Improved monitoring of southern corn rust using UAV-based multi-view imagery and an attention-based deep learning method

Zhengang Lv, Binyuan Xu, Liheng Zhong, Gengshen Chen, Zehua Huang, Rui Sun, Wei Huang, Feng Zhao, Ran Meng

Abstract: Highlights•A novel UAV-based method for efficient SCR monitoring.•Green-red-red edge band related spectral indices are optimal features.•Multi-view spectral measurements outperform single-view spectral measurements.•15 degree view has the highest contribution in SCR severity monitoring.•An attention-based FCN method improves SCR monitoring using multi-view imagery.