Researchers at Carnegie Mellon University have developed a method to create a digital three-dimensional model of the human body and its movements in a room using only Wi-Fi routers. In other words, with just Wi-Fi signals, you can literally spy on people through walls.

To do this, the researchers used DensePose software, a 3D scanning system for all the pixels on the surface of the human body in a photograph. DensePose was developed by Facebook researchers and AI engineers in London. Based on this system, a neural network was created that compares the power, phase and amplitude of Wi-Fi signals sent and received by routers with coordinates on the human body, drawing a 3D model of a person over Wi-Fi.

Researchers have been working for years to "see" people without the use of cameras, thermal imagers, or expensive equipment like lidars. In 2013, an MIT team of researchers found a way to use mobile phone signals to see through walls, and in 2018, another MIT team used Wi-Fi to detect people in another room and monitor their movements.

Researchers at Carnegie Mellon University opined that Wi-Fi signals "could serve as a ubiquitous replacement for conventional cameras when it comes to detecting people in a room." The use of Wi-Fi allows you to overcome obstacles such as poor lighting and blind spots that ordinary camera lenses face.

Particularly noteworthy is the fact that scientists position their research as progress in the field of privacy rights. “Our developments protect people's privacy, and the necessary equipment can be purchased at a reasonable price. In fact, most households in developed countries already have Wi-Fi at home, and this technology can be scaled up to monitor the well-being of older people or simply detect suspicious behavior at home, ”the developers said in a statement.

It is not known what could fall under the term "suspicious behavior" if this technology ever enters the mass market. But with companies like Amazon trying to use drones with cameras in homes, it's easy to imagine how Wi-Fi's widespread human detection could be beneficial, for example, to security — or become another disruptive technology privacy.