Change detection of remotely sensed image using NDVI subtractive and classification methods.

Abstract

Change detection is a technology ascertaining the changes of specific features within a certain time Interval. The use of remotely sensed image to detect changes in land use and land cover is widely preferred over other conventional survey techniques because this method is very efficient for assessing the change or degrading trends of a region. In this research two remotely sensed image of Baghdad city gathered by landsat -7and landsat-8 ETM+ for two time period 2000 and 2014 have been used to detect the most important changes. Registration and rectification the two original imagesare the first preprocessing steps was applied in this paper. Change detection using NDVI subtractive has been computed, subtractive between the bands of the two images and the ratio of the red to blue bands was also computed. Change detection mask using minimum distance classification or detection after classification have be also used to compute the changes between the resultant classes, many statistical properties of the original and process image have been illustrated in this research