HornetAI
Marked and re-identified individual hornets tracked at the bait station by their paint-dot colour.
- Client
- Confidential
- Year
- 2025
- Category
- Computer Vision
- Role
- Design + Build
- Timeline
- TODO(owner): confirm
The problem
The yellow-legged Asian hornet (Vespa velutina) is a highly predative non-native species that has spread rapidly across Europe since being introduced in 2004. Tracking its movement means knowing not just that a hornet visited a bait station, but which hornet. The standard field method is to mark individuals with a coloured paint dot and watch for their return, which is slow, manual work.
What we built
A detector runs on the bait-station camera and classifies each insect in frame, separating Asian hornets from other visitors. On top of that it reads the coloured paint dot applied to marked individuals, labelling each one by colour so the same hornet can be recognised across visits. It is built to run on edge hardware at the station rather than streaming footage away for processing.
The result
Visits are logged automatically with the individual identified rather than tallied by hand.
- paint-dot colour read and labelled per individual
- per hornetpaint-dot colour read and labelled per individual
- runs on edge hardware at the bait site
- on the stationruns on edge hardware at the bait site
- Asian hornet separated from other visiting insects
- species-levelAsian hornet separated from other visiting insects
Built with
- Python
- YOLO
- OpenCV
- Object tracking
- Edge AI
We deliver what we commit.
Tell us what you're trying to build.
We'll come back within 24 hours with honest feedback on scope, timeline and cost, whether or not we turn out to be the right fit.