Share Email Print

Proceedings Paper

A new approach to texture segmentation of remote sensing image based on MRF and particle swarm optimization algorithm
Author(s): Huazhong Jin; Zequn Guan; Benlin Xiao; Bubin Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, a new texture segmentation approach based on Markov random field (MRF) and global optimal method of particle swarm optimization (PSO) is proposed. According to this approach, firstly the MRF texture model is established, and potential function of Gibbs distribution and the calculating method of Gibbs parameters are represented. Then the fitness function is designed and the PSO is adopted here to solve the maximum a posterior (MAP) estimate. Finally, a comparison of the new algorithm with the Metropolis algorithm and the Gibbs Sampler is made in texture segmentation of remote sensing images. Results show that PSO algorithm can reduce the computational complexity and is much more efficient.

Paper Details

Date Published: 29 December 2008
PDF: 10 pages
Proc. SPIE 7285, International Conference on Earth Observation Data Processing and Analysis (ICEODPA), 72851K (29 December 2008); doi: 10.1117/12.815864
Show Author Affiliations
Huazhong Jin, Wuhan Univ. (China)
Hubei Univ. of Technology (China)
Zequn Guan, Wuhan Univ. (China)
Benlin Xiao, Hubei Univ. of Technology (China)
Bubin Zhang, Wuhan Univ. (China)

Published in SPIE Proceedings Vol. 7285:
International Conference on Earth Observation Data Processing and Analysis (ICEODPA)
Deren Li; Jianya Gong; Huayi Wu, Editor(s)

© SPIE. Terms of Use
Back to Top