YOLO KZ
A field computer-vision system that turns a tripod-mounted phone camera into directional counts for vehicles, people, bicycles and scooters.
- 01Detect object
- 02Cross line
- 03Record count
Signal path
The working path from input to physical or measurable outcome.
Car · person · bicycle · scooter
The challenge
Start with the constraint.
Street activity had to be measured from a portable camera setup and converted into reliable, class-specific directional statistics.
The approach
Make complexity local.
- 01
Used a phone on a tripod as a portable field camera for repeatable observation points.
- 02
Detected and classified cars, pedestrians, bicycles and scooters with a YOLO pipeline.
- 03
Converted tracked crossings into directional events and idempotent offline batches.
- 04
Built the ASP.NET Core backend around projects, devices, protected analytics and live counters.
The outcome