Markovian framework for structural change detection with application on detecting built-in changes in airborne images

Csaba Benedek, T. Szirányi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In the paper we address the problem of change detection in airborne image pairs taken with significant time difference. In reconnaissance and exploration tasks, finding the slowly changing areas through a long tract of time is disturbed by the temporal parameter changes of the considered clusters. We introduce a new joint segmentation model, containing two layers corresponding to the same area of different far times and the detected change map. We tested this co-segmentation model considering two clusters on the photos: built-in and natural/cultivated areas. We propose a Bayesian segmentation framework which exploits not only the noisy class-descriptors in the independent images, but also creates links between the segmentation of the two pictures, ensuring to get smooth connected regions in the segmented images, and also in the change mask. The domain dependent part of the model is separated, therefore the proposed structure can be used for significantly different descriptors and problems also.

Original languageEnglish
Title of host publicationProceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007
Pages68-73
Number of pages6
Publication statusPublished - 2007
Event4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007 - Innsbruck, Austria
Duration: Feb 14 2007Feb 16 2007

Other

Other4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007
CountryAustria
CityInnsbruck
Period2/14/072/16/07

Fingerprint

Masks

Keywords

  • Change detection
  • MRF

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Benedek, C., & Szirányi, T. (2007). Markovian framework for structural change detection with application on detecting built-in changes in airborne images. In Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007 (pp. 68-73)

Markovian framework for structural change detection with application on detecting built-in changes in airborne images. / Benedek, Csaba; Szirányi, T.

Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007. 2007. p. 68-73.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Benedek, C & Szirányi, T 2007, Markovian framework for structural change detection with application on detecting built-in changes in airborne images. in Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007. pp. 68-73, 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007, Innsbruck, Austria, 2/14/07.
Benedek C, Szirányi T. Markovian framework for structural change detection with application on detecting built-in changes in airborne images. In Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007. 2007. p. 68-73
Benedek, Csaba ; Szirányi, T. / Markovian framework for structural change detection with application on detecting built-in changes in airborne images. Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007. 2007. pp. 68-73
@inproceedings{0486435d892c42a28ed362ea020ba436,
title = "Markovian framework for structural change detection with application on detecting built-in changes in airborne images",
abstract = "In the paper we address the problem of change detection in airborne image pairs taken with significant time difference. In reconnaissance and exploration tasks, finding the slowly changing areas through a long tract of time is disturbed by the temporal parameter changes of the considered clusters. We introduce a new joint segmentation model, containing two layers corresponding to the same area of different far times and the detected change map. We tested this co-segmentation model considering two clusters on the photos: built-in and natural/cultivated areas. We propose a Bayesian segmentation framework which exploits not only the noisy class-descriptors in the independent images, but also creates links between the segmentation of the two pictures, ensuring to get smooth connected regions in the segmented images, and also in the change mask. The domain dependent part of the model is separated, therefore the proposed structure can be used for significantly different descriptors and problems also.",
keywords = "Change detection, MRF",
author = "Csaba Benedek and T. Szir{\'a}nyi",
year = "2007",
language = "English",
isbn = "9780889866461",
pages = "68--73",
booktitle = "Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007",

}

TY - GEN

T1 - Markovian framework for structural change detection with application on detecting built-in changes in airborne images

AU - Benedek, Csaba

AU - Szirányi, T.

PY - 2007

Y1 - 2007

N2 - In the paper we address the problem of change detection in airborne image pairs taken with significant time difference. In reconnaissance and exploration tasks, finding the slowly changing areas through a long tract of time is disturbed by the temporal parameter changes of the considered clusters. We introduce a new joint segmentation model, containing two layers corresponding to the same area of different far times and the detected change map. We tested this co-segmentation model considering two clusters on the photos: built-in and natural/cultivated areas. We propose a Bayesian segmentation framework which exploits not only the noisy class-descriptors in the independent images, but also creates links between the segmentation of the two pictures, ensuring to get smooth connected regions in the segmented images, and also in the change mask. The domain dependent part of the model is separated, therefore the proposed structure can be used for significantly different descriptors and problems also.

AB - In the paper we address the problem of change detection in airborne image pairs taken with significant time difference. In reconnaissance and exploration tasks, finding the slowly changing areas through a long tract of time is disturbed by the temporal parameter changes of the considered clusters. We introduce a new joint segmentation model, containing two layers corresponding to the same area of different far times and the detected change map. We tested this co-segmentation model considering two clusters on the photos: built-in and natural/cultivated areas. We propose a Bayesian segmentation framework which exploits not only the noisy class-descriptors in the independent images, but also creates links between the segmentation of the two pictures, ensuring to get smooth connected regions in the segmented images, and also in the change mask. The domain dependent part of the model is separated, therefore the proposed structure can be used for significantly different descriptors and problems also.

KW - Change detection

KW - MRF

UR - http://www.scopus.com/inward/record.url?scp=56549108517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56549108517&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:56549108517

SN - 9780889866461

SP - 68

EP - 73

BT - Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007

ER -