A novel dictionary learning method for remote sensing image classification

Michael Ying Yang; Tao Jiang; Saif Al-Shaikhli; Bodo Rosenhahn

doi:10.1109/IGARSS.2015.7326793

A novel dictionary learning method for remote sensing image classification

Michael Ying Yang
, Tao Jiang
, Saif Al-Shaikhli
, Bodo Rosenhahn

Department of Earth Observation Science

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

3 Citations (Scopus)

Abstract

With the widely application of high-resolution remote sensing images, its classification has attracted a lot of attention. Most classification methods focus on various combination of features and ignore the similarities between different categories. In this paper we present a modification by combining ScSPM [1] with a dictionary learning method DL-COPAR [2], which separates the particularity and commonality atoms of class-specific sub-dictionaries. With this over-complete dictionary, the sparse representation of a query image can be specified to capture salient and unique properties. Experimental results on two remote sensing datasets show that, this modification achieves state-of-the-art classification accuracy, when merely SIFT feature is applied.

Original language	English
Title of host publication	IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings
Place of Publication	Milan
Publisher	IEEE
Pages	4364-4367
Number of pages	4
ISBN (Electronic)	9781479979295
DOIs	https://doi.org/10.1109/IGARSS.2015.7326793
Publication status	Published - 10 Nov 2015
Event	IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015: Remote Sensing: Understanding the Earth for a Safer World - Milan, Italy Duration: 26 Jul 2015 → 31 Jul 2015 http://www.igarss2015.org/

Publication series

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

Conference

Conference	IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015
Abbreviated title	IGARSS 2015
Country/Territory	Italy
City	Milan
Period	26/07/15 → 31/07/15
Internet address	http://www.igarss2015.org/

Keywords

classification
dictionary learning
Remote sensing
SPM

Access to Document

10.1109/IGARSS.2015.7326793

Cite this

Yang, M. Y., Jiang, T., Al-Shaikhli, S., & Rosenhahn, B. (2015). A novel dictionary learning method for remote sensing image classification. In IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings (pp. 4364-4367). Article 7326793 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2015-November). IEEE. https://doi.org/10.1109/IGARSS.2015.7326793

@inproceedings{6e5ec39b0fac4fcb86782383b441d971,

title = "A novel dictionary learning method for remote sensing image classification",

abstract = "With the widely application of high-resolution remote sensing images, its classification has attracted a lot of attention. Most classification methods focus on various combination of features and ignore the similarities between different categories. In this paper we present a modification by combining ScSPM [1] with a dictionary learning method DL-COPAR [2], which separates the particularity and commonality atoms of class-specific sub-dictionaries. With this over-complete dictionary, the sparse representation of a query image can be specified to capture salient and unique properties. Experimental results on two remote sensing datasets show that, this modification achieves state-of-the-art classification accuracy, when merely SIFT feature is applied.",

keywords = "classification, dictionary learning, Remote sensing, SPM",

author = "Yang, \{Michael Ying\} and Tao Jiang and Saif Al-Shaikhli and Bodo Rosenhahn",

year = "2015",

month = nov,

day = "10",

doi = "10.1109/IGARSS.2015.7326793",

language = "English",

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

publisher = "IEEE",

pages = "4364--4367",

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

address = "United States",

note = "IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 : Remote Sensing: Understanding the Earth for a Safer World, IGARSS 2015 ; Conference date: 26-07-2015 Through 31-07-2015",

url = "http://www.igarss2015.org/",

}

Yang, MY, Jiang, T, Al-Shaikhli, S & Rosenhahn, B 2015, A novel dictionary learning method for remote sensing image classification. in IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings., 7326793, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2015-November, IEEE, Milan, pp. 4364-4367, IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015, Milan, Italy, 26/07/15. https://doi.org/10.1109/IGARSS.2015.7326793

A novel dictionary learning method for remote sensing image classification. / Yang, Michael Ying; Jiang, Tao; Al-Shaikhli, Saif et al.
IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Milan: IEEE, 2015. p. 4364-4367 7326793 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2015-November).

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

TY - GEN

T1 - A novel dictionary learning method for remote sensing image classification

AU - Yang, Michael Ying

AU - Jiang, Tao

AU - Al-Shaikhli, Saif

AU - Rosenhahn, Bodo

PY - 2015/11/10

Y1 - 2015/11/10

N2 - With the widely application of high-resolution remote sensing images, its classification has attracted a lot of attention. Most classification methods focus on various combination of features and ignore the similarities between different categories. In this paper we present a modification by combining ScSPM [1] with a dictionary learning method DL-COPAR [2], which separates the particularity and commonality atoms of class-specific sub-dictionaries. With this over-complete dictionary, the sparse representation of a query image can be specified to capture salient and unique properties. Experimental results on two remote sensing datasets show that, this modification achieves state-of-the-art classification accuracy, when merely SIFT feature is applied.

AB - With the widely application of high-resolution remote sensing images, its classification has attracted a lot of attention. Most classification methods focus on various combination of features and ignore the similarities between different categories. In this paper we present a modification by combining ScSPM [1] with a dictionary learning method DL-COPAR [2], which separates the particularity and commonality atoms of class-specific sub-dictionaries. With this over-complete dictionary, the sparse representation of a query image can be specified to capture salient and unique properties. Experimental results on two remote sensing datasets show that, this modification achieves state-of-the-art classification accuracy, when merely SIFT feature is applied.

KW - classification

KW - dictionary learning

KW - Remote sensing

KW - SPM

UR - https://ezproxy2.utwente.nl/login?url=https://doi.org/10.1109/IGARSS.2015.7326793

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2015/chap/yang_nov.pdf

U2 - 10.1109/IGARSS.2015.7326793

DO - 10.1109/IGARSS.2015.7326793

M3 - Conference contribution

AN - SCOPUS:84962615499

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 4364

EP - 4367

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

PB - IEEE

CY - Milan

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

Y2 - 26 July 2015 through 31 July 2015

ER -

A novel dictionary learning method for remote sensing image classification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this