30 October 2009 A novel algorithm for ship detection based on fusion of split-look SAR images
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 749538 (2009) https://doi.org/10.1117/12.833474
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
The traditional approach of ship detection is to apply CFAR technique to the statistical property of the sea clutter, one of the main problems is that lots of false alarms will be detected when the TCR(Target-to-Clutter Ratio) is not high enough. The objective of this paper is to apply the split-look analysis technique to the ship detection, and the polarization filter techniques are used on split-look images to generate fused images which have higher TCR and less speckle. By deducing the distribution models of the sea clutter in fused images, CFAR detection can be utilized to distinguish the ship targets. The technique is tested in one ERS-2 and three ALOS-PALSAR images, the previous analyses of the detection of ships are demonstrated. The ship targets in the experimental SAR data can be identified by the naked eye, and the effect of the technique wasn't fully represented, thus further experiments should be carried out for extreme situations-nearly invisible ship targets embedded in the sea clutter.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hong-zhong Li, Chao Wang, Hong Zhang, "A novel algorithm for ship detection based on fusion of split-look SAR images", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749538 (30 October 2009); doi: 10.1117/12.833474; https://doi.org/10.1117/12.833474
PROCEEDINGS
8 PAGES


SHARE
Back to Top