USING DIGITAL PROCESSING OF SATELLITE IMAGES FOR LAND-COVER CLASSIFICATION

Z. Ali, H.

	USING DIGITAL PROCESSING OF SATELLITE IMAGES FOR LAND-COVER CLASSIFICATION
The Iraqi Journal of Agricultural Science
Article 1, Volume 43, Issue 0, 2013, Pages 119-128
Author
H. Z. Ali
Abstract
The measurement and analysis of reflectance usually used to determine the most useful bands for fea-ture discrimination and to identify features based on spectral reflectance curves. The spectral reflectance curve is different from feature to other, each feature on the earth surface have reflectance curve in spectral bands (wavelengths), and this is the signature of this feature. The aim of this research is to find the profiles of different features using ERDAS program Ver. 9.2 applied on ETM+ images for some selected regions in Iraq. This is essential in selecting training samples during supervised classification. The profiles are drawn such that we infer different classes of soil and other features within the scene. Many standard spectral libraries are available and used for comparison with the results of this research. The creation of soil spectral library is necessary. A spectral library should be representative of variability of the soils in a region. The objective of this research was to create a spectral library of distinct soils from selected regions in Iraq. A graphic representation of the spectral curve was created for each profile. The reflectance intensity of the curve was principally influenced by the levels of different components present in the samples. The use of the spectral library as an indicator of possible soil classes proved to be an important tool in profile classification. The aim of this study is to generate map of Al Najaf and its surrounding area using supervised classification method based on calculating the classes’ profiles for the purposes of land cover mapping.

Statistics Article View: 49 PDF Download: 46