people_counter: live venue occupancy with computer vision
Live occupancy counting for bars and venues in Barcelona, where going over the licensed capacity means a fine.
- frames of video stored or sent off the premises.
- 0
- second between counts, so the number on the display stays live.
- 1
- camera works: a webcam, an IP camera or a recorded video.
- Any
Knowing the real number in the room
A venue’s licensed capacity is a hard limit, and the number of people inside changes all night. Staff need the real figure at a glance, without counting by hand at the door.
A camera, a Raspberry Pi and a live count
A camera and a Raspberry Pi count the people in the room every second with a YOLOv8 computer-vision model, and show the number and the night’s peak on a display the staff can see. The count can also feed a sign, a log or an alert.
The video is processed on the device and never stored or sent anywhere, so no footage of customers leaves the building.
A bar terrace, every person boxed and counted · simulated scene
A simulated scene, not a client’s venue: the detections and the total are how the counter marks up what it sees.
The 16×2 panel the counter drives, on the bar
Drawn from the panel the Pi version renders. It can also drive a real LCD on the bar, or send the count on to a sign or a log.
A live number, and no footage
Staff see the live count and the night’s peak at a glance, updated every second, with any camera the venue already has.
What it is built with
- Python
- YOLOv8
- OpenCV
- Raspberry Pi
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.