Abstract
Synthetic aperture radar (SAR) has been widely used in ocean surveillance. As an important part of shipping management and military applications, ship monitoring is a study hotspot in SAR image interpretation; hence, many researches focus on ship targets. Among these studies, ship segmentation is a basic work, but still remains challenging due to the speckle noise and the complicated backscattering phenomenology in SAR images. To solve the problems, this paper proposes a new method for ship segmentation by nonlocal processing. Firstly, the proposed nonlocal energy describes the nonlocal comparison of patches and optimizes regions with spatially-varying features. Secondly, we rewrite the energy functional by introducing a ratio distance defined with respect to the probability density functions of regions to overcome the influence of the multiplicative noise. Finally, the integral histogram is introduced into the pairwise interactions to fasten the speed of convergence. Several rounds of comparative experiments are implemented on real SAR data with different resolutions and bands. The results demonstrate that the proposed method is robust to the speckle noise and intensity variations and could achieve refined segmentation for ship targets.
Highlights
Due to the capability of working under all weather and all time conditions, synthetic aperture radar (SAR) is an important tool in ocean surveillance
On the one hand, segmenting the ship from the background is necessary for extracting target features that are often used in discrimination and classification; on the other hand, the refined segmentation is the pre-processing of the training set in some deep learning-based recognition algorithms, because eliminating the interference of background clutters contributes to classification [3]
We carried out the proposed method with the parameters τ = 3, σ = 15, λ=15 and drew a comparison with the CV, region-scalable fitting (RSF), local and global intensity fitting (LGIF), local and global fuzzy Gaussian distribution (LGFGD), and global minimization of the modified LGIF (GMLGIF)
Summary
Due to the capability of working under all weather and all time conditions, synthetic aperture radar (SAR) is an important tool in ocean surveillance. Because of the great significance of ship monitoring in shipping management and military applications, many research works focusing on ship targets have been carried out, such as ship detection, discrimination, and recognition [1,2]. Among these studies, ship segmentation is a fundamental and meaningful work: The accurate segmentation can facilitate subsequent interpretations. The multiplicative speckle noise caused by SAR systems is a common
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have