Segmentation of remote sensing images using similarity-measure-based fusion-MRF model

T. Szirányi, Maha Shadaydeh

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Classifying segments and detecting changes in terrestrial areas are important and time-consuming efforts for remote sensing image analysis tasks, including comparison and retrieval in repositories containing multitemporal remote image samples for the same area in very different quality and details. We propose a multilayer fusion model for adaptive segmentation and change detection of optical remote sensing image series, where trajectory analysis or direct comparison is not applicable. Our method applies unsupervised or partly supervised clustering on a fused-image series by using cross-layer similarity measure, followed by multilayer Markov random field segmentation. The resulted label map is applied for the automatic training of single layers. After the segmentation of each single layer separately, changes are detected between single label maps. The significant benefit of the proposed method has been numerically validated on remotely sensed image series with ground-truth data.

Original languageEnglish
Article number6730687
Pages (from-to)1544-1548
Number of pages5
JournalIEEE Geoscience and Remote Sensing Letters
Volume11
Issue number9
DOIs
Publication statusPublished - 2014

Fingerprint

segmentation
Labels
Remote sensing
Multilayers
Fusion reactions
remote sensing
Image analysis
Trajectories
repository
image analysis
trajectory
comparison
method

Keywords

  • Change detection
  • cluster reward algorithm
  • fusion-Markov random field (MRF)
  • image segmentation
  • remote sensing
  • similarity measure

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Geotechnical Engineering and Engineering Geology

Cite this

Segmentation of remote sensing images using similarity-measure-based fusion-MRF model. / Szirányi, T.; Shadaydeh, Maha.

In: IEEE Geoscience and Remote Sensing Letters, Vol. 11, No. 9, 6730687, 2014, p. 1544-1548.

Research output: Contribution to journalArticle

@article{b677cf4deccd4d3abddc3143e0fe0a1d,
title = "Segmentation of remote sensing images using similarity-measure-based fusion-MRF model",
abstract = "Classifying segments and detecting changes in terrestrial areas are important and time-consuming efforts for remote sensing image analysis tasks, including comparison and retrieval in repositories containing multitemporal remote image samples for the same area in very different quality and details. We propose a multilayer fusion model for adaptive segmentation and change detection of optical remote sensing image series, where trajectory analysis or direct comparison is not applicable. Our method applies unsupervised or partly supervised clustering on a fused-image series by using cross-layer similarity measure, followed by multilayer Markov random field segmentation. The resulted label map is applied for the automatic training of single layers. After the segmentation of each single layer separately, changes are detected between single label maps. The significant benefit of the proposed method has been numerically validated on remotely sensed image series with ground-truth data.",
keywords = "Change detection, cluster reward algorithm, fusion-Markov random field (MRF), image segmentation, remote sensing, similarity measure",
author = "T. Szir{\'a}nyi and Maha Shadaydeh",
year = "2014",
doi = "10.1109/LGRS.2014.2300873",
language = "English",
volume = "11",
pages = "1544--1548",
journal = "IEEE Geoscience and Remote Sensing Letters",
issn = "1545-598X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "9",

}

TY - JOUR

T1 - Segmentation of remote sensing images using similarity-measure-based fusion-MRF model

AU - Szirányi, T.

AU - Shadaydeh, Maha

PY - 2014

Y1 - 2014

N2 - Classifying segments and detecting changes in terrestrial areas are important and time-consuming efforts for remote sensing image analysis tasks, including comparison and retrieval in repositories containing multitemporal remote image samples for the same area in very different quality and details. We propose a multilayer fusion model for adaptive segmentation and change detection of optical remote sensing image series, where trajectory analysis or direct comparison is not applicable. Our method applies unsupervised or partly supervised clustering on a fused-image series by using cross-layer similarity measure, followed by multilayer Markov random field segmentation. The resulted label map is applied for the automatic training of single layers. After the segmentation of each single layer separately, changes are detected between single label maps. The significant benefit of the proposed method has been numerically validated on remotely sensed image series with ground-truth data.

AB - Classifying segments and detecting changes in terrestrial areas are important and time-consuming efforts for remote sensing image analysis tasks, including comparison and retrieval in repositories containing multitemporal remote image samples for the same area in very different quality and details. We propose a multilayer fusion model for adaptive segmentation and change detection of optical remote sensing image series, where trajectory analysis or direct comparison is not applicable. Our method applies unsupervised or partly supervised clustering on a fused-image series by using cross-layer similarity measure, followed by multilayer Markov random field segmentation. The resulted label map is applied for the automatic training of single layers. After the segmentation of each single layer separately, changes are detected between single label maps. The significant benefit of the proposed method has been numerically validated on remotely sensed image series with ground-truth data.

KW - Change detection

KW - cluster reward algorithm

KW - fusion-Markov random field (MRF)

KW - image segmentation

KW - remote sensing

KW - similarity measure

UR - http://www.scopus.com/inward/record.url?scp=84897110739&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897110739&partnerID=8YFLogxK

U2 - 10.1109/LGRS.2014.2300873

DO - 10.1109/LGRS.2014.2300873

M3 - Article

AN - SCOPUS:84897110739

VL - 11

SP - 1544

EP - 1548

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

SN - 1545-598X

IS - 9

M1 - 6730687

ER -