Title :
Region-based L0 gradient minimization for PolSAR image segmentation
Author :
Bin Liu;Zenghui Zhang;Xingzhao Liu;Wenxian Yu
Author_Institution :
Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China
fDate :
7/1/2015 12:00:00 AM
Abstract :
In order that global, dominant, and complete outlines of land covers are delineated, in this paper, we propose a regularized L0 gradient minimization method which is specially developed for segmenting polarimetric synthetic aperture radar (PolSAR) images, and present a region-based stepwise design to implement it. The performance of the proposed method is tested and analyzed on two experimental data sets, with visual presentation as well as numerical evaluation. They both confirm that the proposed method achieves its principal goal and demonstrate its availability and advantage as a pre-processing step for PolSAR image interpretation chains.
Keywords :
"Image segmentation","Approximation methods","Synthetic aperture radar","Optimization","Minimization","Noise measurement","Covariance matrices"
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International
Electronic_ISBN :
2153-7003
DOI :
10.1109/IGARSS.2015.7326788