PolSAR Ship Detection Based on Neighborhood Polarimetric Covariance Matrix

The detection of small ships in polarimetric synthetic aperture radar (PolSAR) images is still a topic for further investigation. Recently, patch techniques, such as superpixel-level detection, have stimulated wide interest because they can use the information contained similarities among neighboring pixels. In this article, we propose novel neighborhood covariance matrix (NPCM) to detect PolSAR images, leading significant improvement separability between ship targets and sea clutter. NPCM utilizes spatial correlation pixels maps representation given pixel into high-dimensional by embedding polarization information. Using formalism, apply standard whitening filter, similar filter (PWF). We show how inclusion improves performance compared with traditional matrix. However, at expense higher computation cost. theory validated via simulated measured data under different states using platforms.