AI + digital coaching experiments

PLAYER TRACKING

Turn wide match video into player trajectories.

Detect and track players over time, preserve identities where possible, and export court positions for later statistics.

Technology

TrackLab or SportsLabKit-style pipeline: detector + ReID + tracker + court calibration; floorball-specific model training will be needed.

How a coach can use it

Generate heatmaps and shift-level movement summaries.
Measure spacing and team shape after calibration.
Support scouting with repeated evidence rather than isolated clips.

Camera setup

Use a fixed, elevated camera with minimal pan/zoom.
Calibrate the visible rink boundaries or known court points before tracking.
High resolution helps jersey-number and re-identification work.

Implementation path

Start with a small browser prototype, keep the data model explicit, then connect the analysis backend as separate API services. Validate results with coaches before automating scoring.

Prototype

Try the prototype

This is a front-end concept demo. It does not yet send video or personal data to a server.

Match video