using the integration of spectral and 3D information. However, pixel-classification based fusion requires semi-pixel geo-registration accuracy. In this paper the 3D information is obtained from the hyperspectral data set itself. This study presents an adaptation of optimized MRF based stereo matching for the creation of 3D scenes using hyperspectral data. The obtained 3D information is integrated into a SVM classifier procedure. The results obtained in this study show the potential in the creation of 3D scenes using hyperspectral data and the benefit of combining this data with spectral information for better classification of the urban materials.

KW - Disparity map

KW - Hyperspectral

KW - Markov Random Field

KW - Stochastic Expectation Maximization

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=85038599374&partnerID=8YFLogxK

U2 - 10.1109/WHISPERS.2013.8080665

DO - 10.1109/WHISPERS.2013.8080665

M3 - Conference contribution

AN - SCOPUS:85038599374

T3 - Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing

BT - 2013 5th Workshop on Hyperspectral Image and Signal Processing

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013

Y2 - 26 June 2013 through 28 June 2013

ER -

Shimoni M, Idrissa M, Borghys D, Haavardsholm T, Opsahl TO, Perneel C. Urban features classification using 3D hyperspectral data. In 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013. Institute of Electrical and Electronics Engineers Inc. 2013. 8080665. (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing). doi: 10.1109/WHISPERS.2013.8080665

Urban features classification using 3D hyperspectral data

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this