Open AccessWeed Detection in Pea Cultivation with the Faster RCNN ResNet 50 Convolutional Neural Network
Author(s) -
Mohammed Habib,
Adil Tannouche,
Youssef Ounejjar
Publication year - 2022
Publication title -
revue d'intelligence artificielle
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.146
H-Index - 14
eISSN - 1958-5748
pISSN - 0992-499X
DOI - 10.18280/ria.360102
Subject(s) - weed , convolutional neural network , deep learning , computer science , artificial intelligence , residual neural network , crop , machine learning , agronomy , biology
The fight against weed remains one of the major challenges in agriculture to improve land productivity. The first and most important step of this fight is to detect and locate this weed. Artificial intelligence has played a very important contribution in this detection. Several applications have been developed using Deep Learning techniques to detect and identify weed, but the variety of weed types complicates this operation. We propose a Deep Learning technique to detect and localize the crop, by training the pretrained Faster RCNN ResNet model with a rich dataset. We developed an algorithm able to detect and ultra-localize the pea crop with a prediction up to 100%. The obtained results show the feasibility of this method to distinguish the crop among weed.