Contextual unmixing of geospatial data based on gaussian mixture models and markov random fields

R. Nishii; Y. Sawamura; A. Nakamoto; S. Kawaguchi

doi:10.1109/IGARSS.2008.4779660

Contextual unmixing of geospatial data based on gaussian mixture models and markov random fields

R. Nishii, Y. Sawamura, A. Nakamoto, S. Kawaguchi

Division of Advanced Mathematics Technology

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

4 Citations (Scopus)

Abstract

In supervised and unsupervised image classification, it is known that contextual classificationmethods based onMarkov random fields (MRF) improve non-contextual classifiers successfully. In this paper, we consider unsupervised unmixing problem by introduction of a new MRF. First, spectral vectors observed at mixels are assumed to follow Gaussian mixtures. Second, vectors representing fractions of categories are supposed to follow MRF over the observed area. Then, we derive an unsupervised unmixing method, which is also useful for unsupervised classification. The proposed method was evaluated through a synthetic data set and a benchmark data set for classification, and it showed an excellent performance.

Original language	English
Title of host publication	2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings
Pages	IV77-IV80
Edition	1
DOIs	https://doi.org/10.1109/IGARSS.2008.4779660
Publication status	Published - 2008
Event	2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings - Boston, MA, United States Duration: Jul 6 2008 → Jul 11 2008

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Number	1
Volume	4

Other

Other	2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings
Country/Territory	United States
City	Boston, MA
Period	7/6/08 → 7/11/08

All Science Journal Classification (ASJC) codes

Computer Science Applications
Earth and Planetary Sciences(all)

Access to Document

10.1109/IGARSS.2008.4779660

Cite this

Nishii, R., Sawamura, Y., Nakamoto, A., & Kawaguchi, S. (2008). Contextual unmixing of geospatial data based on gaussian mixture models and markov random fields. In 2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings (1 ed., pp. IV77-IV80). Article 4779660 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 4, No. 1). https://doi.org/10.1109/IGARSS.2008.4779660

Contextual unmixing of geospatial data based on gaussian mixture models and markov random fields. / Nishii, R.; Sawamura, Y.; Nakamoto, A. et al.
2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings. 1. ed. 2008. p. IV77-IV80 4779660 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 4, No. 1).

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

Nishii, R, Sawamura, Y, Nakamoto, A & Kawaguchi, S 2008, Contextual unmixing of geospatial data based on gaussian mixture models and markov random fields. in 2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings. 1 edn, 4779660, International Geoscience and Remote Sensing Symposium (IGARSS), no. 1, vol. 4, pp. IV77-IV80, 2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings, Boston, MA, United States, 7/6/08. https://doi.org/10.1109/IGARSS.2008.4779660

@inproceedings{b68d571f15794c28bbef77c7b30db284,

title = "Contextual unmixing of geospatial data based on gaussian mixture models and markov random fields",

abstract = "In supervised and unsupervised image classification, it is known that contextual classificationmethods based onMarkov random fields (MRF) improve non-contextual classifiers successfully. In this paper, we consider unsupervised unmixing problem by introduction of a new MRF. First, spectral vectors observed at mixels are assumed to follow Gaussian mixtures. Second, vectors representing fractions of categories are supposed to follow MRF over the observed area. Then, we derive an unsupervised unmixing method, which is also useful for unsupervised classification. The proposed method was evaluated through a synthetic data set and a benchmark data set for classification, and it showed an excellent performance.",

author = "R. Nishii and Y. Sawamura and A. Nakamoto and S. Kawaguchi",

year = "2008",

doi = "10.1109/IGARSS.2008.4779660",

language = "English",

isbn = "9781424428083",

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

number = "1",

pages = "IV77--IV80",

booktitle = "2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings",

edition = "1",

note = "2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings ; Conference date: 06-07-2008 Through 11-07-2008",

}

TY - GEN

T1 - Contextual unmixing of geospatial data based on gaussian mixture models and markov random fields

AU - Nishii, R.

AU - Sawamura, Y.

AU - Nakamoto, A.

AU - Kawaguchi, S.

PY - 2008

Y1 - 2008

N2 - In supervised and unsupervised image classification, it is known that contextual classificationmethods based onMarkov random fields (MRF) improve non-contextual classifiers successfully. In this paper, we consider unsupervised unmixing problem by introduction of a new MRF. First, spectral vectors observed at mixels are assumed to follow Gaussian mixtures. Second, vectors representing fractions of categories are supposed to follow MRF over the observed area. Then, we derive an unsupervised unmixing method, which is also useful for unsupervised classification. The proposed method was evaluated through a synthetic data set and a benchmark data set for classification, and it showed an excellent performance.

AB - In supervised and unsupervised image classification, it is known that contextual classificationmethods based onMarkov random fields (MRF) improve non-contextual classifiers successfully. In this paper, we consider unsupervised unmixing problem by introduction of a new MRF. First, spectral vectors observed at mixels are assumed to follow Gaussian mixtures. Second, vectors representing fractions of categories are supposed to follow MRF over the observed area. Then, we derive an unsupervised unmixing method, which is also useful for unsupervised classification. The proposed method was evaluated through a synthetic data set and a benchmark data set for classification, and it showed an excellent performance.

UR - http://www.scopus.com/inward/record.url?scp=67649790329&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649790329&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2008.4779660

DO - 10.1109/IGARSS.2008.4779660

M3 - Conference contribution

AN - SCOPUS:67649790329

SN - 9781424428083

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - IV77-IV80

BT - 2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings

T2 - 2008 IEEE International Geoscience and Remote Sensing Symposium - Proceedings

Y2 - 6 July 2008 through 11 July 2008

ER -

Contextual unmixing of geospatial data based on gaussian mixture models and markov random fields

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this