Registrado y fusión de información

Abstract

This work focuses on the registration and fusion of information from different spectra, specifically between images of the long wave in frared spectrum (LWIR) and images of the visible spectrum (VS), with the aim of finding new indices to detect relevant objects or features. In this study, we have revised the information concerning the use of the Iterative Closest Point (ICP) algorithm to carry on the registration of information, explaining what it is and detailing each of its stages. In addition, to venture into the field of multispectral fusion, we have proceeded to perform the analysis of vegetation indices that currently exist, but in this case, the multispectral fusion is between the information of images of near infrared (NIR) and images of the visible spectrum (VS), such as the Normalized Difference Vegetation Index (NDVI), Relative Vigor Index (RVI) and the Enhanced Normalized Difference Vegetation Index (ENDVI), performing the respective comparisons between the results of each of these indices. These indices serve as a starting point for creating indices to detect vegetation, sky and street.