Researchers from MIT's Computer Science and Artificial Intelligence Lab have developed a technology based on wireless signals that detect an object or activity behind a wall. With help from a Wi-Fi network, the silhouette of a person is effectively captured in a process that is said to be capable of determining the identity of a person as well.
Dubbed as RF-Capture, the technology uses a technique that involves bouncing wireless reflections off a human body to outline its silhouette and its motions. It "can trace a person's hand as he writes in the air and even distinguish between 15 different people through a wall with nearly 90 percent accuracy," MIT said in a press statement.
What is also equally interesting is that it can be trained to recognize the identity of the scanned object or person based on measurements and other collected information uploaded through algorithms designed to detect body features. The detailed discussion of RF-Capture can be accessed through this link.
"[We] use the captured human silhouettes from our reconstruction algorithm [to] train a classifier on these silhouettes which allows us to distinguish between people," Fadel Adi, one of the MIT researchers behind the project, told Gizmodo. "The classifier captures features like height and body builds, which allows us to distinguish between people using RF-Capture."
The MIT researchers did not identify any specific real-world application for RF-Capture. However, it could serve as a basis for other technologies such as a monitoring device for the elderly or as a means to control home appliances, according to The Verge. Watch the technology in action in the video below.