Player tracking data is treated as the core input for measuring football momentum because player movement, positioning, spacing, and reaction time are what actually drive the dynamics of a match. Ball data and limb tracking are newer and heavier to process, and ball movement itself is described as an outcome of what players decide to do rather than the cause, which is why player tracking alone can capture most of what is needed to define momentum.
- 01
Limb tracking is framed as a possible future addition that could add detail on body position and orientation, but it is not yet part of the core momentum model.
- 02
Ball tracking data is described as very new and heavy in size and processing rate compared to player tracking.
337 words · auto-generated from the episode video
17:16so when you know I kind of want to dig in a little bit about this idea of momentum and why is it that uh given the vast array of data that's available the having a confidence level that that minimum data set like is the correct approach like can you help me understand the philosophy behind that a little bit if that makes sense. I'm going to come back at you for a second because I think if we simplify it for a moment, we have all of this data which gives us loads of different other opportunities. Um but the reality is is those are very new things, right? So the ball data is very new, the limb tracking is very new.
17:58Um, it's very heavy in terms of its its size and its processing rate, which is also that's not an issue in in many ways. But the big thing for us is the most telling when it comes to momentum and dynamics of the game actually is not how fast the ball spins or the location of the ball or where it goes to. That is a uh an outcome of what the players decide to do. Now the next iteration may be that limb tracking supports movement. It supports body position. It supports body orientation. But the reality is is the dynamics are all in players movements, which positions they hold, the spacing between each other, the
18:39spacing between them and the opposition, their reaction, their timing, the real, you know, dynamics of of of the game. So that's why we're so confident that just with this single data source that we get the majority of what we need to really understand how we define momentum, right? >> No, that that makes a lot of sense. And so maybe another interesting just this question to kind of touch on this is you brought it up earlier where simple possession like the idea of simple possession as a value um is unique and
Data ScienceSports AnalyticsWorld CupPerformance Analysis