Abstract
The use of a fallow phase is an important tool for maximizing yield potential in moisture limited environments. There is a focus on ensuring these phases are maintained weed-free as even low weed densities can be detrimental to fallow efficiency. Repeated whole field herbicide treatment to control low-density weed populations is expensive and wasteful. Site-specific application of herbicide treatments to low density fallow weed populations is currently facilitated by sensor-based devices that detect chlorophyll fluorescence from living plant tissue. The use of image-based weed detection technology for fallow weed detection is an opportunity to develop an approach that can be translated for in-crop weed recognition. Here we present the OpenWeedLocator (OWL), an open-source, low-cost image-based approach for fallow weed detection that improves accessibility to this technology for the weed control community. A comprehensive repository, containing all code and assembly instructions, has been developed that will allow for community driven improvement over time. Four different colour-based weed detection algorithms were tested with the OWL system over seven fallow field scenarios under varying light, soil and stubble conditions. Across all scenarios, the four algorithms were similarly effective in detecting fallow weeds with average precision and recall of 79% and 52%, respectively. In individual transects, precision and recall values of up to 92% and 74%, respectively, suggest the potential fallow weed detection performance of the colour-based system. OWL represents an opportunity to redefine the approach to weed detection by enabling community-driven technology development and implementation in the weed control industry.