A Comparative Study of Crop Classification By Using Radiometric and Photographic Data

Abstract

The aim of this study is to compare the performance of two types of remote sensing data, radiometric and photographic, obtained from five different crops; canola, radish-plants and three varieties of wheat crop (Ass, Meraj, and Bhakkar).Radiometric data was acquired by using a handheld crop scan device ‘MSR5’,in the form of five spectral bands, from 450nm to 1750nm, with five types of wavelength blue, green, red, infrared and far-infrared, whereas, photographic data was obtained by a digital camera with14.1Mpixels resolution. Both types of data were classified by using ANN classifier in MaZda software environment. It was observed that the radiometric data gave better classification results as compared to the photographic data. In training phase we received an accuracy of 94.50% and 91.43% with radiometric and photographic data respectively, and when classifier was tested it gave an accuracy of 96.00% and 93.14% respectively.