Researchers at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) have created a device that allows them to “see” what a person is doing and track his or her movement even if that person is located behind a wall, and does not hold or wear any other device that would enable tracking.
The device, called RF Capture, transmits specific radio frequency (RF) signals aimed at the wall. While the signals pass through the wall, they reflect off a person’s body back to the device, which then uses them to create a silhouette of the person, and track its movements. The researchers have developed a series of algorithms that minimize the noise, so that the output is more clear.
But the device can also, with a high degree of certainty (nearly 90 percent), distinguish between different individuals.
Depending on the person’s movements, only some of their body parts reflects the wireless signals back to the device. The device is able to monitor how these reflections change as a person moves, and it creates, over time, a single image of the person’s silhouette – a “silhouette fingerprint”, if you will.
The researchers were thus able to “train” the device to distinguish between different subjects.
Here is a video demonstration of how the device works:
The researchers have thought out of different ways to use this technology – in gaming, movie production, smart homes.
“We’re working to turn this technology into an in-home device (Emerald) that can call 911 if it detects that a family member has fallen unconscious. You could also imagine it being used to operate your lights and TVs, or to adjust your heating by monitoring where you are in the house,” Dina Katabi, an MIT professor involved in the research and co-author of the paper explained.