University of Turku

Capstone

The goal of the project

The goal was to create a system that can be used when practicing curling. The system provides information about the slide of a curling stone, more accurately the current speed of the stone and the angle of the throw.

Results on high level

We created a system that uses two cameras, which are installed at both ends of the track. Machine vision is used to detect and track moving stones in the video feed in real time. The stone’s real coordinates are calculated using an algorithm. The system is carefully calibrated which ensures accurate results. The graphic user interface provides information on the current speed of the stone as well as the angle in the beginning of the throw. In addition to the speed and angle, the GUI also provides a visualization of the throw.

Our solution uses two IP cameras, two raspberry pi 3 computers and a router. It also requires Ethernet connection and power cords for the cameras.

Curling players can use this given information to replicate throws or to make slight modifications to them based on how successful the throw was.
Bild av projektet