Researchers at the Massachusetts Institute of Technology’s (MIT) Computer Science and Artificial Intelligence Laboratory have created a system that can identify people through walls using just wi-fi signals.
The technology works by detecting “reflections” created by the signals when they touch other objects, such as human bodies.
By analysing the different characteristics of the “reflections”, such as height and build, it can distinguish between 15 different people with 90% accuracy.
Researchers plan to use the device to monitor elderly people, with the intention of detecting and preventing falls and injury in the home.
BBC Click’s Stephen Beckett spoke to Prof Dina Katabi about the project.