New X-Ray Vision Tech Lets Users Track People Through Walls

A new kind of technology has been developed by researchers at MIT's Computer Science and Artificial Intelligence Lab (CSAIL). Called RF-Capture, the tech is basically x-ray vision that can identify and track human movement through walls.

RF-Capture works this way: there is a wireless transmitter on a device that relays a radio signal. The device's receivers will then pick up the signal reflected by a person hidden by the wall. Using the data, an algorithm can determine the silhouette of the person on the other side. The device is also able to distinguish up to 15 different people with 90% accuracy. The device tracks motion and posture up to 0.8 inches, PopSci reported.

The researchers who developed RF-Capture say that there are many practical application of this tech. For instance, it might be possible to rival Microsoft's Kinect system and for use in capturing special effects in movies. It is also possible to monitor hospital vital signs using RF-Capture.

"It basically lets you see through walls," said Fadel Adib, a Ph.D. student at MIT's Computer Science and Artificial Intelligence Lab and lead author of the paper that describes the system. "Our revolution is still nowhere near what optical systems can give you, but over the last three years, we have moved from being able to detect someone behind a wall and sense coarse movement, to today, where you can see roughly what a person looks like and even get a person’s breathing and heart rate."

Dr. Dina Katabi, professor of electrical engineering and computer science at MIT, has been developing wireless tracking technology for several years now. In 2013, she and her team used Wi-Fi signals to detect people on the other side of thick walls and track their movements, Yahoo News noted.

RF-Capture uses radio waves that are a thousand times less powerful than Wi-Fi signals. According to Adib, improved hardware and software make RF-Capture a more powerful tool nonetheless. “These [radio waves used by RF-Capture] produce a much weaker signal, but we can extract far more information from them because they are structured specifically to make this possible.”

Real Time Analytics