Researchers have demonstrated an improved system that “sees” humans through walls using Wi-Fi signals

Hot potatoes: George Orwell’s vision of Big Brother is a reality. While most areas of the world don’t quite fit the dystopian model set in his 1984 novel, you’d be hard-pressed to find an urban place on Earth that doesn’t have cameras watching your every move. What Orwell did not imagine in his opening narration was that Big Brother’s eyes would one day have X-ray vision.

A team of researchers at Carnegie Mellon University has discovered how humans can “see” through walls using Wi-Fi router signals (repeatedly). The system can detect 3D human shapes and interpret movements in real time.

The team started with a technology developed by Facebook AI researchers called DensePose. dense pose It is an algorithm that can map the surface of the human body from a 2D image (or video). With DensePose as Direction, Carnegie Mellon Scholars advanced A deep neural network maps the phase and amplitude of incoming and outgoing Wi-Fi signals to points on the human body, providing DensePose with the necessary inputs.

The result is a vivid picture that does not have the limitations of standard RGB security cameras. For example, a sensor installed in a room can detect dead bodies in the dark or hidden behind other objects. Of course, the technology isn’t perfect, as shown in the sample photos below. But again, the algorithm predicts positions based on Wi-Fi signals, so it’s still pretty impressive.

Examples a and b are rare modes and c and d are three or more simultaneous objects. Systems struggle with both conditions due to lack of training.

The researchers mention “privacy” six times in their study, but all references paint the technology in a pro-privacy light.

The study concluded that the sensors are “privacy-friendly” because they cannot detect personally identifiable features. the paper published Via Cornell University’s arXiv repository, he envisions the technology as an inexpensive alternative to home monitoring and hospice care.

“In addition, it protects the privacy of individuals and the required equipment can be purchased at a reasonable price,” the front of the newspaper reads. “In fact, most families in developed countries already have Wi-Fi at home, and this technology could be expanded to monitor the well-being of the elderly or simply identify suspicious behaviors at home.”

This naive view ignores the fact that bad actors can just as easily use technology to spy on the activities of their victims without even entering the home or installing equipment on the premises. However, there are other means symmetry through walls, and this isn’t the first time researchers have used Wi-Fi as a method for lighting.

Image credit: cameras by Henning Schlottmann, dense positions from Carnegie Mellon University

Source link

Related Posts