Log-Euclidean distance based superpixel segmentation for PolSAR images

DOI

10.2991/icmia-16.2016.71How to use a DOI?

Keywords

SLIC, polarimetric synthetic aperture radar, Log-Euclidean distance, Postprocessing

Abstract

The simple linear iterative clustering (SLIC) method is a popular recently proposed superpixel algorithm for its simpleness and good performance for optical images. However, it may provide poor superpixels for polarimetric synthetic aperture radar (PolSAR) images because of the inherent speckle noise. In this paper, an improved SLIC based on Log-Euclidean distance with a novel postprocessing procedure by iteratively merging similar superpixels as well as preserving strong point targets is proposed. Experiments on a real image from ESAR demonstrate its superiority over two state-of-the-art algorithms, i.e., SLIC-GC and standard SLIC.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hongyan Kang
AU  - Yue Zhang
AU  - Huanxin Zou
AU  - Tiancheng Luo
PY  - 2016/11
DA  - 2016/11
TI  - Log-Euclidean distance based superpixel segmentation for PolSAR images
BT  - Proceedings of the 2016 5th International Conference on Measurement, Instrumentation and Automation (ICMIA 2016)
PB  - Atlantis Press
SP  - 397
EP  - 400
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmia-16.2016.71
DO  - 10.2991/icmia-16.2016.71
ID  - Kang2016/11
ER  -