Investigating the Performance of Sar Polarimetric Features in Land-cover Classification

This paper represents a study on land-cover classification using different polarimetric SAR features. The experiment is carried out using Cand L-band fully polarimetric EMISAR data acquired on July 5 and 6, 1995 over an agricultural area in Fjärdhundra, near Uppsala, Sweden. The polarimetric features investigated are coherency matrix, intensity of both Cand L-band SAR, and Cloud decomposition product H(1-A) of L-band, and ‘entropy’ texture of L-band HV intensity image. In order to investigate the performance of the different features, each feature is classified using a classifier that is best suited for the feature based on previous research. H/A/α Wishart unsupervised classification is used for coherency matrix while neural network is applied to six “mean” texture layers of C and L bands fully polarimetric intensity images. The best classification accuracy was achieved using the intensity images combined with H(1-A) and ‘entropy’ texture (overall: 81%; kappa: 0.7). The producer’s accuracy of intensity classification result for forest is 100.0% which reveals that the H(1-A) of L-band is a very good indicator for forest. The ’entropy’ texture of L-band HV intensity image has the potential to be a good indicator for road with 77.2% user accuracy, while road is not discriminated in coherency matrix. The results indicate that the supervised classification of the intensity of both Cand Lbands has a good potential for land-cover mapping in this study area.