This AI can ‘see’ through walls to track people’s movements
Being able to track movement through walls is no longer the domain of superheros and military radars, as researchers at MIT have used a combination of artificial intelligence and wireless signals to sense people when they’re hidden from view.
The team at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has developed a system it calls RF-Pose, which uses a neural network to monitor the movement of bodies, even behind obstacles.
To train the system, the researchers analysed wireless signals as they bounce off people. “We leverage the fact that wireless signals in the WiFi frequencies traverse walls and reflect off the human body,” an open-access paper on the research explains, adding that the project introduces a “deep neural network approach that parses such radio signals to estimate 2D poses”.
Because wireless signals travel through walls, the system can track people even when they’re hidden from the human eye. The AI translates this information into a stick model of a person, showing their posture, position and movement. As the scientists explain: “RF-Pose transmits a low power wireless signal (1000 times lower power than WiFi) and observes its reflections from the environment. Using only the radio reflections as input, it estimates the human skeleton.”
According to MIT, the technology could be used to help study diseases like Parkinson’s, multiple sclerosis (MS), and muscular dystrophy, with RF-Pose offering a detailed monitoring system for patient movement and therefore progression of the disease. The team also claims it could be used to help the elderly live more independently, with any falls picked up by the system, even if it happens out of view.
“We’ve seen that monitoring patients’ walking speed and ability to do basic activities on their own gives health care providers a window into their lives that they didn’t have before, which could be meaningful for a whole range of diseases,” says Dina Katabi, who co-wrote the paper. “A key advantage of our approach is that patients do not have to wear sensors or remember to charge their devices.”
These are outwardly positive examples, however. The most obvious area something like this could be used is surveillance, which the researchers acknowledge as a major sector for computer vision. However, CSAIL claims that future iterations of the technology could use a “consent mechanism” to ensure those being watched are in control of the system, with users needing to perform a certain set to movements to activate the mechanism.
All the same, it isn’t a stretch to see how this research could be used by authorities to keep track of individuals. Being able to monitor people through the walls of their homes would make for an intimidating advanced surveillance system.