In a paper accepted to the SIGGRAPH Asia conference taking place next month, the team presents a new technology called RF Capture that picks up wireless reflections off the human body to see the silhouette of a human standing behind a wall.
Advertisement
RF Capture, in fact, is so clear that it can identify individuals within certain limits, track small hand gestures, and even see silhouettes of people on the other side of a wall. Using variations in Wi-Fi signal, the technology can recognize human silhouettes and even distinguish between 15 different people, with 90 percent accuracy. But the researchers told Gizmodo that in addition to necessary regulation that would need to be implemented, they’re now designing blockers that would only allow a person to be tracked by her own device.
They emphasize that, although this capability inevitably raises privacy concerns around the potential for more intrusive surveillance, it also has benign applications in gaming, elder care, and smarter home appliances. But now MIT researchers have found a way to use it to identify people, but not necessarily with the internet itself.
The group of researchers includes MIT PhD student and lead author Fadel Adib, Professor and Director of Wireless@MIT Dina Katabi, Professor Frédo Durand, PhD student Chen-Yu Hsu and intern Hongzi Mao.
RF-Capture doesn’t require the user to wear any sensor, yet it can differentiate between different unseen people by transmitting wireless signals that can pass through physical objects and reflect off whatever is on the other side. “RF Capture would enable motion capture without body sensors and could track actors’ movements even if they are behind furniture or walls”. In contrast to these past systems which abstract the entire human body as a single point and find the overall location of that point through walls, we show how we can reconstruct various human body parts and stitch them together to capture the human figure. “Can we detect heart problems using this wireless technology?” “For example, can we track human fingers from behind a wall?”
“The data you get back from these reflections are very minimal”, says Katabi. “However, we can extract meaningful signals through a series of algorithms we developed that minimize the random noise produced by the reflections”.
The Emerald Fall Detection system is still under development but it was demonstrated by the researchers to President Obama in August.
RF-Capture uses a compact array of 20 antennas to transmit the wireless signals – yet it emits just 1/10,000 the amount of radiation given off by a standard cell phone.
Advertisement
The device would also call 911 if it detects an unconscious family member.
