Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Is there something low-cost and purpose-built to do this at short range, for when you just want to do some body tracking for VR/metaverse stuff? The trouble with doing this with a webcam is that occlusion results in errors and the avatar's limbs jump around. This sort of RF thing has more field of view, too.


This MS/Stanford project looks relevant, https://web.stanford.edu/~mkotaru/wicapture & https://www.science.org/content/article/wi-fi-could-protect-...

Commercially, Plume has 200K early adopters of Wi-Fi Sensing for human presence, but not VR specific, https://www.protocol.com/plume-wifi-data-intelligence

> Plume began testing Wi-Fi motion detection technology developed by Cognitive Systems in early 2020, and the company is now considering offering additional services atop of that technology. These could include triggers that help consumers save energy by automatically turning off lights after someone leaves a room, or even provide security and elder care products.

Amazon Echo uses ultrasound for motion detection.


> This MS/Stanford project looks relevant,

That's not imaging, that's tracking a WiFi equipped target. That's pretty standard now. Sony's Mocopi is probably the most elegant implementation.[1] Tundra Tracker [2] also gets good reviews.

Motion detection is much lower rez. Ultrasound is like trying to sense the world with a probe the size of a broom.

[1] https://www.youtube.com/watch?v=ovHHpralCD8&t=3s

[2] https://www.youtube.com/watch?v=ImEKHrUp4QM


This one tracks limbs, https://dl.acm.org/doi/abs/10.1145/3447993.3482857 & https://techxplore.com/news/2021-11-winect-tracks-3d-human-p...

> Our system tracks free-form activity by estimating a 3D skeleton pose that consists of a set of joints of the human body. In particular, Winect first identifies the moving limbs by leveraging the signals reflected off the human body and separates the entangled signals for each limb. Then, our system tracks each limb and constructs a 3D skeleton of the body by modeling the inherent relationship between the movements of the limb and the corresponding joints. Our evaluation results show that Winect achieves centimeter-level accuracy for free-form activity tracking under various environments.

~200 papers for VR + CSI, ~30 for 2022, https://scholar.google.com/scholar?hl=en&as_sdt=40005&sciodt...


For future, please share any thing you find.

I have some "quantified self" use cases that I'd like to try out.

- Monitor my breathing, nudge me when I'm holding my breath.

- Monitor my posture, nudge me as needed.

- Real time feedback for learning tai chi, qi gong, etc.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: