This would be interesting, feel free to email me if you get stuck. If you had a camera at eye level, you could try to train it on recognizing the player jersey numbers.
Facial recognition would be better. Don’t forget that canonically in Mighty Ducks D2 Goldberg and Russ switched jerseys so that Russ could get his infamous “Knuckle Puck” shot off undisputed because everyone thought the puck was passed to Goldberg until the mask came off. So the ML training on jerseys would have missed this critical moment and potentially assigned the score to Goldberg, when really it was Russ (wearing Goldberg’s jersey) who should have gotten the credit.
One might argue that this sort of thing rarely happens so it’s not worth doing more complex facial recognition vis a vis Jersey numbering. But I say that while it may be rare, when it does happen it’s a major event, so no complexity should be spared to ensure we capture it accurately.
I would have multiple camera footage. One gopro would be just be a wide-angle of the bench behind the players, another would be on the game clock, and additional ones would be on-ice footage. Typically my gopro set-up has been behind the goalie (https://www.youtube.com/watch?v=CCavsdzc-OY) and the rinks have Livebarn feeds (here's one on my YT from 2018 https://www.youtube.com/watch?v=5WEE9y4cAHg) but there are challenges in quality abound.
