A new parallel tool for classification of remotely sensed imagery

Sergio Bernabé; Antonio Plaza; Prashanth Reddy Marpu; Jon Atli Benediktsson

doi:10.1016/j.cageo.2011.12.009

A new parallel tool for classification of remotely sensed imagery

Sergio Bernabé
, Antonio Plaza
, Prashanth Reddy Marpu
, Jon Atli Benediktsson

University of Iceland

University of Iceland

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

Abstract

In this paper, we describe a new tool for classification of remotely sensed images. Our processing chain is based on three main parts: (1) pre-processing, performed using morphological profiles which model both the spatial (high resolution) and the spectral (color) information available from the scenes; (2) classification, which can be performed in unsupervised fashion using two well-known clustering techniques (ISODATA and k-means) or in supervised fashion, using a maximum likelihood classifier; and (3) post-processing, using a spatial-based technique based on a moving a window which defines a neighborhood around each pixel which is used to refine the initial classification by majority voting, taking in mind the spatial context around the classified pixel. The processing chain has been integrated into a desktop application which allows processing of satellite images available from Google Maps™ engine and developed using Java and the SwingX-WS library. A general framework for parallel implementation of the processing chain has also been developed and specifically tested on graphics processing units (GPUs), achieving speedups in the order of 30×with regard to the serial version of same chain implemented in C language.

Original language	English
Pages (from-to)	208-218
Number of pages	11
Journal	Computers and Geosciences
Volume	46
DOIs	https://doi.org/10.1016/j.cageo.2011.12.009
Publication status	Published - Sept 2012

Bibliographical note

Funding Information: This work has been supported by the European Community's Marie Curie Research Training Networks Programme under reference MRTN-CT-2006-035927 (HYPER-I-NET). Funding from the Spanish Ministry of Science and Innovation (HYPERCOMP/EODIX project, reference AYA2008-05965-C04-02) is also gratefully acknowledged. Last but not least, the authors would like to gratefully thank the three anonymous reviewers for their outstanding comments and suggestions, which greatly improved the technical quality and presentation of this manuscript.

Other keywords

Google maps™ engine
Graphics processing units (GPUs)
Information extraction
Parallel processing
Satellite image classification

Access to Document

10.1016/j.cageo.2011.12.009

Cite this

@article{9d372ea0d62d4d5ab4556e9d0aff70a8,

title = "A new parallel tool for classification of remotely sensed imagery",

abstract = "In this paper, we describe a new tool for classification of remotely sensed images. Our processing chain is based on three main parts: (1) pre-processing, performed using morphological profiles which model both the spatial (high resolution) and the spectral (color) information available from the scenes; (2) classification, which can be performed in unsupervised fashion using two well-known clustering techniques (ISODATA and k-means) or in supervised fashion, using a maximum likelihood classifier; and (3) post-processing, using a spatial-based technique based on a moving a window which defines a neighborhood around each pixel which is used to refine the initial classification by majority voting, taking in mind the spatial context around the classified pixel. The processing chain has been integrated into a desktop application which allows processing of satellite images available from Google Maps{\texttrademark} engine and developed using Java and the SwingX-WS library. A general framework for parallel implementation of the processing chain has also been developed and specifically tested on graphics processing units (GPUs), achieving speedups in the order of 30×with regard to the serial version of same chain implemented in C language.",

keywords = "Google maps{\texttrademark} engine, Graphics processing units (GPUs), Information extraction, Parallel processing, Satellite image classification",

author = "Sergio Bernab{\'e} and Antonio Plaza and \{Reddy Marpu\}, Prashanth and \{Atli Benediktsson\}, Jon",

note = "Funding Information: This work has been supported by the European Community's Marie Curie Research Training Networks Programme under reference MRTN-CT-2006-035927 (HYPER-I-NET). Funding from the Spanish Ministry of Science and Innovation (HYPERCOMP/EODIX project, reference AYA2008-05965-C04-02) is also gratefully acknowledged. Last but not least, the authors would like to gratefully thank the three anonymous reviewers for their outstanding comments and suggestions, which greatly improved the technical quality and presentation of this manuscript.",

year = "2012",

month = sep,

doi = "10.1016/j.cageo.2011.12.009",

language = "English",

volume = "46",

pages = "208--218",

journal = "Computers and Geosciences",

issn = "0098-3004",

publisher = "Elsevier Ltd.",

}

TY - JOUR

T1 - A new parallel tool for classification of remotely sensed imagery

AU - Bernabé, Sergio

AU - Plaza, Antonio

AU - Reddy Marpu, Prashanth

AU - Atli Benediktsson, Jon

N1 - Funding Information: This work has been supported by the European Community's Marie Curie Research Training Networks Programme under reference MRTN-CT-2006-035927 (HYPER-I-NET). Funding from the Spanish Ministry of Science and Innovation (HYPERCOMP/EODIX project, reference AYA2008-05965-C04-02) is also gratefully acknowledged. Last but not least, the authors would like to gratefully thank the three anonymous reviewers for their outstanding comments and suggestions, which greatly improved the technical quality and presentation of this manuscript.

PY - 2012/9

Y1 - 2012/9

N2 - In this paper, we describe a new tool for classification of remotely sensed images. Our processing chain is based on three main parts: (1) pre-processing, performed using morphological profiles which model both the spatial (high resolution) and the spectral (color) information available from the scenes; (2) classification, which can be performed in unsupervised fashion using two well-known clustering techniques (ISODATA and k-means) or in supervised fashion, using a maximum likelihood classifier; and (3) post-processing, using a spatial-based technique based on a moving a window which defines a neighborhood around each pixel which is used to refine the initial classification by majority voting, taking in mind the spatial context around the classified pixel. The processing chain has been integrated into a desktop application which allows processing of satellite images available from Google Maps™ engine and developed using Java and the SwingX-WS library. A general framework for parallel implementation of the processing chain has also been developed and specifically tested on graphics processing units (GPUs), achieving speedups in the order of 30×with regard to the serial version of same chain implemented in C language.

AB - In this paper, we describe a new tool for classification of remotely sensed images. Our processing chain is based on three main parts: (1) pre-processing, performed using morphological profiles which model both the spatial (high resolution) and the spectral (color) information available from the scenes; (2) classification, which can be performed in unsupervised fashion using two well-known clustering techniques (ISODATA and k-means) or in supervised fashion, using a maximum likelihood classifier; and (3) post-processing, using a spatial-based technique based on a moving a window which defines a neighborhood around each pixel which is used to refine the initial classification by majority voting, taking in mind the spatial context around the classified pixel. The processing chain has been integrated into a desktop application which allows processing of satellite images available from Google Maps™ engine and developed using Java and the SwingX-WS library. A general framework for parallel implementation of the processing chain has also been developed and specifically tested on graphics processing units (GPUs), achieving speedups in the order of 30×with regard to the serial version of same chain implemented in C language.

KW - Google maps™ engine

KW - Graphics processing units (GPUs)

KW - Information extraction

KW - Parallel processing

KW - Satellite image classification

UR - https://www.scopus.com/pages/publications/84864323267

U2 - 10.1016/j.cageo.2011.12.009

DO - 10.1016/j.cageo.2011.12.009

M3 - Article

SN - 0098-3004

VL - 46

SP - 208

EP - 218

JO - Computers and Geosciences

JF - Computers and Geosciences

ER -

A new parallel tool for classification of remotely sensed imagery

Abstract

Bibliographical note

Other keywords

Access to Document

Fingerprint

Cite this