Fusion based enhancement techniques for hyper spectral image classification

Abstract

Remote Sensing is a technology measuring the characteristics of an object or surface from a distance. Remote Sensing image sensors can acquire various bands of the electromagnetic spectrum like visible infrared thermal and microwave wavelengths Each part of the spectrum has different characteristics and gives different information about the earths surface Reflectance of the surface of a material is its effectiveness in reflecting radiant energy which is the fraction of incident electromagnetic power Each material has a reflectance property which represents the physical and chemical state surface roughness and geometric circumstances Hyper spectral remote sensing is a new technology currently being investigated with regard to detection and identification of minerals terrestrial vegetation and man made materials and backgrounds The strength of absorption of each material in all the wavelength region is measured which depend upon the spectral coverage spectral resolution signal to noise ratio of spectrometer and abundance of the material Hyper spectral imagery is a data cube with spatial information along an XY plane and spectral information along Z axis Hyper spectral remote sensing includes large dataset and hence requires new processing methods Both hyper spectral imaging and spectroscopy are combined together in hyper spectral remote sensing newline