Land-use scene classification using multi-scale completed local binary patterns

Chen Chen; Baochang Zhang; Hongjun Su; Wei Li; Lu Wang

doi:10.1007/s11760-015-0804-2

Land-use scene classification using multi-scale completed local binary patterns

Chen Chen
, Baochang Zhang^*
, Hongjun Su
, Wei Li
, Lu Wang

^*Corresponding author for this work

University of Texas at Dallas
Beihang University
Hohai University
Beijing University of Chemical Technology

Research output: Contribution to journal › Article › peer-review

167 Citations (Scopus)

Abstract

In this paper, we introduce the completed local binary patterns (CLBP) operator for the first time on remote sensing land-use scene classification. To further improve the representation power of CLBP, we propose a multi-scale CLBP (MS-CLBP) descriptor to characterize the dominant texture features in multiple resolutions. Two different kinds of implementations of MS-CLBP equipped with the kernel-based extreme learning machine are investigated and compared in terms of classification accuracy and computational complexity. The proposed approach is extensively tested on the 21-class land-use dataset and the 19-class satellite scene dataset showing a consistent increase on performance when compared to the state of the arts.

Original language	English
Pages (from-to)	745-752
Number of pages	8
Journal	Signal, Image and Video Processing
Volume	10
Issue number	4
DOIs	https://doi.org/10.1007/s11760-015-0804-2
Publication status	Published - 1 Apr 2016
Externally published	Yes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 15 Life on Land

Keywords

Extreme learning machine
Land-use scene classification
Local binary patterns
Multi-scale analysis

Access to Document

10.1007/s11760-015-0804-2

Cite this

@article{e5cdc2819be740f08c5651f6a26b725e,

title = "Land-use scene classification using multi-scale completed local binary patterns",

abstract = "In this paper, we introduce the completed local binary patterns (CLBP) operator for the first time on remote sensing land-use scene classification. To further improve the representation power of CLBP, we propose a multi-scale CLBP (MS-CLBP) descriptor to characterize the dominant texture features in multiple resolutions. Two different kinds of implementations of MS-CLBP equipped with the kernel-based extreme learning machine are investigated and compared in terms of classification accuracy and computational complexity. The proposed approach is extensively tested on the 21-class land-use dataset and the 19-class satellite scene dataset showing a consistent increase on performance when compared to the state of the arts.",

keywords = "Extreme learning machine, Land-use scene classification, Local binary patterns, Multi-scale analysis",

author = "Chen Chen and Baochang Zhang and Hongjun Su and Wei Li and Lu Wang",

note = "Publisher Copyright: {\textcopyright} 2015, Springer-Verlag London.",

year = "2016",

month = apr,

day = "1",

doi = "10.1007/s11760-015-0804-2",

language = "English",

volume = "10",

pages = "745--752",

journal = "Signal, Image and Video Processing",

issn = "1863-1703",

publisher = "Springer London",

number = "4",

}

TY - JOUR

T1 - Land-use scene classification using multi-scale completed local binary patterns

AU - Chen, Chen

AU - Zhang, Baochang

AU - Su, Hongjun

AU - Li, Wei

AU - Wang, Lu

PY - 2016/4/1

Y1 - 2016/4/1

N2 - In this paper, we introduce the completed local binary patterns (CLBP) operator for the first time on remote sensing land-use scene classification. To further improve the representation power of CLBP, we propose a multi-scale CLBP (MS-CLBP) descriptor to characterize the dominant texture features in multiple resolutions. Two different kinds of implementations of MS-CLBP equipped with the kernel-based extreme learning machine are investigated and compared in terms of classification accuracy and computational complexity. The proposed approach is extensively tested on the 21-class land-use dataset and the 19-class satellite scene dataset showing a consistent increase on performance when compared to the state of the arts.

AB - In this paper, we introduce the completed local binary patterns (CLBP) operator for the first time on remote sensing land-use scene classification. To further improve the representation power of CLBP, we propose a multi-scale CLBP (MS-CLBP) descriptor to characterize the dominant texture features in multiple resolutions. Two different kinds of implementations of MS-CLBP equipped with the kernel-based extreme learning machine are investigated and compared in terms of classification accuracy and computational complexity. The proposed approach is extensively tested on the 21-class land-use dataset and the 19-class satellite scene dataset showing a consistent increase on performance when compared to the state of the arts.

KW - Extreme learning machine

KW - Land-use scene classification

KW - Local binary patterns

KW - Multi-scale analysis

UR - https://www.scopus.com/pages/publications/84938519282

U2 - 10.1007/s11760-015-0804-2

DO - 10.1007/s11760-015-0804-2

M3 - Article

AN - SCOPUS:84938519282

SN - 1863-1703

VL - 10

SP - 745

EP - 752

JO - Signal, Image and Video Processing

JF - Signal, Image and Video Processing

IS - 4

ER -

Land-use scene classification using multi-scale completed local binary patterns

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this