Multi-feature Fusion for the Edge Tracing of PolSAR Oil Slick

The diffusion of oil slick is very fast. There are speckle noises and vague boundaries in PolSAR image of oil slick, how to distinguish and mark the continuous edges of oil slick quickly is the basic requirement of oil slick monitoring service. This paper presents a new edge tracing algorithm, which implements the edge tracing of oil slick based on multi-feature fusion. Based on the polarimetric feature analysis of the PolSAR data, an optimal feature subset is provided to distinguish the oil slick boundaries. The method, which is implemented by means of changing the resolution of PolSAR image and reducing the searching range based on the position of the adjacent boundary points, can trace and mark the continuous boundaries of oil slick quickly. We demonstrate through several examples the effectiveness of the algorithm in tracing the edge of the two scenes of PolSAR images of oil slick in Gulf of Mexico.

[1]  Eric Pottier,et al.  A review of target decomposition theorems in radar polarimetry , 1996, IEEE Trans. Geosci. Remote. Sens..

[2]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Kenneth I. Joy,et al.  Real-time optimal adaptation for planetary geometry and texture: 4-8 tile hierarchies , 2005, IEEE Transactions on Visualization and Computer Graphics.

[4]  Hiroyoshi Yamada,et al.  Four-component scattering model for polarimetric SAR image decomposition , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Pepe Siy,et al.  Effective shape contour extraction, and multiresolution representation and matching methods , 2005, IS&T/SPIE Electronic Imaging.

[6]  T. Pavlidis.  Algorithms for Graphics and Image Processing , 1981, Springer Berlin Heidelberg.

[7]  Stephen L. Durden,et al.  A three-component scattering model for polarimetric SAR data , 1998, IEEE Trans. Geosci. Remote. Sens..