Multiscale Markov Random Field Method for SAR Image Segmentation

Author

Zhang, Jian-Guang ; Wen, Xian-Bin ; Jiao, Xu ; Wang, Lei

Author_Institution

Key Lab. of Comput. Vision & Syst., Tianjin Univ. of Technol., Tianjin, China

fYear

2009

fDate

17-19 Oct. 2009

Firstpage

1

Lastpage

5

Abstract

In this paper, a multiscale Markov random field method for segmentation of the synthetic aperture radar (SAR) images is proposed. A classifier which inherits the strongpoint of the Markov random field (MRF) and the multiscale autoregressive (MAR) model is designed. The MAR models are utilized to extract the multiscale feature of SAR image, which is used to train the MRF with the proposed algorithm, and then the SAR images is segmented by the trained random field. The experimental result demonstrates the effectiveness and efficiency of the proposed method.

Keywords

Markov processes; autoregressive processes; image segmentation; radar imaging; synthetic aperture radar; Markov random field; image segmentation; multiscale autoregressive model; synthetic aperture radar; Computer vision; Educational technology; Image resolution; Image segmentation; Laboratories; Markov random fields; Signal resolution; Speckle; Stochastic processes; Synthetic aperture radar;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing, 2009. CISP '09. 2nd International Congress on

Conference_Location

Tianjin

Print_ISBN

978-1-4244-4129-7

Electronic_ISBN

978-1-4244-4131-0

Type

conf

DOI

10.1109/CISP.2009.5301448

Filename

5301448