TY  - CONF
T1  - Improved and Generalized Vine Line Detection on Aerial Images Using Asymmetrical Neural Networks and ML Subclassifiers
A1  - Treboux, Jerome
A1  - Ingold, Rolf
A1  - Genoud, Dominique
Y1  - 2021
PB  - i6doc.com publ.
T2  - ESANN
CY  - Bruges, Belgium (Online)
SN  - 978287587082-7
N2  - It is widely accepted that deep neural networks are very efficient for detecting objects in images. They reach their limit when detecting multiple instances of long lines in low-resolution images. We present
an original methodology for the recognition of vine lines in low-resolution satellite images. The method consists in combining an asymmetrical neural network with a sub-classifier. We first compare a traditional U-Net architecture with an asymmetrical U-Net architecture designed for precision
agriculture. We then highlight the significant improvement in vine line detection when a Random Forest is added after the customized U-Net. This methodology addresses the complex task of dissociating vine lines from other agricultural objects. As a result, our experiments improve the precision from 0.83 to 0.94 over our optimized neural network.
ER  -