CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2012 vol.34 Issue No.10 - Oct.

Subscribe

Issue No.10 - Oct. (2012 vol.34)

pp: 2046-2057

Regis C. Pinheiro Marques , Federal University of Ceara, Fortaleza

Fátima N. Medeiros , Federal University of Ceara, Fortaleza

Juvencio Santos Nobre , Federal University of Ceara, Fortaleza

ABSTRACT

This paper proposes an image segmentation method for synthetic aperture radar (SAR), exploring statistical properties of SAR data to characterize image regions. We consider {\cal G}_A^0 distribution parameters for SAR image segmentation, combined to the level set framework. The {\cal G}_A^0 distribution belongs to a class of {\cal G} distributions that have been successfully used to model different regions in amplitude SAR images for data modeling purpose. Such statistical data model is fundamental to deriving the energy functional to perform region mapping, which is input into our level set propagation numerical scheme that splits SAR images into homogeneous, heterogeneous, and extremely heterogeneous regions. Moreover, we introduce an assessment procedure based on stochastic distance and the {\cal G}_A^0 model to quantify the robustness and accuracy of our approach. Our results demonstrate the accuracy of the algorithms regarding experiments on synthetic and real SAR data.

INDEX TERMS

Level set, Image segmentation, Mathematical model, Data models, Equations, Synthetic aperture radar, Speckle, G-amplitude zero distribution., Speckle, SAR image, segmentation, level sets, energy functional

CITATION

Regis C. Pinheiro Marques, Fátima N. Medeiros, Juvencio Santos Nobre, "SAR Image Segmentation Based on Level Set Approach and {\cal G}_A^0 Model",

*IEEE Transactions on Pattern Analysis & Machine Intelligence*, vol.34, no. 10, pp. 2046-2057, Oct. 2012, doi:10.1109/TPAMI.2011.274REFERENCES