The aim of this letter is to provide a novel method connecting statistical optimization and information geometry for ship detection in synthetic aperture radar (SAR) imagery. The method consists of two steps: initial detection and iterative optimization. For the first stage, the Weibull clutter model is used for initial detection. For the second step, the metric tensor of the Weibull distribution manifold is constructed for iterative optimization. Experiments show that the proposed method is effective in reducing false alarms and obtains a satisfactory detection performance.
2. Gao, G., Characterization of SAR Clutter and Its Applications to Land and Ocean Observations, Springer, Singapore, 2019.
3. Yang, M. and G. Zhang, "A novel ship detection method for SAR images based on nonlinear diffusion filtering and Gaussian curvature," Remote Sens. Lett., Vol. 7, No. 3, 211-219, 2016.
4. Arwini, K. A. and C. T. J. Dodson, Information Geometry --- Near Randomness and Near Independence, Springer-Verlag, Berlin, Heidelberg, Germany, 2008.
5. Cao, L., H. Sun, and X. Wang, "The geometric structures of the Weibull distribution manifold and the generalized exponential distribution manifold," Tamkang J. Math., Vol. 39, No. 1, 45-51, 2008.
6. Forbes, C., M. Evans, N. Hastings, and B. Peacock, Statistical Distributions, John Weiley & Sons, New Jersey, USA, 2011.
7. Gao, G., S. Gao, J. He, and G. Li, "Ship detection using compact polarimetric SAR based on the notch filter," IEEE Trans. Geosci. Remote Sens., Vol. 56, No. 9, 5380-5393, 2018.
8. Yang, M. and C. Guo, "Ship detection in SAR images based on lognormal ρ-metric," IEEE Geosci. Remote Sens. Lett., Vol. 15, No. 9, 1372-1376, 2018.