Nonlinear Bayesian unmixing of geospatial data based on GIBBS sampling

Ryuei Nishii, Pan Qin, Daisuke Uchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Image classification has a long history for estimating landcover categories by feature vectors, and various methods have been proposed from many viewpoints; statistics, machine learning and others. Multivariate normal distributions are frequently used to model feature distributions. Also, it is known that contextual classification methods based on Markov random fields (MRF) improve non-contextual classifiers successfully.

Original languageEnglish
Title of host publication2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings
Pages3104-3107
Number of pages4
DOIs
Publication statusPublished - 2013
Event2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Melbourne, VIC, Australia
Duration: Jul 21 2013Jul 26 2013

Other

Other2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013
CountryAustralia
CityMelbourne, VIC
Period7/21/137/26/13

Fingerprint

Image classification
Normal distribution
Learning systems
Classifiers
Statistics
Sampling
sampling
image classification
land cover
history
distribution
method
machine learning
statistics

All Science Journal Classification (ASJC) codes

  • Earth and Planetary Sciences(all)
  • Computer Science Applications

Cite this

Nishii, R., Qin, P., & Uchi, D. (2013). Nonlinear Bayesian unmixing of geospatial data based on GIBBS sampling. In 2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings (pp. 3104-3107). [6723483] https://doi.org/10.1109/IGARSS.2013.6723483

Nonlinear Bayesian unmixing of geospatial data based on GIBBS sampling. / Nishii, Ryuei; Qin, Pan; Uchi, Daisuke.

2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings. 2013. p. 3104-3107 6723483.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nishii, R, Qin, P & Uchi, D 2013, Nonlinear Bayesian unmixing of geospatial data based on GIBBS sampling. in 2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings., 6723483, pp. 3104-3107, 2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013, Melbourne, VIC, Australia, 7/21/13. https://doi.org/10.1109/IGARSS.2013.6723483
Nishii R, Qin P, Uchi D. Nonlinear Bayesian unmixing of geospatial data based on GIBBS sampling. In 2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings. 2013. p. 3104-3107. 6723483 https://doi.org/10.1109/IGARSS.2013.6723483
Nishii, Ryuei ; Qin, Pan ; Uchi, Daisuke. / Nonlinear Bayesian unmixing of geospatial data based on GIBBS sampling. 2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings. 2013. pp. 3104-3107
@inproceedings{48daca28dc864bca84424c4f94a3371e,
title = "Nonlinear Bayesian unmixing of geospatial data based on GIBBS sampling",
abstract = "Image classification has a long history for estimating landcover categories by feature vectors, and various methods have been proposed from many viewpoints; statistics, machine learning and others. Multivariate normal distributions are frequently used to model feature distributions. Also, it is known that contextual classification methods based on Markov random fields (MRF) improve non-contextual classifiers successfully.",
author = "Ryuei Nishii and Pan Qin and Daisuke Uchi",
year = "2013",
doi = "10.1109/IGARSS.2013.6723483",
language = "English",
isbn = "9781479911141",
pages = "3104--3107",
booktitle = "2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings",

}

TY - GEN

T1 - Nonlinear Bayesian unmixing of geospatial data based on GIBBS sampling

AU - Nishii, Ryuei

AU - Qin, Pan

AU - Uchi, Daisuke

PY - 2013

Y1 - 2013

N2 - Image classification has a long history for estimating landcover categories by feature vectors, and various methods have been proposed from many viewpoints; statistics, machine learning and others. Multivariate normal distributions are frequently used to model feature distributions. Also, it is known that contextual classification methods based on Markov random fields (MRF) improve non-contextual classifiers successfully.

AB - Image classification has a long history for estimating landcover categories by feature vectors, and various methods have been proposed from many viewpoints; statistics, machine learning and others. Multivariate normal distributions are frequently used to model feature distributions. Also, it is known that contextual classification methods based on Markov random fields (MRF) improve non-contextual classifiers successfully.

UR - http://www.scopus.com/inward/record.url?scp=84894259900&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894259900&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2013.6723483

DO - 10.1109/IGARSS.2013.6723483

M3 - Conference contribution

SN - 9781479911141

SP - 3104

EP - 3107

BT - 2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings

ER -