Ultra-High-Resolution UAV-Based Detection of Alternaria solani Infections in Potato Fields

Automatic detection of foliar diseases in potato fields, such as early blight caused by Alternaria solani, could allow farmers to reduce the application plant protection products while minimizing production losses. UAV-based, high resolution, NIR-sensitive cameras offer advantage a detailed top-down perspective, with high-contrast images ideally suited for detecting solani lesions. A field experiment was conducted 8 plots housing 256 infected plants which were monitored 6 times over 16-day period UAV. modified RGB camera, sensitive NIR, combined superzoom lens obtain ultra-high-resolution spatial resolution 0.3 mm/px. More than 15,000 lesions annotated points two full size corresponding 1250 cropped tiles pixels. deep learning U-Net model trained predict density every pixel. In this way, maps calculated indicate disease hotspots guide farmer.