Investigating various change detection techniques of land use usingRS and GIS (Case study- Sarabeleh,Ilam province)

Change detection is used to monitor anthropogenic effect such as deforestation، farming، urbanization and etc. Various change detection techniques exist. In this study، images of landsat (TM) 1988 and landsat (ETM+) 2007 were analyzed using five change detection techniques in 45803 hectares in the region of Sarabeleh،Ilam province. Change detection techniques considered were image differencing، tasscap differencing، NDVI differencing، PCA differencing and CCA differencing. In this study، from statistical method for determining the threshold levelwas used which from the change threshold was achieved. In this study،threshold level was set at ±1 standard deviation from the mean. After determining optimal threshold،areas having decreasing changes، increasing changes and no change was determined. Based on ground data and field visit and Google Earth، accuracy assessment of change detection techniques was carried out using overall accuracy and Kappa coefficient. According to the results، PCA2differencing with overall accuracy of 0. 97 and Kappa coefficient of 95% showed the highest accuracy among applied change detection techniques and on the contrary،band differencing with overall accuracy 0. 65 and Kappa coefficient of 0. 62 had lowest accuracy in land use/land cover change in study area.