Ocean SAR Image Segmentation and Edge Gradient Feature Extraction

Abstract

Ma, H.-L. and Zhang, L.-Y., 2019. Ocean SAR image segmentation and edge gradient feature extraction. In: Gong, D.; Zhu, H., and Liu, R. (eds.), Selected Topics in Coastal Research: Engineering, Industry, Economy, and Sustainable Development. Journal of Coastal Research, Special Issue No. 94, pp. 141–144. Coconut Creek (Florida), ISSN 0749-0208.In order to improve the segmentation effect of synthetic aperture radar (SAR) ocean oil spill image and obtain accurate information of oil spill on ocean surface. Current image segmentation techniques are based on two properties called discontinuity and similarity based. In the segmentation based on discontinuity, image segmentation is performed based on a change in the intensity of the gray level of the image. Isolated points, edges and lines are identified primarily by methods based on discontinuities. In the similarity-based segmentation, the same points, lines and edges are identified. It contains region segmentation and merging, thresholds, and region growth.