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.
Highlights
Pasture is increasingly seen as crop, which when managed effectively can provide a healthy diet for livestock throughout the year
“in-pasture” weed detection is considerably harder as the weeds and grass are both predominantly green, and the grass can often obscure the weed. [1] provided an excellent comparison of machine vision techniques for detecting Dockleaf in pasture, concluding that the best performing was an approach that used Local Binary Patterns (LBP) which describe local textures as a feature extractor and a Support Vector Machine (SVM) as the classifier
It should be noted that these results are based on local binary pattern histograms (LBPH) features extracted from RGB colour images
Summary
Pasture is increasingly seen as crop, which when managed effectively can provide a healthy diet for livestock throughout the year. Current methods of controlling weeds tend to rely on blanket spraying of the field using herbicides such as glyphosphate. [1] provided an excellent comparison of machine vision techniques for detecting Dockleaf in pasture, concluding that the best performing was an approach that used Local Binary Patterns (LBP) which describe local textures as a feature extractor and a Support Vector Machine (SVM) as the classifier. This approach achieved an accuracy of just over 80%. We replicate this finding on a large dataset and compare this method with other conventional machine learning methods, as well as providing improved performance through the use of deep learning
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.