“We developed a deep neural network that maps the phase and amplitude of WiFi signals to UV coordinates within 24 human regions. The results of the study reveal that our model can estimate the dense pose of multiple subjects, with comparable performance to image-based approaches, by utilizing WiFi signals as the only input.”

  • Mossy Feathers (She/They)
    link
    fedilink
    English
    45
    edit-2
    11 months ago

    Also VR nerds. Current tracking is either based on the headset, so you can’t move your arms unless the headset can see them, or your arms have to be seen by lighthouses, or you rely purely on gyroscope and accelerometers for tracking, which tend to drift. So either you have blind spots, have to deal with occlusion, or will slowly drift and have to recalibrate periodically. Wifi-based tracking seems like a neat idea tbh.

    Edit: considering wifi is just photons that aren’t wiggling fast enough for us to see, I’d be surprised if the government doesn’t already have this technology behind closed doors.

    • @CleoTheWizard
      link
      English
      1011 months ago

      For VR I don’t see why we wouldn’t use a variety of other technologies before we ever use WiFi. The main issue with the WiFi thing is going to be polling rates and interference (which limits polling rates). They’re also using a neural net here which requires both processing power and time so there’s latency far beyond VR uses. That’s without talking about tracking that would be needed for higher spatial resolution which this also doesn’t have currently. So it’s not impossible to use this, just not currently practical or even close.

      The real solve to that stuff is just an improvement on existing tech or maybe Lidar. With the progress that has been made on the Quest with hand tracking, I’d bet their next goal is body and face tracking so you’ll see this soon.

      As for the government having this, I doubt they really need to have it this specific to track poses or body parts. If you have a cell phone on you, they likely know exactly where you’re at in a room. If you don’t, I’m betting they have access to other important data. Motion detection, number of people, room shape and some contents, interference sources.