MIT’s Computer Science and Artificial Intelligence Laboratory is trying to make you see through a wall. Well no, not really – but the outcome is the same.

Under the guidance of Professor Dina Katabi, a team at CSAIL is working on a project named RF-Pose, which, according to MIT, uses artificial intelligence and a neural network to sense people’s postures and movement from the other side of a wall.

“The researchers use a neural network to analyse radio signals that bounce off people’s bodies, and can then create a dynamic stick figure that walks, stops, sits, and moves its limbs as the person performs those actions,” the article said. The video above demonstrates and explains the mechanism.

Advertisement

So it’s not exactly X-Ray vision, which is precisely why it is feasible.

For now, RF-Pose can be used for health care – for monitoring disease like Parkinson’s, multiple sclerosis, muscular dystrophy – and to gain a better understanding of disease progression. The team estimates it will make it easier for doctors to adjust medication, and could help elderly people live more independently.

But its use isn’t limited to health care. It also opens up a series of exciting possibilities, such as new classes of video games where players move around the house, search-and-rescue missions to locate survivors, and more.