Large-Scale Fine-Grained Change Detection from Multisensory Satellite Images

In this Chapter, we present a multisensor, multiresolution fusion strategy improving the detec- tion of landcover changes at metric resolution and regional scale. Spectral-preserving fusion is performed between Sentinel-2 multispectral bands at 10m and 20m spatial resolution and hyper- spectral/panchromatic bands from the PRISMA satellite. Hyperspectral (HS) data from PRISMA are spatially enhanced by means of the Sentinel-2 visible and near infrared (VNIR) and shortwave infrared (SWIR) bands at 10 and 20 m spatial resolution, and the 5 m panchromatic (PAN) band also acquired by the PRISMA satellite. The 20-m bands of Sentinel-2 are hypersharpened to 10 m by means of the four 10 m VNIR bands of the same instrument. Then, the 10-m hypersharpened bands of Sentinel-2 are used to sharpen the 30-m bands of PRISMA to 10 m as well. Finally, the 10-m hypersharpened bands of PRISMA are pansharpened to 5 m by means of the Pan image of the same satellite.