The technology detects human movements through walls. (Image Credit: Carnegie Mellon University)
Just because you can, should you make it? Seems like something that can/will be abused.
Carnegie Mellon University researchers leveraged WiFi routers to visualize a human being's movement and 3D shape in a room. They achieved this see-through method with the DensePose system, which maps each pixel on a human body's surface in a photo. Then, the team created a deep neural network to map the WiFi signals' phase and amplitude that routers transmit and receive for human-body coordination.
A low-frequency WiFi signal passes through a wall and bounces around the room. It detects any object, offsetting the static types. After the signal returns, the system produces a radar-like image based on the reflection of moving objects. The technology works with wooden fences, drywall, and concrete wall. Varying wall types may also affect the range and accuracy.
"We developed a deep neural network that maps the phase and amplitude of WiFi signals to UV coordinates within 24 human regions. The results of the study reveal that our model can estimate the dense pose of multiple subjects, with comparable performance to image-based approaches, by utilizing WiFi signals as the only input," the team wrote in the paper.
According to the researchers, WiFi signals can replace traditional RGB cameras for detecting humans in a room. WiFi also works much better because poor lighting and occlusion don't interfere with the system, which affects camera lenses.
They say this approach leads to improved privacy rights, "In addition, they protect individuals' privacy and the required equipment can be bought at a reasonable price. In fact, most households in developed countries already have WiFi at home, and this technology may be scaled to monitor the well-being of elder people or just identify suspicious behaviors at home."
However, they didn't clarify what entails "suspicious behavior" if the technology lands on the market. This isn't the first time researchers have developed unique ways to see humans without LiDAR or cameras. MIT engineers used cell phone signals to detect humans through walls in 2013. Then, in 2018, MIT researchers used WiFi signals to see people in a room with their movements shown on screen as stick figures.
Have a story tip? Message me at: http://twitter.com/Cabe_Atwell