Recognising gym excerises in real-time using a neural network
dilpreetsingh.me
Recognising gym excerises in real-time using a neural network
1–10 of 31 posts
Re: Recognising gym excerises in real-time using a neural network
#2That's awesome!
I didn't think this would work but it does. It would be amazing to combine this with a training tracking app. So far the data entry has always been really annoying so only machine exercises could really be captured properly. Really exciting stuff. I think this has a lot of potential for a startup!
Re: Recognising gym excerises in real-time using a neural network
#3"Wouldn’t a better approach be to initially train the neural network on more than just one person?
That is a great point! In fact Microsoft’s research arm published a paper last year doing exactly that. Although they achieved great results, their initial training cohort consisted of 94 participants! I, as a one man team, can’t possibly duplicate that. This is why I created a system that can adapt, eliminating the need of Microsoft level resources."
--
Rather than using an accelerometer (OP attached an old iPhone to his person while doing the movements) - you could plausibly point a camera and try to use video as the input.
If that pans out the next step would be using Mechanical Turk to cheaply and quickly build the initial training set (no pun intended) using publicly available videos of people working out.
Re: Recognising gym excerises in real-time using a neural network
#4And this what happens when you bring a Computer Scientist into the gym! One question: how well would a neural network recognize a more complex and involved exercise like Kettlebell Turkish Getup compared to an exercise with simple movement like Push-ups?
Re: Recognising gym excerises in real-time using a neural network
#5"Wouldn’t a better approach be to initially train the neural network on more than just one person? That is a great point! In fact Microsoft’s research arm published a paper last year doing exactly that. Although they achieved great results, their initial training cohort consisted of 94 participants! I, as a one man team, can’t possibly duplicate that. This is why I created a system that can adapt, eliminating the nee…
That's an interesting point. The problem here would be that video input would not provide accel+gryo motion information, which is what the network needs in order to learn.
If we instead simply used video information to track exercises the problem would be scaling that to consumers. They'd require an external camera to watch them.
But the idea of using Mechanical Turk is quite smart. It'd help me get varied form - especially if I can get them to wear a band/phone that has the sensors.
Re: Recognising gym excerises in real-time using a neural network
#6And this what happens when you bring a Computer Scientist into the gym! One question: how well would a neural network recognize a more complex and involved exercise like Kettlebell Turkish Getup compared to an exercise with simple movement like Push-ups?
That's a good question! Turkish Getup's are very complex like you say. Given my current setup and window length, it's unlikely that it'll recognise them, because one rep is very long. Maybe if I did exercise based window lengths it could work better? I'm honestly not sure. But that is something to try out!
Re: Recognising gym excerises in real-time using a neural network
#7Here's a problem: I'm pretty sure you'd get just as good (probably superior) results with a simpler, faster out-of-the-box algorithm like logistic regression, random forests or boosted trees (depending on the amount of data). This just isn't a problem that seems well suited for neural networks.
Gyroscope/accelerometer data might seem like the kind of extremely-noisy, high-dimensional data well-suited for neural nets, but 1) you don't have a lot of data, and 2) intuitively the data isn't actually that noisy; my guess is the data separates out quite nicely (not necessarily linearly).
Re: Recognising gym excerises in real-time using a neural network
#8And this what happens when you bring a Computer Scientist into the gym! One question: how well would a neural network recognize a more complex and involved exercise like Kettlebell Turkish Getup compared to an exercise with simple movement like Push-ups?
>And this what happens when you bring a Computer Scientist into the gym!
Ah, now I understand why it took so long for someone to do this! ;)
Re: Recognising gym excerises in real-time using a neural network
#9Actually thought about an app that would do this on a smartwatch. I would definitely buy a smartwatch if I could have this level of accuracy of body movement tracking.
Re: Recognising gym excerises in real-time using a neural network
#10Actually thought about an app that would do this on a smartwatch. I would definitely buy a smartwatch if I could have this level of accuracy of body movement tracking.
WatchOS can detect the type of exercise, based on a recent talk I saw. Here's the docs on the types of exercises detected: https://developer.apple.com/library/watchos/documentation/He...