Pittsburgh scientists have found a way to use WiFi waves to map the poses of a human body, even if it’s behind a wall.
Thousands of scholars seek ways to see through walls. To do this, they design ever more advanced technologies, involving the use of laser beams and other photon detectors. A team of scientists from Carnegie Mellon University has found a much simpler technique, based on WiFi routers and artificial intelligence.
Messrs. Jiaqi Geng, Dong Huang, and Fernando de la Torre have published a paper detailing a method allowing them to detect and 3D modeling of human bodies and objects, even if they are behind a wall. Although this vision beyond obstacles is a subject studied by many researchers, their inventions will, for the most part, not be never offered to the general public. They are either too expensive, too cumbersome, or simply unthinkable for legal reasons.
These scientists use WiFi waves to map the positions of a human body
The Carnegie Mellon team has developed a neural network that correlates the phase and amplitude of a WiFi signal to 24 different regions of the human body using data provided by Densepose. This software maps and transcribes in 3D the pixels making up the surface of a human body in an image. According to them, this technique works as well as an approach based on the study of images. According to them, “this technology can be used to ensure the well-being of the elderly or to identify suspicious behavior in your home.
MM De la Torre, Geng and Huang are not the only scientists trying to create this invention that would bring humans closer to superheroes. In 2015, the prestigious MIT developed a program to display the silhouettes of people on the other side of an opaque wall. More recently, researchers at the University of Waterloo in Canada used WiFi to locate connected objects through walls.
Source: Vice