by Csaba Benedek, Maha Shadaydeh, Zoltan Kato, Tamas Sziranyi, Josiane Zerubia
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.
Reference:
Csaba Benedek, Maha Shadaydeh, Zoltan Kato, Tamas Sziranyi, Josiane Zerubia, Multilayer Markov Random Field Models for Change Detection in Optical Remote Sensing Images, In ISPRS Journal of Photogrammetry and Remote Sensing, volume 107, pp. 22-37, 2015.
Bibtex Entry:
@Article{Benedek-etal2015,
author = {Csaba Benedek and Maha Shadaydeh and Zoltan Kato and
Tamas Sziranyi and Josiane Zerubia},
title = {Multilayer {M}arkov Random Field Models for Change
Detection in Optical Remote Sensing Images},
journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
year = 2015,
volume = 107,
pages = {22--37},
month = sep,
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.}
}