We present an experimental study on the effects of pansharpening on target detection from multispectral and panchromatic images acquired by very-high resolution satellite sensors. Original and spatially-enhanced image data are used to detect relatively small targets (vehicles on an airport scenario) characterized by a sufficiently well-defined spectral signature in the four MS bands. The aim of the paper is to compare different pansharpening methods by evaluating the performances of target detection on true MS and panchromatic data Both linear and kernel-based one-class classification methods are considered for the target detection process.
Scheda prodotto non validato
Scheda prodotto in fase di analisi da parte dello staff di validazione