Instance segmentation for the fine detection of crop and weed plants by precision agricultural robots.

Julien ChampAdan Mora-FallasHervé GoëauErick Mata-Montero Pierre BonnetAlexis Joly

Published in: Applications in plant sciences (2020)

Instance segmentation opens many possibilities for optimized weed removal actions. Weed electrification, for instance, could benefit from the targeted adjustment of the voltage, frequency, and location of the electrode to the plant. The results of this work will enable the evaluation of this type of weeding approach in the coming months.

Keyphrases

deep learning
convolutional neural network
climate change
air pollution
heavy metals
risk assessment
cancer therapy
loop mediated isothermal amplification
real time pcr
human health
label free
machine learning
drug delivery
solid state