Consumer Grade Passive Radar using Wifi Signals (and a bit of history)

By breaking down a 20Mhz-wide Wifi signal into 10Hz-wide spikes, researchers have creaded an SDR-based passive radar system (with your local WiFi access point as a transmitter) that can be used for gesture recognition throughout an entire house.

In other words, if you have an access point nearby, anyone nearby can recognize you moving inside of a house-shaped space… and identify those movements accurately enough to perform gesture recognition.

Evidently looking at the signal with such fine (<2Hz) frequency-domain resolution lets you spot movement-induced doppler shifts.

This would make a FANTASTIC burglar alarm, I think. Doppler microwave sensors are a pain to avoid and damn near undetectable. But it’s also just as great an argument for wifi-blocking wallpaper, wifi-blocking curtains, wifi-blocking house paint, wifi-blocking shower curtains…

See, as soon as someone gets a really good SDR, this system will start picking up vibrations of metal objects, vocal cords, and all the rest.

Maybe in the next few years we’ll discover a social need for legalizing low-power jammers.

History: Reading the news reminded me of this guy, even if nothing we’ve seen so far can really compare with what he pulled off. https://en.wikipedia.org/wiki/Mitrokhin

http://wisee.cs.washington.edu/

“WiSee is a novel interaction interface that leverages ongoing wireless transmissions in the environment (e.g., WiFi) to enable whole-home sensing and recognition of human gestures. Since wireless signals do not require line-of-sight and can traverse through walls, WiSee can enable whole-home gesture recognition using few wireless sources (e.g., a Wi-Fi router and a few mobile devices in the living room).

WiSee is the first wireless system that can identify gestures in line-of-sight, non-line-of-sight, and through-the-wall scenarios. Unlike other gesture recognition systems like Kinect, Leap Motion or MYO, WiSee requires neither an infrastructure of cameras nor user instrumentation of devices. We implement a proof-of-concept prototype of WiSee and evaluate it in both an office environment and a two-bedroom apartment. Our results show that WiSee can identify and classify a set of nine gestures with an average accuracy of 94%.”

Advertisements
%d bloggers like this: