Scientists Use WiFi ‘Neural Network’ to ‘See’ People Through Walls
Scientists at Carnegie Mellon University have unveiled a revolutionary new technology that allows them to see through walls using nothing but WiFi signals.
By harnessing the power of DensePose, a system developed by Facebook that maps all pixels on the surface of a human body, and a deep neural network that maps WiFi signals’ phase and amplitude, the team has created a 3D map of human bodies.
Their findings, published in the journal arXiv, reveal that WiFi signals can serve as a substitute for traditional RGB cameras, as Wifi doesn’t face the same restrictions traditional cameras do like lighting, occlusions, shutter speed, etc.
“We believe that WiFi signals can serve as a ubiquitous substitute for RGB images for human sensing in certain instances,” the study authors wrote.
“In addition, they protect individuals’ privacy and the required equipment can be bought at a reasonable price. In fact, most households in developed countries already have WiFi at home, and this technology may be scaled to monitor the well-being of elder people or just identify suspicious behaviours at home.”
From: The team’s research builds on previous work in the field of “through-wall imaging” using wireless signals, VICE reports. In 2013, MIT researchers…