360° Foot Traffic Counter MVP

I need a lean, working proof-of-concept that automatically counts foot traffic using a single 360-degree camera. The goal is to drop the unit into busy conference halls, festival entrances, or outdoor promotional zones and have it return reliable head-counts without manual intervention.

Here is what matters to me:

• Vision logic: Please build or integrate computer-vision models (OpenCV, YOLO, TensorFlow Lite or similar) that detect and track people moving through the camera’s full 360° field of view. The algorithm must distinguish unique passes so that every person is counted once.

• Edge or cloud flexibility: I am fine with the model running on a Raspberry Pi 4, Jetson Nano, or a small cloud instance—as long as latency is low and setup remains simple.

• Mixed environments: Accuracy should hold both indoors and outdoors. Lighting at trade-show booths is very different from an outdoor activation, so include a quick calibration routine (e.g., exposure, background learning).

• Output & dashboard: All I need is a lightweight web interface or API that displays live counts, stores historical totals with timestamps, and lets me export CSV.

• Documentation: A short guide that covers hardware connections, software install, and a checklist for on-site deployment at events/conferences.

Acceptance criteria: During a controlled two-hour test with at least 200 passers-by, the counter should reach 90 %+ accuracy compared to a manual tally.

If you have already worked with 360° cameras or crowd-analytics, please mention the hardware and frameworks you prefer so we can lock specs quickly. Show More