A group of MIT researchers have built upon previous advances in the use of wireless signals to track human motion through walls to show how subtle human movements can be observed through objects to distinguish between individuals. There are implications for heating bills, motion capturing for movies, and keeping family members safe in a smart home.
A team of researchers (two professors and three students) at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) have constructed a device that uses radio frequency (RF) signals to take snapshots of a human figure through a wall, which are then pieced together in a “reconstruction algorithm” to generate a heat-map-like silhouette.
“In other words, from the opposite side of a building, RF Capture can determine where you are, who you are, and even which hand you are moving,” according to the press release.
This technology could make motion capturing for films less cumbersome, as the RF Capture approach precludes the traditional setup of multiple cameras and body markers.
It also has intriguing potential in smart homes, according to the researchers. “We’re working to turn this technology into an in-home device that can call 911 if it detects that a family member has fallen unconscious,” said Dina Katabi, MIT professor and co-author of the paper. “You could also imagine it being used to operate your lights and TVs, or to adjust your heating by monitoring where you are in the house.”
For those wondering, the team says that the RF Capture device in question emits radiation that’s 1/10,000 the amount of radiation emitted by a standard cellphone.
The group of researchers has already used this technology to develop Emerald, which is meant to detect, predict, and prevent falls. They presented Emerald at the White House’s first annual Demo Day back in August.