Wavelet transform based edge detection of marine oil spill image

Ocean pollution due to marine oil spill accidents occurred continually is a major environmental hazard highlighted. For this, satellite is a well-known effective tool, and especially synthetic aperture radar (SAR) can fill the lack of pollution survey which affects seas and coasts. Edge detection is an essential pre-process for marine oil spill because it involves the identification and classification of objects in an image. In order to monitor and detect oil spill automatically, this paper presents a wavelet transform based sub-pixel edge detection of marine oil spill image that exploits multiresolution characteristic of wavelet transform to extract the edges and restrain noise. Experimental results demonstrate that the proposed method is robust and effective to extract edges of SAR image.