Multilayer Markov Random Field models for change detection in optical remote sensing images

Csaba Benedek, Maha Shadaydeh, Z. Kato, T. Szirányi, Josiane Zerubia

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

In this paper, we give a comparative study on three Multilayer Markov Random Field (MRF) based solutions proposed for change detection in optical remote sensing images, called Multicue MRF, Conditional Mixed Markov model, and Fusion MRF. Our purposes are twofold. On one hand, we highlight the significance of the focused model family and we set them against various state-of-the-art approaches through a thematic analysis and quantitative tests. We discuss the advantages and drawbacks of class comparison vs. direct approaches, usage of training data, various targeted application fields and different ways of Ground Truth generation, meantime informing the Reader in which roles the Multilayer MRFs can be efficiently applied. On the other hand we also emphasize the differences between the three focused models at various levels, considering the model structures, feature extraction, layer interpretation, change concept definition, parameter tuning and performance. We provide qualitative and quantitative comparison results using principally a publicly available change detection database which contains aerial image pairs and Ground Truth change masks. We conclude that the discussed models are competitive against alternative state-of-the-art solutions, if one uses them as pre-processing filters in multitemporal optical image analysis. In addition, they cover together a large range of applications, considering the different usage options of the three approaches.

Original languageEnglish
Pages (from-to)22-37
Number of pages16
JournalISPRS Journal of Photogrammetry and Remote Sensing
Volume107
DOIs
Publication statusPublished - Sep 1 2015

Fingerprint

change detection
remote sensing
Remote sensing
Multilayers
ground truth
Antenna grounds
Model structures
Image analysis
Feature extraction
Masks
readers
preprocessing
image analysis
Fusion reactions
Tuning
pattern recognition
Antennas
comparative study
education
masks

Keywords

  • Change detection
  • Fusion MRF
  • Mixed Markov models
  • Multilayer MRF

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Computers in Earth Sciences
  • Engineering (miscellaneous)
  • Geography, Planning and Development
  • Computer Science Applications

Cite this

Multilayer Markov Random Field models for change detection in optical remote sensing images. / Benedek, Csaba; Shadaydeh, Maha; Kato, Z.; Szirányi, T.; Zerubia, Josiane.

In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 107, 01.09.2015, p. 22-37.

Research output: Contribution to journalArticle

@article{9008f34c41b44b968aba401fa139e5d4,
title = "Multilayer Markov Random Field models for change detection in optical remote sensing images",
abstract = "In this paper, we give a comparative study on three Multilayer Markov Random Field (MRF) based solutions proposed for change detection in optical remote sensing images, called Multicue MRF, Conditional Mixed Markov model, and Fusion MRF. Our purposes are twofold. On one hand, we highlight the significance of the focused model family and we set them against various state-of-the-art approaches through a thematic analysis and quantitative tests. We discuss the advantages and drawbacks of class comparison vs. direct approaches, usage of training data, various targeted application fields and different ways of Ground Truth generation, meantime informing the Reader in which roles the Multilayer MRFs can be efficiently applied. On the other hand we also emphasize the differences between the three focused models at various levels, considering the model structures, feature extraction, layer interpretation, change concept definition, parameter tuning and performance. We provide qualitative and quantitative comparison results using principally a publicly available change detection database which contains aerial image pairs and Ground Truth change masks. We conclude that the discussed models are competitive against alternative state-of-the-art solutions, if one uses them as pre-processing filters in multitemporal optical image analysis. In addition, they cover together a large range of applications, considering the different usage options of the three approaches.",
keywords = "Change detection, Fusion MRF, Mixed Markov models, Multilayer MRF",
author = "Csaba Benedek and Maha Shadaydeh and Z. Kato and T. Szir{\'a}nyi and Josiane Zerubia",
year = "2015",
month = "9",
day = "1",
doi = "10.1016/j.isprsjprs.2015.02.006",
language = "English",
volume = "107",
pages = "22--37",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier",

}

TY - JOUR

T1 - Multilayer Markov Random Field models for change detection in optical remote sensing images

AU - Benedek, Csaba

AU - Shadaydeh, Maha

AU - Kato, Z.

AU - Szirányi, T.

AU - Zerubia, Josiane

PY - 2015/9/1

Y1 - 2015/9/1

N2 - In this paper, we give a comparative study on three Multilayer Markov Random Field (MRF) based solutions proposed for change detection in optical remote sensing images, called Multicue MRF, Conditional Mixed Markov model, and Fusion MRF. Our purposes are twofold. On one hand, we highlight the significance of the focused model family and we set them against various state-of-the-art approaches through a thematic analysis and quantitative tests. We discuss the advantages and drawbacks of class comparison vs. direct approaches, usage of training data, various targeted application fields and different ways of Ground Truth generation, meantime informing the Reader in which roles the Multilayer MRFs can be efficiently applied. On the other hand we also emphasize the differences between the three focused models at various levels, considering the model structures, feature extraction, layer interpretation, change concept definition, parameter tuning and performance. We provide qualitative and quantitative comparison results using principally a publicly available change detection database which contains aerial image pairs and Ground Truth change masks. We conclude that the discussed models are competitive against alternative state-of-the-art solutions, if one uses them as pre-processing filters in multitemporal optical image analysis. In addition, they cover together a large range of applications, considering the different usage options of the three approaches.

AB - In this paper, we give a comparative study on three Multilayer Markov Random Field (MRF) based solutions proposed for change detection in optical remote sensing images, called Multicue MRF, Conditional Mixed Markov model, and Fusion MRF. Our purposes are twofold. On one hand, we highlight the significance of the focused model family and we set them against various state-of-the-art approaches through a thematic analysis and quantitative tests. We discuss the advantages and drawbacks of class comparison vs. direct approaches, usage of training data, various targeted application fields and different ways of Ground Truth generation, meantime informing the Reader in which roles the Multilayer MRFs can be efficiently applied. On the other hand we also emphasize the differences between the three focused models at various levels, considering the model structures, feature extraction, layer interpretation, change concept definition, parameter tuning and performance. We provide qualitative and quantitative comparison results using principally a publicly available change detection database which contains aerial image pairs and Ground Truth change masks. We conclude that the discussed models are competitive against alternative state-of-the-art solutions, if one uses them as pre-processing filters in multitemporal optical image analysis. In addition, they cover together a large range of applications, considering the different usage options of the three approaches.

KW - Change detection

KW - Fusion MRF

KW - Mixed Markov models

KW - Multilayer MRF

UR - http://www.scopus.com/inward/record.url?scp=84938743017&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938743017&partnerID=8YFLogxK

U2 - 10.1016/j.isprsjprs.2015.02.006

DO - 10.1016/j.isprsjprs.2015.02.006

M3 - Article

AN - SCOPUS:84938743017

VL - 107

SP - 22

EP - 37

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

ER -