Skip to main content

Research Repository

See what's under the surface

Broad-leaf weed detection in pasture

Zhang, Wenhao; Hansen, Mark F; Volonakis, Timothy N; Smith, Melvyn; Smith, Lyndon; Wilson, Jim; Ralston, Graham; Broadbent, Laurence; Wright, Glynn

Authors

Wenhao Zhang Wenhao.Zhang@uwe.ac.uk
Senior Lecturer in Machine Vision

Mark Hansen Mark.Hansen@uwe.ac.uk
Senior Research Fellow - Centre for Machine Vision

Tim Volonakis Tim.Volonakis@uwe.ac.uk
Research Associate in Computer Vision

Melvyn Smith Melvyn.Smith@uwe.ac.uk
Research Centre Director Vision Lab/Prof

Lyndon Smith Lyndon.Smith@uwe.ac.uk
Professor in Computer Simulation and Machine

Jim Wilson

Graham Ralston

Laurence Broadbent

Glynn Wright



Abstract

Weed control in pasture is a challenging problem that can be expensive and environmentally unfriendly. This paper proposes a novel method for recognition of broad-leaf weeds in pasture such that precision weed control can be achieved with reduced herbicide use. Both conventional machine learning algorithms and deep learning methods have been explored and compared to achieve high detection accuracy and robustness in real-world environments. In-pasture grass/weed image data have been captured for classifier training and algorithm validation. The proposed deep learning method has achieved 96.88% accuracy and is capable of detecting weeds in different pastures under various representative outdoor lighting conditions.

Start Date Jun 27, 2018
Publication Date Nov 1, 2018
Peer Reviewed Peer Reviewed
ISBN 9781538649916
APA6 Citation Zhang, W., Hansen, M. F., Volonakis, T. N., Smith, M., Smith, L., Wilson, J., …Wright, G. (2018). Broad-leaf weed detection in pasture
Keywords weed detection, machine learning, deep learning, support vector machine
Publisher URL http://dx.doi.org/10.1109/ICIVC.2018.8492831
Additional Information Additional Information : (c) 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Title of Conference or Conference Proceedings : 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)
Corporate Creators : SoilEssentials, Aralia Systems Ltd

Files







You might also like



Downloadable Citations