“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.”
How would one go about setting this up? Because that sounds really cool for home automation.
It’s a very crude way of detecting presence for a variety of reasons, and likely won’t be as useful as you imagine.
The biggest problem is how modern smartphones handle networking when they’re locked. They enter a power saving state where they don’t respond to all pings, or they respond late enough that the pinger decides the device is just not there. Of course there are ways around it, but those are things you need to do explicitly so it won’t work on all devices until you’ve taken the time to set it up.
And since it detects a mobile device’s existence in the local wireless network rather than the actual presence of a human being, it’s not very flexible at all. What if you want to detect the presence of a guest? Are you gonna make sure they’re on your network with their devices set up to properly respond to pings? What if you forgot to turn on your phone’s wifi after turning it off?
I mean it does work once you’ve set it up, but do expect it to have a very limited scope in what you can and cannot do with it.
There is this Home Assistant integration which I remember getting working. I haven’t used Home Assistant in a while though, so I can’t be a good resource if you need any help.