Researchers have been working on ways to “see” people without using cameras or expensive LiDAR hardware for years. In 2013, a team of researchers at MIT found a way to use cell phone signals to see through walls. In 2018, another MIT team used Wi-Fi to detect people in another room and translate their movements into walking stick figures. Now, researchers at Carnegie Mellon University and the University of Waterloo are advancing our ability to see through walls using Wi-Fi.
How it’s possible to see through walls
The researchers at Carnegie Mellon University have developed a new method for detecting three-dimensional shapes and movements of human bodies in a room, using only Wi-Fi routers. The team used DensePose, a system for mapping all of the pixels on the surface of a human body in a photo, which was developed by London-based researchers and Facebook’s AI team. Essentially it is a way to capture a set of coordinates for each joint like an arm, a head, a torso, etc., which is known as a key point that can describe a person’s pose. They then created a deep neural network that maps Wi-Fi signals’ phase and amplitude sent and received by routers to coordinates on human bodies.
The technology works by sending a low-powered Wi-Fi signal through a wall, which reverberates around the room. It detects all the objects in the room, cancels out the static objects, and when the signal bounces back, uses the reflection of moving objects to generate a radar-like image. It can work through standard drywall, wooden fences, and even concrete walls, though the range and accuracy depend on the type of wall.
Read more via InterestingEngineering