Detecting Water Bodies on RADARSAT Imagery

This paper presents a novel geodesic active contour (GAC) model based on an edge detector for rapid detection of water bodies from spaceborne synthetic aperture radar (SAR) imagery with high speckle noise. The original edge indicator function based on gradients is replaced by an edge indicator function based on the ratio of exponentially weighted averages (ROEWA) operator. Thus, the capability of edge detection and the accuracy of locating edges are greatly improved, which makes the model more appropriate for SAR images. In addition, an enhancing term is added to the original model's energy function in order to boost the strength for the contour's evolution. An unconditionally stable additive operator splitting (AOS) scheme and a fast algorithm for re-initialization of the level set function are adopted, which not only enhances the model's stability, but also speeds up the model's convergence remarkably. The experimental results on simulated and real RADARSAT-1/-2 images show its efficiency and accuracy.

[1]  A. Lopes,et al.  A statistical and geometrical edge detector for SAR images , 1988 .

[2]  Florence Tupin,et al.  Unsupervised classification of radar images using hidden Markov chains and hidden Markov random fields , 2003, IEEE Trans. Geosci. Remote. Sens..

[3]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[4]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[5]  David Potter.  Computational physics , 1973 .

[6]  Shaun Quegan,et al.  Quantitative comparison of the performance of SAR segmentation algorithms , 1998, IEEE Trans. Image Process..

[7]  Michael J. Collins,et al.  On the Design and Evaluation of Multiobjective Single-Channel SAR Image Segmentation Algorithms , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Olivier Germain,et al.  Edge location in SAR images: performance of the likelihood ratio filter and accuracy improvement with an active contour approach , 2001, IEEE Trans. Image Process..

[9]  Philippe Réfrégier,et al.  Influence of the noise model on level set active contour segmentation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Jonathan Li,et al.  Shoreline Extraction from RADARSAT-2 Intensity Imagery Using a Narrow Band Level Set Segmentation Approach , 2010 .

[11]  Christophe Chesnaud,et al.  Statistical Region Snake-Based Segmentation Adapted to Different Physical Noise Models , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Max A. Viergever,et al.  Efficient and reliable schemes for nonlinear diffusion filtering , 1998, IEEE Trans. Image Process..

[13]  Alan C. Bovik,et al.  On detecting edges in speckle imagery , 1988, IEEE Trans. Acoust. Speech Signal Process..

[14]  Petros Maragos,et al.  Multigrid Geometric Active Contour Models , 2007, IEEE Transactions on Image Processing.

[15]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[16]  Philippe Marthon,et al.  An optimal multiedge detector for SAR image segmentation , 1998, IEEE Trans. Geosci. Remote. Sens..

[17]  J A Sethian,et al.  A fast marching level set method for monotonically advancing fronts. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Roman Goldenberg,et al.  Fast Geodesic Active Contours , 1999, Scale-Space.

[19]  Alan L. Yuille,et al.  Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  P Refregier,et al.  Improvement in robustness of the statistically independent region snake-based segmentation method of target-shape tracking. , 1998, Optics letters.

[21]  Jun Shen,et al.  An optimal linear operator for step edge detection , 1992, CVGIP Graph. Model. Image Process..

[22]  Laurent D. Cohen,et al.  On active contour models and balloons , 1991, CVGIP Image Underst..