People counting and occupancy
Live counts for venues and shops, with the peak of the night and an alert before you reach the licensed capacity.
Services
Computer vision for real operations
A camera and a small computer can count people and detect objects in real time. We build the model and the device setup, and the video stays on your premises.
What we build
Cameras that report numbers, not footage
Object detection
Detection models such as YOLOv8 find and count what is in the frame, from a webcam, an IP camera or recorded video.
Private by design
Video is processed on the device and never stored or sent anywhere. Only the numbers leave the room.
Displays and integrations
Results on a display your staff can see, or sent on to a sign, a log or an alert.
How we work
Five steps, from your requirements to a system you own
Every project runs the same way: brief, specification, implementation, deployment and handover. At the end you get the code, the documentation and the runbook, with no licence fees.
Proof
Computer vision we have already deployed
Technology
What we build with
Built with
- Python
- YOLOv8
- OpenCV
- PyTorch
- Raspberry Pi
Questions
Frequently asked questions
Do we need special cameras?
No. It works with a webcam, an IP camera or recorded video.
Is any video stored?
No. The video is processed on the device and never stored or sent anywhere, so no footage of your customers leaves the building.
How fast is the count?
people_counter updates the count every second, so the number on the display stays live.
What hardware does it run on?
For occupancy counting, a Raspberry Pi next to the camera is enough. We size the hardware to the job in the specification step.
Get in touch
Tell us what you need
Describe the problem and imagine the solution you want. We’ll come back with the right answer and the best product for you.