Loading video...

Video Failed to Load

Go Home

football AI code is finally open-source - player detection and tracking - team clustering - camera calibration I still need to work on README; don't judge me on that code:

2,050,207 views • 2 years ago •via X (Twitter)

10 Comments

emre's profile picture
emre2 years ago

following from the beginning. admired the final repo. congrats

SkalskiP's profile picture
SkalskiP2 years ago

@toIIenar It’s not final final yet ;) still have few ideas

Devin Pleuler's profile picture
Devin Pleuler2 years ago

Very neat. How does this perform on broadcast footage? These wide-angle captures aren't readily available to the public.

SkalskiP's profile picture
SkalskiP2 years ago

Not sure what you mean. This is taken straight from Bundesliga

Hussein's profile picture
Hussein2 years ago

this is the type of work that can literally change how soccer is played forever, I don't think Tiki taka style play would've been possible without broadcast footage and there are new types of play we can't imagine yet that will only be unlocked through this tech. Thanks again!

SkalskiP's profile picture
SkalskiP2 years ago

It would be awesome to make this project that influential ;)

Ankit Jha's profile picture
Ankit Jha2 years ago

You go man!!! Completely support you on this effort…

SkalskiP's profile picture
SkalskiP2 years ago

I’m having fun overhere

Vlad's profile picture
Vlad2 years ago

So do you mean that I can run this on my Saturday morning games to get stats on myself and the team? Man if that is the case imma feel like playing pro soccer, I guess I can use groq an eleven labs and add real-time narration😅

SkalskiP's profile picture
SkalskiP2 years ago

It’s not running in real time unfortunately:/

Related Videos