[Abstract] Markovian Framework for Structural...

来源:百度文库 编辑:神马文学网 时间:2024/04/29 02:25:39

•Home•Login•My Cart•Reviewers Only•FAQ•Careers•Contact•
Find/Buy ArticlesJournalsProceedingsSubscriptionsSubmissionsCall for Papers
Games-Based LearningTechnology for Collaborative Learning
Publication Search:
advanced search

Publishing Services
Markovian Framework for Structural Change Detection with Application on Detecting Built-In Changes in Airborne Images
C. Benedek and T. Szirányi (Hungary)
Keywords
Change detection, MRF.
Abstract
In the paper we address the problem of change detection in airborne image pairs taken with significant time differ ence. In reconnaissance and exploration tasks, finding the slowly changing areas through a long tract of time is dis turbed 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 pic tures, ensuring to get smooth connected regions in the seg mented images, and also in the change mask. The domain dependent part of the model is separated, therefore the pro posed structure can be used for significantly different de scriptors and problems also.
From Proceeding(554) Signal Processing, Pattern Recognition, and Applications - 2007
Go Back

Privacy & LegalSitemapCopyright © 2007 ACTA Press