Roof materials identification based on pleiades spectral responses using supervised classification

Abstract

The current urban environment is very dynamic and always changes both physically and socio-economically very quickly. Monitoring urban areas is one of the most relevant issues related to evaluating human impacts on environmental change. Nowadays remote sensing technology is increasingly being used in a variety of applications including mapping and modeling of urban areas. The purpose of this paper is to classify the Pleiades data for the identification of roof materials. This classification is based on data from satellite image spectroscopy results with very high resolution. Spectroscopy is a technique for obtaining spectrum or wavelengths at each position from various spatial data so that images can be recognized based on their respective spectral wavelengths. The outcome of this study is that high-resolution remote sensing data can be used to identify roof material and can map further in the context of monitoring urban areas. The overall value of accuracy and Kappa Coefficient on the method that we use is equal to 92.92% and 0.9069.