F. Baret

SegVeg: Segmenting RGB images into green and senescent vegetation by combining deep and shallow methods

SegVeg segments RGB images into green and senescent vegetation using a hybrid deep and shallow learning approach, achieving high accuracy for green vegetation but lower for senescent and background.

Plant detection and counting from high-resolution RGB images acquired from UAVs: comparison between deep-learning and handcrafted methods with application to maize, sugar beet, and sunflower crops

This paper compares deep-learning and handcrafted methods for plant detection and counting in UAV-acquired RGB images of maize, sugar beet, and sunflower, finding that deep learning outperforms handcrafted methods, especially with weed management improvements.

Leaf rolling in maize crops: from leaf scoring to canopy level measurements for phenotyping

This study links leaf rolling in maize under water stress to canopy structure changes, enabling high-throughput remote sensing phenotyping.