TY - JOUR
T1 - Deep learning-based visual recognition of rumex for robotic precision farming
AU - Kounalakis, Tsampikos
AU - Triantafyllidis, Georgios A.
AU - Nalpantidis, Lazaros
N1 - Funding Information:
This work has been supported by the DockWeeder project (project ID: 30079 ), administered through the European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement no 618123 [ICT-AGRI 2]. The project has received funding from the Ministry of Economic Affairs (The Netherlands), from the Federal Office for Agriculture (Switzerland), and from Innovation Fund Denmark, the Ministry of Science, Innovation and Higher Education (Denmark).
Funding Information:
This work has been supported by the DockWeeder project (project ID: 30079), administered through the European Union's Seventh Framework Programme for research, technological development and demonstration under grant agreement no 618123 [ICT-AGRI 2]. The project has received funding from the Ministry of Economic Affairs (The Netherlands), from the Federal Office for Agriculture (Switzerland), and from Innovation Fund Denmark, the Ministry of Science, Innovation and Higher Education (Denmark).
Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2019/10
Y1 - 2019/10
N2 - In this paper we address the problem of recognising the Broad-leaved dock (Rumex obtusifolius L.) in grasslands from high-resolution 2D images. We discuss and present the determining factors for developing and implementing weed visual recognition algorithms using deep learning. This analysis, leads to the formulation of the proposed algorithm. Our implementation exploits Transfer Learning techniques for deep learning-based feature extraction, in combination with a classifier for weed recognition. A prototype robotic platform has been used to make available an image dataset from a dairy farm containing broad-leaved docks. The evaluation of the proposed algorithm on this dataset shows that it outperforms competing weed/plant recognition methods in recognition accuracy, while producing low false-positive rates under real-world operation conditions.
AB - In this paper we address the problem of recognising the Broad-leaved dock (Rumex obtusifolius L.) in grasslands from high-resolution 2D images. We discuss and present the determining factors for developing and implementing weed visual recognition algorithms using deep learning. This analysis, leads to the formulation of the proposed algorithm. Our implementation exploits Transfer Learning techniques for deep learning-based feature extraction, in combination with a classifier for weed recognition. A prototype robotic platform has been used to make available an image dataset from a dairy farm containing broad-leaved docks. The evaluation of the proposed algorithm on this dataset shows that it outperforms competing weed/plant recognition methods in recognition accuracy, while producing low false-positive rates under real-world operation conditions.
KW - Agricultural robotics
KW - Deep learning visual recognition
KW - Precision farming
KW - Weed recognition
UR - http://www.scopus.com/inward/record.url?scp=85071398904&partnerID=8YFLogxK
U2 - 10.1016/j.compag.2019.104973
DO - 10.1016/j.compag.2019.104973
M3 - Journal article
AN - SCOPUS:85071398904
SN - 0168-1699
VL - 165
JO - Computers and Electronics in Agriculture
JF - Computers and Electronics in Agriculture
M1 - 104973
ER -