Maryam Imani - Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran

Polarimetric Synthetic aperture radar (PolSAR) images contain polarimetric and spatial information of materials present in the scene. Three simple architectures of convolutional neural networks (CNNs) with different dimensions are proposed for PolSAR image classification in this work. A one dimensional CNN (۱D CNN) is suggested for polarimetric feature extraction. A ۲D CNN is presented for spatial feature extraction and a ۳D CNN is introduced for polarimetric-spatial feature extraction. The performance of CNNs are compared with morphological profile of PolSAR cube when fed to the support vector machine (SVM) and random forest (RF) classifiers. The experiments are done in two cases of using ۱% and ۵% training samples. The superiority of ۳D CNN compared to other methods is shown using different quantitative classification measures.

PolSAR, classification, feature extraction, CNN