OpenWeedLocator (OWL)

Open-source, low-cost weed detection for site-specific weed control

OWL is a camera-based weed detection system based on the Raspberry Pi that uses green-detection algorithms to trigger relay-controlled solenoids for spot spraying. It's built entirely from off-the-shelf components and 3D-printable parts, making precision weed control accessible to anyone.

Website | Documentation | Community | Newsletter

OWLs in Action

2m vehicle OWL	2m robot-mounted OWL	Bicycle OWL
12m X-fold OWL (in development)	4m OWL sprayer	16 channel vegetables OWL

---

Quick Start

# Clone and install on Raspberry Pi (Bookworm or Trixie OS)
git clone https://github.com/geezacoleman/OpenWeedLocator owl
bash owl/owl_setup.sh

During this process you'll be asked to setup:

1. Green-on-Green - this adds about 2GB of dependencies
2. Dashboard - standlone or networked

One complete you'll need to reboot and then it should be running.

To confirm, run sudo systemctl status owl.service or sudo journalctl -u owl.service -f

See the two step installation guide for detailed instructions.

Documentation

• Getting Started - What you need, how it works
• Hardware Assembly - Parts list, wiring, 3D printing
• Software Setup - Installation, configuration, algorithms
• Controller Setup - Standalone and networked dashboards
• Troubleshooting - Common issues and fixes

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines, or join the conversation at community.openweedlocator.org.

Citing OWL

OpenWeedLocator was originally published in Scientific Reports.

@article{Coleman2022,
author = {Coleman, Guy and Salter, William and Walsh, Michael},
doi = {10.1038/s41598-021-03858-9},
issn = {2045-2322},
journal = {Scientific Reports},
number = {1},
pages = {170},
title = {{OpenWeedLocator (OWL): an open-source, low-cost device for fallow weed detection}},
url = {https://doi.org/10.1038/s41598-021-03858-9},
volume = {12},
year = {2022}
}

The OWL speed testing paper has been published in Computers and Electronics in Agriculture. Please consider citing the published article using the details below.

@article{Coleman2023,
author = {Coleman, Guy R.Y. and Macintyre, Angus and Walsh, Michael J. and Salter, William T.},
doi = {10.1016/j.compag.2023.108419},
issn = {0168-1699},
journal = {Computers and Electronics in Agriculture},
pages = {108419},
title = {{Investigating image-based fallow weed detection performance on Raphanus sativus and Avena sativa at speeds up to 30 km h$^{-1}$}},
url = {https://doi.org/10.1016/j.compag.2023.108419},
volume = {215},
year = {2023}
}

License

This project is licensed under the MIT License.

Star History