Unsupervised Change Detection in Sar Images Using Gaussian Mixture Models

Abstract

ABSTRACT:In this paper, we propose a method for unsupervised change detection in Remote Sensing Synthetic Aperture Radar (SAR) images. This method is based on the mixture modelling of the histogram of difference image. In this process, the difference image is classified into three classes; negative change class, positive change class and no change class. However the SAR images suffer from speckle noise, the proposed method is able to map the changes without speckle filtering. To evaluate the performance of this method, two dates of SAR data acquired by Uninhabited Aerial Vehicle Synthetic from an agriculture area are used. Change detection results show better efficiency when compared to the state-of-the-art methods.

Comparison of Decomposition Methods Over Agricultural Fields Using the Uavsar Polarimetric Synthetic Aperture Radar

“…The study site is the SMAPVEX12 experimental area ( Figure. 1) which covers 15 km × 70 km and is located in Winnipeg, Canada. It consists of agricultural, urban and forests areas (Kiana, Homayouni et al 2015). The landscape is characterized by an extremely flat topography, and the main crops over the agricultural area are wheat (32.2%), canola (13.2% of the area), corn (7%) and soybean (6.7%) (Wang, Magagi et al 2017).…”

“…Remote sensing technique provides a powerful way to estimate the crop biomass at several high spatial and temporal resolutions (Lu 2006). Unlike to optical images, Synthetic Aperture Radar (SAR) is independent of day time (Kiana, Homayouni et al 2015) (Carrara, Goodman et al 1995). Polarimetric decomposition was established to isolate the individual scattering mechanism (e.g.…”