Title :
PolSAR Ship Detection Based on Superpixel-Level Scattering Mechanism Distribution Features
Author :
Yinghua Wang ; Hongwei Liu
Author_Institution :
Nat. Lab. of Radar Signal Process., Xidian Univ., Xi´an, China
Abstract :
To improve the target detection performance under a low signal-to-clutter ratio, this letter presents a new polarimetric synthetic aperture radar (PolSAR) ship detector based on superpixel-level scattering mechanism (SM) distribution features. The proposed method is based on the observation that the SMs of targets and clutter have different distributions in the classical H/α plane. To make use of this difference in ship detection, multiscale superpixels are first generated for PolSAR images. Then, two features describing the SM distribution in the superpixel are proposed. Based on these features, a test statistic independent of the scattering intensity is finally defined. The performance improvement of the proposed method is verified using a synthetic data set and real PolSAR images obtained from a RADARSAT-2 data set.
Keywords :
object detection; radar clutter; radar detection; radar imaging; radar polarimetry; ships; statistical analysis; synthetic aperture radar; PolSAR imaging; PolSAR ship detection; RADARSAT-2 data set; SM; classical H-α plane; multiscale superpixel; polarimetric synthetic aperture radar; signal-to-clutter ratio; superpixel-level scattering mechanism distribution feature; target detection performance; Clutter; Detectors; Feature extraction; Marine vehicles; Scattering; Synthetic aperture radar; Thyristors; Polarimetric synthetic aperture radar (PolSAR); scattering mechanism (SM); ship detection; signal-to-clutter ratio (SCR); superpixel;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2015.2425873