Repolode
Submit
geezacoleman

geezacoleman/OpenWeedLocator

Low-cost, Raspberry Pi-based camera device that detects green plants in images to trigger spot spraying of weeds.

View on GitHub
Stars
503
Forks
92
Open issues
18
Last commit
3 days ago

What is it?

OpenWeedLocator (OWL) is a camera-based weed detection system built around a Raspberry Pi. It uses green-detection algorithms to identify plant material in images and drives relay-controlled solenoids to spray only where weeds are found, which reduces herbicide use compared with blanket spraying.

The hardware is made from off-the-shelf components and 3D-printable parts. The project supports in-crop and fallow scenarios and has been mounted on vehicles, bicycles, robots and multi-channel sprayers in the examples shown in its documentation. A Green-on-Green option adds a more advanced detection mode at the cost of roughly 2GB of extra dependencies.

Installation is handled by a setup script for Raspberry Pi OS (Bookworm or Trixie), which runs the device as a systemd service. Configuration can use a standalone or networked dashboard. The project is MIT-licensed and comes with documentation covering hardware assembly, software setup and troubleshooting.

Key features

  • 01Detects green plant material from camera images on a Raspberry Pi.
  • 02Triggers relay-controlled solenoids for spot spraying.
  • 03Built from off-the-shelf components and 3D-printable parts.
  • 04Includes an optional Green-on-Green detection mode.
  • 05Runs as a systemd service with standalone or networked dashboards.

Use cases

  • Spot spraying of weeds in in-crop rows on vehicles or robots.
  • Weed control on fallow ground before planting.
  • Research into image-based weed detection at different travel speeds.
  • Low-cost precision agriculture experiments by DIY farmers and students.

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/geezacoleman/OpenWeedLocator owl
  2. 2

    Run the setup script on a Raspberry Pi (Bookworm or Trixie OS) and answer its prompts

    bash owl/owl_setup.sh
  3. 3

    Reboot the Pi when setup finishes, then check the service status

    sudo systemctl status owl.service

Things to know

  • Designed for Raspberry Pi with Bookworm or Trixie OS, so it is not a general desktop tool.
  • Requires building camera, relay and solenoid hardware, which takes physical assembly effort.
  • The optional Green-on-Green feature adds about 2GB of dependencies.

In collections

Computer vision libraries & toolsEmbedded systems & microcontroller projects

Topics

#computer-vision#raspberry-pi#precision-agriculture#weed-detection#embedded#iot#diy#agriculture

FAQ

What is OpenWeedLocator?
Low-cost, Raspberry Pi-based camera device that detects green plants in images to trigger spot spraying of weeds. OpenWeedLocator (OWL) is a camera-based weed detection system built around a Raspberry Pi. It uses green-detection algorithms to identify plant material in images and drives relay-controlled solenoids to spray only where weeds are found, which reduces herbicide use compared with blanket spraying.
Is OpenWeedLocator free to use? What license does it have?
OpenWeedLocator is open source under the MIT license. Check the license terms before using it in commercial products.
Is OpenWeedLocator still maintained?
Actively maintained. The last commit to OpenWeedLocator was on Oct 19, 2026.
What can I use OpenWeedLocator for?
Spot spraying of weeds in in-crop rows on vehicles or robots. Weed control on fallow ground before planting. Research into image-based weed detection at different travel speeds. Low-cost precision agriculture experiments by DIY farmers and students.
How do I install OpenWeedLocator?
Clone the repository: git clone https://github.com/geezacoleman/OpenWeedLocator owl Run the setup script on a Raspberry Pi (Bookworm or Trixie OS) and answer its prompts: bash owl/owl_setup.sh Reboot the Pi when setup finishes, then check the service status: sudo systemctl status owl.service
Where can I get OpenWeedLocator?
The source code and installation instructions are on GitHub: https://github.com/geezacoleman/OpenWeedLocator

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects