Log-Euclidean distance based superpixel segmentation for PolSAR images

Hongyan Kang, Yue Zhang, Huanxin Zou, Tiancheng Luo
2016 Proceedings of the 2016 5th International Conference on Measurement, Instrumentation and Automation (ICMIA 2016)   unpublished
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
more » ... nt 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.
doi:10.2991/icmia-16.2016.71 fatcat:t4yrms5mrnf4flnokw4olgfvlq