We are searching data for your request:
Upon completion, a link will appear to access the found materials.
Researchers have been working on this technology since the 1970s, and it is becoming more and more accurate.
Anyone who has been intrigued by the X-ray spec ads on the back of a comic will appreciate MIT's latest work, advancing the technology to "see" through walls.
Using Wi-Fi, a team from the Computer Science and Artificial Intelligence Laboratory (CSAIL) can now "see" a person on the other side of the wall and track their movements precisely, even if it is something as subtle as moving. fingers, according to new research to be presented at the Conference on Computer Vision and Pattern Recognition next week.
"People have been trying to detect people through walls since the 1970s," said Dina Katabi, CSAIL professor and lead researcher on the project. “Around 2013, we showed that we can track people accurately. What's new here is that, for the first time, we can create a dynamic skeleton of the person, their posture and how they move.
Katabi told me that earlier versions of the technology his team developed were tables to give you the position of the person and a vague type of contour, similar to a smudge, but not precise movements. Now, they say they have been able to train a neural network to interpret the way in which Wi-Fi radio signals bounce off a person's body and translate it into the movement of 14 different key points on the body, including the head, elbows. and knees.
There was no set of data to train the AI, so the team had to create them, manually creating human movement figures based on images they captured via the wireless device and a camera. By displaying the figures to the neural network along with the Wi-Fi signals, the network was able to learn which radio signals were generated by each movement.
"Let's say the police want to use that device to see behind a wall," Katabi explained. “It is very important to know if someone is in a position that indicates that they have a weapon, for example. All of that cannot be done with just one blob. "
Along with law enforcement applications, Katabi said the technology could be used for interactive games. But the team's main focus is on healthcare applications, particularly for neurodegenerative diseases like Parkinson's, Alzheimer's and Multiple Sclerosis. They have been working with experts in the treatment of each of these diseases, where being able to monitor a patient's daily movements and gait with precision would provide doctors with a wealth of information that they cannot obtain after a half hour of monitoring.
Of course, once you start introducing something like that, people naturally start to worry that the government might use it to spy on us through the walls. Katabi said privacy is something they are deeply aware of when developing new technologies like this.
"Particularly in the current climate, this is an important question," Katabi said. “We have developed mechanisms to block the use of technology, and it anonymizes and encrypts the data. And then there is a policy role that protects the user and does not stifle innovation. "
Privacy is always going to be a concern with new technology, especially something that can be seen through walls, but it also comes with many possible benefits.
Original article (in English)