SAR Image Classification Combining Structural and Statistical Methods

Narcisse T. Talla, Christophe Bobda, Emmanuel TonyƩ, Janvier Fotsing, and Albert Dipanda


structural parameter, variogram, SAR image, supervised classification


The main objective of this paper is to develop a new technique of SAR image classification based on variograms. This technique combines structural parameters, including the Sill, the slope, the fractal dimension and the range, with statistical methods in a supervised image classification. Thanks to the range parameter, we define the suitable size of the image window used in the proposed approach of supervised image classification. This approach is based on a new way of characterising different classes identified on the image. The first step consists in determining relevant area of interest. The second step consists in characterising each area identified, by a matrix. The last step consists in automating the process for image classification. We apply the proposed technique with success to classify two SAR images acquired respectively on the Cameroonian littoral coast and the Mount Cameroon region. A comparative study with existing data (lithographic and topographic charts) reveals that the results of this approach are interesting.

Important Links:

Go Back