The study was conducted by researchers at Carnegie Mellon University, Pittsburgh.

Researchers at Carnegie Mellon University in Pittsburgh have developed a way to use WiFi signals to monitor human movement in indoor environments. By analyzing the ratio of the transmitted signal wave and the received wave, a neural network can recognize the specific pose of each person in a room.

“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 researchers wrote in the study.

“This paves the way for low-cost, broadly accessible, and privacy-preserving algorithms for human sensing.”

This non-visual method, dubbed “DensePose,” provides a low-cost, privacy-preserving option for indoor surveillance; however, it also raises concerns about security and privacy as WiFi signals can be detected beyond the confines of homes and offices, potentially allowing malicious users to monitor activities behind closed doors.

But there are also positive possibilities.

“Most households in developed countries already have WiFi at home, and this technology may be scaled to monitor the well-being of elderly people or just identify suspicious behaviours at home,” says the Carnegie Mellon researchers.

Related Story:  An Israeli AI-Based System Can See Through Walls

Image source: DensePose From WiFi