Pixel Purity Index Algorithm and N-Dimensional Visualization For ETM+ Image Analysis: A Case of District Vehari
The hyperspectral image analysis technique, one of the most advanced remote sensing tools, has been used as a possible means of identifying from a single pixel or in the field of view of the sensor. An important problem in hyperspectral image processing is to decompose the mixed pixels into the information that contribute to the pixel, endmember, and a set of corresponding fractions of the spectral signature in the pixel, abundances, and this problem is known as un-mixing. The effectiveness of the hyperspectral image analysis technique used in this study lies in their ability to compare a pixel spectrum with the spectra of known pure vegetation, extracted from the spectral endmember selection procedures, including the reflectance calibration of Landsat ETM+ image using ENVI software, minimum noise fraction (MNF), pixel purity index (PPI), and n-dimensional visualization. The Endmember extraction is one of the most fundamental and crucial tasks in hyperspectral data exploitation, an ultimate goal of an endmember extraction algorithm is to find the purest form of spectrally distinct resource information of a scene. The endmember extraction tendency to the type of endmembers being derived, and the number of endmembers, estimated by an algorithm, with respect to the number of spectral bands, and the number of pixels being processed, also the required input data, and the kind of noise, if any, in the signal model surveying done. Results of the present study using the hyperspectral image analysis technique ascertain that Landsat ETM+ data can be used to generate valuable vegetative information for the District Vehari, Punjab Province, Pakistan.
