Project Skate is a Machine Learning tool that uses Tensorflow, Blazepose and a combination of cameras to analyse a skateboarder’s movements in real-time. It can capture speed, height, rotation, grabs and tricks, showcasing the skills of any skateboarder – no matter who they are. We invited Sky Brown to put the technology to the test.
Some screenshots from the video:
Wow, stylish.
@8bitmp3 I would like to ask, if there is a further link to github, a dataset or a research paper?
Looking forward
HI Dennis, here there’s more information about the project: Reaching new heights - Google
It’s still on it’s early stages and not much more to share but I think the post above gives some more information.
The key model used is this one: TensorFlow Hub
but you can also look into these ones: TensorFlow Hub
