Share Email Print
cover

Proceedings Paper

A novel algorithm for ship detection based on fusion of split-look SAR images
Author(s): Hong-zhong Li; Chao Wang; Hong Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 30 October 2009
PDF: 8 pages
Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749538 (30 October 2009); doi: 10.1117/12.833474
Show Author Affiliations
Hong-zhong Li, Ctr. for Earth Observation and Digital Earth (China)
Graduate Univ. of the Chinese Academy of Sciences (China)
Chao Wang, Ctr. for Earth Observation and Digital Earth (China)
Hong Zhang, Ctr. for Earth Observation and Digital Earth (China)


Published in SPIE Proceedings Vol. 7495:
MIPPR 2009: Automatic Target Recognition and Image Analysis
Tianxu Zhang; Bruce Hirsch; Zhiguo Cao; Hanqing Lu, Editor(s)

© SPIE. Terms of Use
Back to Top