Detection of Object Motion Regions in Aerial Image Pairs With a Multilayer Markovian Model

Author

Benedek, Csaba ; Szirányi, Tamás ; Kato, Zoltan ; Zerubia, Josiane

Author_Institution

Distrib. Events Anal. Res. Group, Comput. & Autom. Res. Inst., Budapest, Hungary

Volume

18

Issue

10

fYear

2009

Firstpage

2303

Lastpage

2315

Abstract

We propose a new Bayesian method for detecting the regions of object displacements in aerial image pairs. We use a robust but coarse 2D image registration algorithm. Our main challenge is to eliminate the registration errors from the extracted change map. We introduce a three-layer Markov random field (L ³MRF) model which integrates information from two different features, and ensures connected homogenous regions in the segmented images. Validation is given on real aerial photos.

Keywords

Bayes methods; Markov processes; feature extraction; image motion analysis; image registration; image segmentation; object detection; random processes; Bayesian method; L3MRF model; aerial image pairs; change map; image registration; image segmentation; multilayer Markovian model; object displacement; object motion detection; real aerial photo; three-layer Markov random field; Aerial images; Markov random field (MRF); camera motion; change detection; Algorithms; Artificial Intelligence; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Markov Chains; Motion; Pattern Recognition, Automated; Photogrammetry; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique;

fLanguage

English

Journal_Title

Image Processing, IEEE Transactions on

Publisher

ieee

ISSN

1057-7149

Type

jour

DOI

10.1109/TIP.2009.2025808

Filename

5089480