Mohsen Esmail nezhad soltanloo; Mahmod Reze Sahebi
Volume 10, Issue 4 , February 2019, , Pages 121-144
Abstract
Polarimetric Interferometric SAR (POLINSAR) data by providing wealth of information containing intensity, polarimetric and interferometric measurements, have shown many capability of mentioned data in the land cover classification. These three componentes of POLINSAR data could be found independently ...
Read More
Polarimetric Interferometric SAR (POLINSAR) data by providing wealth of information containing intensity, polarimetric and interferometric measurements, have shown many capability of mentioned data in the land cover classification. These three componentes of POLINSAR data could be found independently in the Shannon entropy of POLINSAR data. These components play a complementary role in the classification where the presence of interferometric information improves the classification results. As well as the data acquired form the real world has spatial connectivity so considering the neighboring and spatial connectivity in the classification process is essential and useful. So in this paper Markov Random Field segmentation algorithm has been used for classification of Shannon Entropies of POLINSAR data. In order to provide a Markovian field for the MRF classification, an initialization method has been proposed where classifies the image into 16 classes according to the polarimetric and interferometric entropy and anisotropy and merges the clusters obtained to 8 clusters using equality test of coherency matrices. The purity indices (PI) of the clusters obtained over the POLINSAR data acquired by DLR (German Aerospace center) E-SAR have been used to evaluate the effectiveness of the Entropy based MRF classification. The proposed method has been compared with the –Wishart (), -Wishart (, -FCM ( and FCM clustering using Shannon Entropy parameters where this comparisons show approximately 28%, 11%, 17% and 20% increasing in the Purity Indices respectively.
