Over the past few months I have gone down a rabbit hole trying to work out what would be necessary to produce crowdsourced, publicly available tracking data. In this post I want to take stock of my progress so far, give an overview of the Narya API (an open-source computer vision API trained on broadcast footage) and introduce two possible applications. With a growing analytics community there is ever more demand for more publicly available data and in particular tracking data.

A couple of weeks ago another great dataset was made available to the soccer analytics community. In collaboration with Friends-of-Tracking the data provider SkillCorner open-sourced tracking data for nine matches across the Top5 leagues. Here is the link of the 9 matches of broadcast tracking data, we're open sourcing today:https://t.co/4CnxCO1EAC We'll open source soon some tooling to help visualizing the data, computing derivatives or synchronizing the data with event data.