For decades, scientists have been looking to create x-ray vision to see through walls. And, in the past few years, they’ve succeeded; they created technology that uses WiFi to sense people through walls.
In this latest project from MIT, RF-Pose, uses artificial intelligence (AI) to teach wireless devices to sense people’s postures and movement—even from the other side of a wall. Led by Professor Dina Katabi from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), researchers use a neural network to analyze radio signals that bounce off people’s bodies. It can then create a dynamic stick figure that walks, stops, sits, and moves its limbs as the person performs those actions.
How it works
A neural network trained to identify dogs, for example, requires that people look at a big dataset of images and label each one as either “dog” or “not dog.” So, the researchers collected examples using both their wireless device and a camera. They gathered thousands of images of people doing activities like walking, talking, sitting, opening doors and waiting for elevators.
Interestingly, the camera can’t see through walls. So, the system was never explicitly trained in identifying people on the other side of a barrier. It just works because the radio waves bounce off a person on the other side of a wall just like they do in the same room. The ability to sense people through walls even works with multiple people crossing paths.
“By using this combination of visual data and AI to see through walls, we can enable better scene understanding and smarter environments to live safer, more productive lives.”
Applications for a technology to sense people through walls
For now, RF-Pose is being developed for the healthcare industry, focusing on the monitor of diseases such as Parkinson’s, MS, and muscular dystrophy, as well as aiding independent living by the elderly. And it could offer additional security by monitoring falls, injuries, and alterations in behaviour.
“All data the team collected has subjects’ consent and is anonymized and encrypted to protect user privacy,” says the team. “For future real-world applications, [we plan] to implement a ‘consent mechanism’ in which the person who installs the device is cued to do a specific set of movements in order for it to begin to monitor the environment.”
Besides healthcare, the team says that RF-Pose could also be used for new classes of video games where players move around the house; even in search-and-rescue missions to help locate survivors.
Daniel is an Art Director and Graphic Designer with over a decade of experience in advertising and marketing in the Greater Toronto Area.