A level set method for oil slick segmentation in SAR images

Abstract

Despite much effort and significant progress in recent years, image segmentation remains a challenging problem in image processing, especially for the low contrast, noisy synthetic aperture radar (SAR) images. This paper explores the segmentation of oil slicks using a partial differential equation (PDE)-based level set method, which represents the slick surface as an implicit propagation interface. Starting from an initial estimation with priori information, the level set method creates a set of speed functions to detect the position of the propagation interface. Specifically, the image intensity gradient and the curvature flow are utilized together to determine the speed and direction of the propagation. This allows the front interface to propagate naturally with topological changes, significant protrusions and narrow regions, giving rise to stable and smooth boundaries that discriminate oil slicks from the surrounding water. As the speckles are removed concurrently while the front interface propagates, the prefiltering of noise is saved. The proposed method has been illustrated by experiments on oil slick segmentation using the ERS-2 SAR images. Its advantages over the traditional image segmentation approaches have also been demonstrated.

Land Surface Water Mapping Using Multi-Scale Level Sets and a Visual Saliency Model from SAR Images

“…(1) Initialize the level set function using Equation (15); (2) Evolve the level set function φ according to Equations (13) and (14); (3) Check whether the evolution is stationary. If not, return to Step 2.…”

Dark-spot detection from SAR intensity imagery with spatial density thresholding for oil-spill monitoring

“…The dark spot detection from SAR imagery is in fact a segmentation problem, aiming to partition a SAR image into dark spots and the background. Several methods based on various segmentation techniques have been proposed for dark spot detection, including thresholding, region growing, level set segmentation, and so on (Huang et al, 2005;Karanthanassi, 2006;Solberg, 2007).…”

“…Interested readers are referred to (Osher & Fedkiw 2002) for the detail explanation. Huang et al (2005) detected dark spots by using a partial differential equation (PDE)-based level set method. Starting from an initial curve generated by threshold segmentation, the level set function is propagated under the control of the speed function which is determined by both the image intensity gradient and the curvature flow.…”

Target Detection in SAR Images Based on a Level Set Approach

“…Several applications in shape analysis and pattern recognition require robust segmentation methods, which have clear implications on the success of posterior analysis. An important application is target detection in SAR (Synthetic Aperture Radar) images, which has motivated several publications as in [1,2,3,4,5,6].…”

“…Such techniques have been applied mainly in optical images [13,14,15,16,17], but Huang et. al [2] developed a level set formulation for oil slick segmentation in SAR images. This method integrates models of intensity and curvature to determine the intensity gradient-driven and curvature driven front propagation speed.…”