POLSAR terrain classification using deep convolutional networks

Terrain classification is one of the most important applications of the polarimetric SAR (PolSAR) data. Although many effective methods have been proposed, it is still a hot issue. This paper proposes a novel algorithm using deep convolutional networks (ConvNets) for PolSAR data classification. This algorithm is validated by AirSAR data over San Francisco and ALOS-PALSAR2 data over Shanghai Hengsha Island. The proposed approach has achieved good results in PolSAR data terrain classification. This paper also explores the influence of sliding window size on the results. Experimental results show that classification performance will be better with smaller sliding window.