Imaging spectroscopy

UAV-based hyperspectral imaging for weed discrimination in maize

Timely weed mapping in crop post-emergence situations is a challenging task required for developing precision weed management solutions. It is necessary to discriminate the crop from the weeds and, if possible, to distinguish different weed species. The ability to map weeds using hyperspectral images acquired from an unmanned airborne vehicle (UAV) over a maize field was evaluated by comparing different classification strategies. The results were mainly affected by the variability in crop and weed spectral signatures.

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma