Share Email Print
cover

Journal of Applied Remote Sensing

Semisupervised synthetic aperture radar image segmentation with multilayer superpixels
Author(s): Can Wang; Weimin Su; Hong Gu; Dachen Gong
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Image segmentation plays a significant role in synthetic aperture radar (SAR) image processing. However, SAR image segmentation is challenging due to speckle. We propose a semisupervised bipartite graph method for segmentation of an SAR image. First, the multilayer over-segmentation of the SAR image, referred to as superpixels, is computed using existing segmentation algorithms. Second, an unbalanced bipartite graph is constructed in which the correlation between pixels is replaced by the texture similarity between superpixels, to reduce the dimension of the edge matrix. To also improve efficiency, we define a new method, called the combination of the Manhattan distance and symmetric Kullback–Leibler divergence, to measure texture similarity. Third, by the Moore–Penrose inverse matrix and semisupervised learning, we construct an across-affinity matrix. A quantitative evaluation using SAR images shows that the new algorithm produces significantly high-quality segmentations as compared with state-of-the-art segmentation algorithms.

Paper Details

Date Published: 14 January 2015
PDF: 12 pages
J. Appl. Remote Sens. 9(1) 095098 doi: 10.1117/1.JRS.9.095098
Published in: Journal of Applied Remote Sensing Volume 9, Issue 1
Show Author Affiliations
Can Wang, Nanjing Univ. of Science and Technology (China)
Weimin Su, Nanjing Univ. of Science and Technology (China)
Hong Gu, Nanjing Univ. of Science and Technology (China)
Dachen Gong, Nanjing Univ. of Science and Technology (China)


© SPIE. Terms of Use
Back to Top