Effectiveness of soft classification approaches as inputs for super resolution mapping of Hyperion image: a study on Peechi Reservoir, south India

Abstract

Image classification has evolved from per-pixel to sub-pixel and from sub-pixel to super resolution mapping approaches. Super-resolution mapping (SRM) is a technique which allows mapping at the sub-pixel scale. Super-resolution mapping proves to be the better approach for the accurate classification of coarse spatial resolution images and to resolve mixed pixels in the boundary of such images. The accuracy of the super-resolved output depends on the input derived from the soft classification technique. This paper aims to compare the potential of support vector machine (SVM), spectral angle mapper (SAM) and linear spectral unmixing (LSU) as inputs for super-resolution mapping. The fraction image, distance measure image and probability image obtained from linear spectral unmixing, spectral angle mapper and support vector machine respectively are used as an input for super resolution mapping designed on Hopfield Neural Network (HNN) for the Hyperion image of Peechi reservoir, south India. Effectiveness of the inputs is evaluated by estimating the water-spread area of the Peechi reservoir from each of the outputs. The results indicate that the accuracy of any super-resolution approach depends on the inputs from the soft classification approaches. The accuracy of the water spread area estimated from the classified outputs is 95.9%, 96.6% and 99.7% from LSU, SAM and SVM respectively as inputs for the SRM method. Thus, the HNN based SRM method proves to be better when the soft classification input is from SVM.