Urban Classification Using Multi-temporal Sentinel-1 Data Based On Coherence Characteristics

Abstract

Classification urban features plays an important part in monitoring and development planning of the area. Optical remote sensing data is currently used in study land use/land cover. However, optical remote sensing data are affected by clouds and weather. Hence, it is difficult to update information. Sentinel-1 is the satellite mission which conducted by the European Space Agency (ESA). Sentinel-1 is composed of two satellites, Sentinel-1A and Sentinel-1B which carried C-band Synthetic Aperture Radar (SAR) instrument, 10m spatial resolution and provided free of charge. SAR images, which is an active microwave data, is not affected by weather, day and night. In this article, the authors present the experimental results of using coherence technique of two SAR images acquised at different times to classify urban features. The classification accuracy by using VV and VH polarization images were respectively 89% and 93%. VH polarization image data used in classification urban feature is better than VV polarization image.