The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XL-1/W5
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-1/W5, 407–410, 2015
https://doi.org/10.5194/isprsarchives-XL-1-W5-407-2015
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-1/W5, 407–410, 2015
https://doi.org/10.5194/isprsarchives-XL-1-W5-407-2015

  11 Dec 2015

11 Dec 2015

UNSUPERVISED CHANGE DETECTION IN SAR IMAGES USING GAUSSIAN MIXTURE MODELS

E. Kiana1, S. Homayouni2, M. A. Sharifi1, and M. Farid-Rohani3 E. Kiana et al.
  • 1School of Surveying and Geospatial Engineering, Dept. of Remote Sensing, College of Engineering, U. of Tehran, Tehran, Iran
  • 2Dept. of Geography, Environmental Studies and Geomatics, U. of Ottawa, Ottawa, Canada
  • 3Faculty of mathematical Sciences, Dept. of Statistics, University of Shahid Beheshti, Tehran, Iran

Keywords: Gaussian Mixture model, Change Detection, SAR images, Difference image, Multi-temporal Images

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.