Researchers at Carnegie Mellon University have developed a method to use WiFi routers to detect and track human movements, even through walls. The technology uses radio signals from WiFi routers to map the 3D shape and movements of humans in a room, without the need for cameras or expensive LiDAR hardware.
We believe that WiFi signals can serve as a ubiquitous substitute for RGB images for human sensing in certain instances.
The technology uses DensePose, a system developed by Facebook’s AI lab, to identify key points on the human body. The researchers demonstrated the technology using three $30 WiFi routers and three receivers. The system focuses on signals reflected off moving objects, reconstructing the pose of a person in a radar-like image. This technology could potentially see through various opaque obstacles, including drywall and concrete walls. However, concerns about privacy breaches have been raised.
For more details, read the full article here.