Researchers at Carnegie Mellon University have developed a method to detect the three-dimensional shape and movements of human bodies in a room, using only WiFi routers. For this they used DensePose, a system for mapping all the pixels on the surface of a human body in a photo. DensePose was developed by London-based researchers and Facebook AI researchers. From there, they developed a deep neural network that links WiFi signals in phase and amplitude sent and received by routers to coordinates on human bodies, according to their preliminary article recently published on arXiv.
Researchers have been working for years on detecting people without using cameras or expensive LiDAR hardware. In 2013, a team of MIT researchers found a way to use cellphone signals to see through walls, and in 2018, another MIT team used WiFi to detect people in another room and translate their movements in stick figures.
As strange as it may seem, Carnegie Mellon researchers present this advancement as an advancement in privacy rights: "In addition, they protect the privacy of individuals and the required equipment can be purchased at a reasonable price" , they wrote. “In fact, most households in developed countries already have WiFi at home and this technology can be used to monitor the well-being of the elderly or simply identifying suspicious behavior at home,” without mentioning what “suspicious behavior” this technology might include, should it ever enter the mainstream market.