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.
A vision model is designed using low-level vision principles so that it can perform as a surrogate human observer. In a camouflage assessment task, using military patterns in an outdoor environment, human performance at recognition and detection is compared with the surrogate human observer. This involved field data acquisition and subsequent image calibration, a human experiment, and the design of the vision model. Human and machine performance, at recognition and detection, of military patterns in two environments was found to correlate highly.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.