Merging spectral and textural information for classifying remote sensing images

Wei Zhao; Shumei Cui; Zhen Wang

doi:10.1109/VPPC.2008.4677795

Merging spectral and textural information for classifying remote sensing images

Wei Zhao^*
, Shumei Cui
, Zhen Wang

^*Corresponding author for this work

Harbin Engineering University

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

1 Scopus citations

Abstract

Machine interpretation using pattern recognition technique for remote sensing images not only liberates plenty of human resources, but improves results on the efficiency in certain aspects. In this paper, land/water classifiers that combined the texture measures with spectral analysis for remote sensing images have been built. And specific recognition has been designed in order to take advantages of both analyses. The use of red/infrared spectral analysis refines the boundary of land/water; meanwhile the merging of co-occurrence matrix texture analysis and spectral information has improved the accuracy of the two-class labeling.

Original language	English
Title of host publication	2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008
DOIs	https://doi.org/10.1109/VPPC.2008.4677795
State	Published - 2008
Event	2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008 - Harbin, China Duration: 3 Sep 2008 → 5 Sep 2008

Publication series

Name	2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008

Conference

Conference	2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008
Country/Territory	China
City	Harbin
Period	3/09/08 → 5/09/08

Keywords

Grey level co-occurrence matrix
Remotely sensed images
Spectral feature
Texture analysis

Access to Document

10.1109/VPPC.2008.4677795

Cite this

@inproceedings{e3431e0975f544768362254af0647e50,

title = "Merging spectral and textural information for classifying remote sensing images",

abstract = "Machine interpretation using pattern recognition technique for remote sensing images not only liberates plenty of human resources, but improves results on the efficiency in certain aspects. In this paper, land/water classifiers that combined the texture measures with spectral analysis for remote sensing images have been built. And specific recognition has been designed in order to take advantages of both analyses. The use of red/infrared spectral analysis refines the boundary of land/water; meanwhile the merging of co-occurrence matrix texture analysis and spectral information has improved the accuracy of the two-class labeling.",

keywords = "Grey level co-occurrence matrix, Remotely sensed images, Spectral feature, Texture analysis",

author = "Wei Zhao and Shumei Cui and Zhen Wang",

year = "2008",

doi = "10.1109/VPPC.2008.4677795",

language = "英语",

isbn = "9781424418497",

series = "2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008",

booktitle = "2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008",

note = "2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008 ; Conference date: 03-09-2008 Through 05-09-2008",

}

Zhao, W , Cui, S & Wang, Z 2008, Merging spectral and textural information for classifying remote sensing images. in 2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008., 4677795, 2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008, 2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008, Harbin, China, 3/09/08. https://doi.org/10.1109/VPPC.2008.4677795

TY - GEN

T1 - Merging spectral and textural information for classifying remote sensing images

AU - Zhao, Wei

AU - Cui, Shumei

AU - Wang, Zhen

PY - 2008

Y1 - 2008

N2 - Machine interpretation using pattern recognition technique for remote sensing images not only liberates plenty of human resources, but improves results on the efficiency in certain aspects. In this paper, land/water classifiers that combined the texture measures with spectral analysis for remote sensing images have been built. And specific recognition has been designed in order to take advantages of both analyses. The use of red/infrared spectral analysis refines the boundary of land/water; meanwhile the merging of co-occurrence matrix texture analysis and spectral information has improved the accuracy of the two-class labeling.

AB - Machine interpretation using pattern recognition technique for remote sensing images not only liberates plenty of human resources, but improves results on the efficiency in certain aspects. In this paper, land/water classifiers that combined the texture measures with spectral analysis for remote sensing images have been built. And specific recognition has been designed in order to take advantages of both analyses. The use of red/infrared spectral analysis refines the boundary of land/water; meanwhile the merging of co-occurrence matrix texture analysis and spectral information has improved the accuracy of the two-class labeling.

KW - Grey level co-occurrence matrix

KW - Remotely sensed images

KW - Spectral feature

KW - Texture analysis

UR - https://www.scopus.com/pages/publications/57849125088

U2 - 10.1109/VPPC.2008.4677795

DO - 10.1109/VPPC.2008.4677795

M3 - 会议稿件

AN - SCOPUS:57849125088

SN - 9781424418497

T3 - 2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008

BT - 2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008

T2 - 2008 IEEE Vehicle Power and Propulsion Conference, VPPC 2008

Y2 - 3 September 2008 through 5 September 2008

ER -

Merging spectral and textural information for classifying remote sensing images

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this