top | item 36533465

Show HN: Gamebody, a full-body game controller

107 points| fheisler | 2 years ago |github.com

28 comments

order

freedmand|2 years ago

I’ve been doing something similar to control racing video games while biking on an indoor exercise bike. I convert pedal speed into brake and acceleration keys (there’s some middle amount of pedaling that’s neutral) with pynput. I used OpenCV for webcam input and MediaPipe’s models to convert lean angle into left and right keyboard presses, and head tilt into up and down. It’s really fun but the slight latency in recognizing my pose is tough for fast courses. Now I’m thinking about some Arduino with a sensor or low res IR camera or something else that could detect changes a lot quicker.

grrdotcloud|2 years ago

People like you exist and do stuff like that and yet no one has an upgraded version of the NES Zapper after all these years.

berendka|2 years ago

Wait, can you now do QWOP with real human body parts as input and ... finally run? that would be so full circle!

fheisler|2 years ago

Yep, arms and legs control "thighs" and "calves" - although I was roughly as bad at full-body QWOP as on a keyboard!

mellosouls|2 years ago

Considering his last (brilliant) project featured here, the semaphore keyboard madness, I'm not sure how serious this is but it seems there is potential for providing a useful API for AR/VR apps/games/experiences; I'm not sure the body is extensively served by Quest etc beyond hand and head tracking.

fheisler|2 years ago

Thank you! For those who missed that one: https://github.com/everythingishacked/Semaphore

To me, the main motivation beyond "because I can" is the accessibility of these projects: you just need some Python code and any webcam. I'd love to play around more with VR, but the owners of the leading systems aren't exactly known for their openness to external APIs... Maybe Google Cardboard is worth a revisit :)

recursive|2 years ago

I'm still sad the MS didn't stick to their kinect concept.

dr_kiszonka|2 years ago

Yeah, it is a pity. You can still buy their Azure Kinect DK Developer kit, though.

j2bax|2 years ago

I like your name! What is shacking?

fheisler|2 years ago

I shack you for noticing :o)

doitLP|2 years ago

“Everything is hacked”

jncfhnb|2 years ago

Time for the dark souls run I guess

iasoy|2 years ago

That's interesting, I always wanted to try something similar but put it off. I'll try it with my phone & see if I can get it working in small space but with ulta-wide camera.

kylejrp|2 years ago

"I'm the video game boy! I'm the one who wins!"

0xfai|2 years ago

Wow! I've built dozens of stabs at exactly this and the consistency you've achieved is really good! Cool. Very cool.

iamflimflam1|2 years ago

How well does pose detection work on people wearing baggy clothes. Or for "non gym" type bodies?

fheisler|2 years ago

Pretty well from my limited testing! For standing poses, it works roughly as well as a human in good lighting and contrast conditions - as in, in situations where you would have a hard time picking out where limbs are, Mediapipe will too. The more common issue is poor lighting, or clothing that blends into a busy background.

topfloorboss|2 years ago

this goes so hard. I think I would prefer this to vr.