A joint multicontext and multiscale approach to Bayesian image segmentation

Author

Fan, Guoliang ; Xia, Xiang-Gen

Author_Institution

Dept. of Electr. & Comput. Eng., Delaware Univ., Newark, DE, USA

Volume

39

Issue

12

fYear

2001

fDate

12/1/2001 12:00:00 AM

Firstpage

2680

Lastpage

2688

Abstract

In this paper, a joint multicontext and multiscale (JMCMS) approach to Bayesian image segmentation is proposed. In addition to the multiscale framework, the JMCMS applies multiple context models to jointly use their distinct advantages, and we use a heuristic multistage, problem-solving technique to estimate sequential maximum a posteriori of the JMCMS. The segmentation results on both synthetic mosaics and remotely sensed images show that the proposed JMCMS improves the classification accuracy, and in particular, boundary localization and detection over the methods using a single context at comparable computational complexity

Keywords

Bayes methods; edge detection; geophysical signal processing; image classification; image segmentation; radar imaging; remote sensing; synthetic aperture radar; Bayesian image segmentation; JMCMS approach; SAR; boundary detection; boundary localization; classification accuracy; computational complexity; heuristic multistage problem-solving technique; joint multicontext and multiscale approach; multiple context models; multiscale framework; radar images; remotely sensed images; sequential maximum; synthetic mosaics; Bayesian methods; Computational complexity; Context modeling; Hidden Markov models; Image analysis; Image segmentation; Iterative algorithms; Problem-solving; Radar detection; Synthetic aperture radar;

fLanguage

English

Journal_Title

Geoscience and Remote Sensing, IEEE Transactions on

Publisher

ieee

ISSN

0196-2892

Type

jour

DOI

10.1109/36.975002

Filename

975002