The use of Spectral Reflectances of IRS Satellite Images in Differentiating Olive Orchards from Forest, Rangelands and Other Vegetations

Due to some changes which are created over time in the olive cultivated fields preparing updated map of the olive orchards is one of the most important requirements in the management region agricultural planning of the region. In this research, olive orchards were studied using IRS Satellite images in the region including some sectors of Roudbar, Manjil, Loshan and Abbar, Guilan, Iran. For this purpose, 248 land control points were studied taking into consideration the surface cover. Helping and training points of different land covers were prepared to place on a sample set of color composite (bands 1, 2 and 3). The mean and standard deviation of training and auxiliary pixels of olive orchards was calculated. Upper and lower limits of DN-olive orchards were distinguished by adding standard deviation to mean or subtracting that. In each band, olive limits were introduced to the software and slicing method was used to prepare olive map. Final map of olive fields was obtained by overlapping these three maps. The olive orchards map has been crossed by training point map to calculate the accuracy of method. The results indicate that in the classification of images with spectrum reflex statistics, more than 70% of training points had again been classified in the olive orchards class.