Segmentation of synthetic aperture radar image using multiscale information measure-based spectral clustering

徐海霞 徐海霞, Haixia Xu, 田铮 田铮, 丁明涛 丁明涛, Zheng Tian, and Mingtao Ding and Mingtao DingChinese 2008 · DOI

Abstract

A multiscale information measure (MIM), calculable from per-pixel wavelet coefficients, but relying on global statistics of synthetic aperture radar (SAR) image, is proposed. It fully exploits the variations in speckle pattern when the image resolution varies from course to fine, thus it can capture the intrinsic texture of the scene backscatter and the texture due to speckle simultaneously. Graph spectral segmentation methods based on MIM and the usual similarity measure are carried out on two real SAR images. Experimental results show that MIM can characterize texture information of SAR image more effectively than the commonly used similarity measure.
BibTeX
@inproceedings{2008segmentation,
  author = {徐海霞 徐海霞 and Haixia Xu and 田铮 田铮 and 丁明涛 丁明涛 and Zheng Tian and and Mingtao Ding and Mingtao Ding},
  title = {{Segmentation of synthetic aperture radar image using multiscale information measure-based spectral clustering}},
  booktitle = {Chinese},
  year = {2008},
  doi = {10.3788/col20080604.0248},
}

Loading related content...

Figure