Abstract Views :191 |
PDF Views:0
Authors
Affiliations
1 Department of Computer Science & Engineering, Vidya College of Engineering, Meerut, IN
2 Department of Civil Engineering, Indian Institute of Technology, Roorkee (IITR), IN
3 Department of Computer Science, Gurukul Kangri Vishwavidyalaya, Haridwar, IN
Source
Oriental Journal of Computer Science and Technology, Vol 3, No 1 (2010), Pagination: 13-20
Abstract
In the present study Multispectral Image Processing (MIP) technique is applied on ASTER (Advance Spaceborne Thermal Emission and Reflection Radiometer) L1 B high resolution (15 m/ pixel) satellite data. A comprehensive spectral library of rice crop varieties : Hybrid-6129 (IET 18815), Pant Dhan-19 (IET 17544), Pusa Basmati-1 (IET-18990) and Pant Dhan-18 (IET-17920) has been developed with Blue (0.56 nm), Red (0.66 nm) and NIR (0.81 nm) spectral bands. The PCA (Principal Component Analysis) transformation with correlation matrix is applied for feature extraction to select an optimum subset of data in term of classification accuracy. Four PC (Principal Component) images selected for conventional spectral and integrated image classification. The integrated image Spectral/ NDVI (Normalized Difference Vegetation Index) is developed using Spectral and NDVI bands classified using ML (Maximum Likelihood) classifier. The conventional spectral classification accuracy for rice mapping is 79.5%, which improves up to 84.5% with Spectra/NDVI imagery data.
Keywords
Multispectral Image Processing (MIP), NDVI, PCA and ML (Maximum Likelihood).
Full Text
