News

Video: MIT Technology With Wi-Fi Can Recognize People Through Walls

By R. Siva Kumar | Update Date: Nov 01, 2015 01:33 PM EST

A new technology has been developed by scientists from MIT's Computer Science and Artificial Intelligence Lab.

They are based on wireless signals that can locate an object or activity that is behind a wall. In the vicinity of Wi-Fi network, an individual's silhouette as well as the identity can be determined immediately.

This is called the 'RF-Capture'. It is a technology that harnesses a technique which lets wireless reflections strike as well as bounce off a human body to show a profile and the actions it takes.

It "can trace a person's hand as he writes in the air and even distinguish between 15 different people through a wall with nearly 90 percent accuracy," MIT said in a press statement.

The identity of the object or person can be captured, based on measurements and related data uploaded through algorithms that can locate physical features.

"[We] use the captured human silhouettes from our reconstruction algorithm [to] train a classifier on these silhouettes which allows us to distinguish between people," Fadel Adi, one of the MIT researchers behind the project, told Gizmodo. "The classifier captures features like height and body builds, which allows us to distinguish between people using RF-Capture."

Even though the real-world application for RF-Capture has not been specifically captured, it could be the foundation for related technologies, such as a monitoring device for the elderly or one to monitor home appliances, according to The Verge.

For more explanation of the RF-Capture, you can go through this link.

YouTube/MITCSAIL 

© 2023 Counsel & Heal All rights reserved. Do not reproduce without permission.

Join the Conversation

Real Time Analytics