Urban extraction based on the Machine learning and the eigenvalue/eigenvector PolSAR decomposition

This work shows the current approaches to recognize and locate urban land-uses and understand the complex urban environment for sustainable urban systems using machine learning methods and the most physical scattering mechanism-based polarimetric decomposition models. This paper intends to identify the urban area from polarimetric Synthetic aperture radar (PolSAR) data using the CNN model.This model has shown its effectiveness in classification. For this purpose, we propose to use a feature vector that contains the elements of the 6 real elements extracted from the coherency matrix and the three physical descriptors (entropy, alpha angle and anisotropy) from the eigenvalue/eingenvector decomposition. The used elements are roll invariants, which make them not sensitive to the orientation angle, which can create ambiguity between oriented buildings and vegetation. To test the performance of the proposed method, ALOS-2/PALSAR-2L-band over the San-Francisco, USA were used. The results show that man-made targets could be effectively discriminated from natural scenes using the proposed method.