Researchers at Carnegie Mellon University have turned a common piece of technology found in practically every home into a tracking device.
They were able to recognize and monitor the three-dimensional form and movements of human beings within a room by using radio signals emitted by WiFi routers. Surprisingly, they accomplished this without the use of cameras or expensive LiDAR technology.
In their study, the authors wrote:
We believe that WiFi signals can serve as a ubiquitous substitute for RGB images for human sensing in certain instances. Illumination and occlusion have little effect on WiFi-based solutions used for interior monitoring. In addition, they protect individuals’ privacy and the required equipment can be bought at a reasonable price.
The researchers used DensePose, a technique devised by a collaborative team from Facebook’s AI laboratory and a London-based organization for allocating every pixel on the surface of a human body in an image.
DensePose’s strength rests in its ability to detect over two dozen essential places and zones in human anatomy, such as joints and various body components such as limbs, head, and chest. This enables the device to correctly track the posture of a human body.