AI System Can See Human Movement Through Walls

A new AI system that and see human movements through walls has been developed by a research team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL).
The new system is called RF-Prose. RF-Prose uses AI to teach wireless devices to detect and sense a person’s movement or position through a wall. The system uses a neural network to detect and analyze the radio signals that bounce off of people’s bodies. It then creates a dynamic stick figure that can walk, stop, sit, and move like a human. RF-Prose could be used to monitor diseases like Parkinson’s or MS, to better understand the development of these diseases and help doctors adjust medications for each individual patient. The system could also help elderly people live more independently by adding an extra level of security that monitors accidents and activity changes in the person’s life. RF-Prose could also be used for new video games and in search-and-rescue missions.
"We've seen that monitoring patients' walking speed and ability to do basic activities on their own gives healthcare providers a window into their lives that they didn't have before, which could be meaningful for a whole range of diseases," says Professor Dina Katabi , who led the team and co-wrote a new paper about the project. "A key advantage of our approach is that patients do not have to wear sensors or remember to charge their devices."
There was one main challenge that the researchers faced when developing RF-Prose. Most neural networks are trained using data that has been labeled by humans. But RF-Prose uses radio frequencies, which are nearly impossible to label by hand. This problem was solved by the researchers collecting examples of radio frequencies bouncing of human bodies with a wireless device and a camera. Thousands of images of people in various activities, like walking, waiting for an elevator and more, were taken.
Once the images were taken, a stick figure of the human’s general pose was created. The stick figures and images were shown to the neural network with a corresponding radio signal. These examples allowed the system to learn what radio signals were associated with the stick figures and positions.
After training, the RF-Prose was able to estimate a person’s posture and movements with only the radio waves that bounce off of people’s bodies.
One thing that the system was never trained on was to read through walls because cameras can’t see through walls. RF-Prose taught itself to detect and analyze the radio signals coming through a wall and it was able to figure out what a person’s position is on the other side of the wall.
The system was also able to recognize a specific person out a 100-person line up with 83% accuracy. This is an important ability if the system is going to be used in a search-and-rescue mission.
The paper on this research will be presented at the Conference on Computer Vision and Pattern Recognition (CVPR) in Salt Lake City, Utah.

Views: 80

©ictnews.az. All rights reserved.

Facebook Google Favorites.Live BobrDobr Delicious Twitter Propeller Diigo Yahoo Memori MoeMesto

18 October 2018

Azerpost LLC announced winner of bank nomination

Azerpost LLC, the national postal operator of Azerbaijan, was announced the winner of the bank nomination

NASA is Working on a Conceptual Human-Crewed Mission to Venus

Although Venus is probably not the number one destination for aspiring space tourists due to it being a hellish 

Qualcomm unveils 60 GHz Wi-Fi chipsets for WiGig devices

Qualcomm Technologies announced a family of 60 GHz Wi-Fi chipsets, the QCA64x8 and QCA64x1, noting 

Robot Pepper speaks before U.K. Parliament

SoftBank Group Corp.’s Pepper humanoid robot testified on Tuesday at the Education Committee of Britain’s

This App Checks How You Type And Use Your Phone, To Predict And Warn You If You Are Depressed

According to the World Health Organization, approximately 300 million people around the world suffer from depression 

Huawei’s Nano Memory Cards are replacing microSD on its latest phones

Alongside the slate of new phones Huawei announced today was an interesting addition: a new type of expandable

UK Gov makes bold steps to tackle long-ignored security problem

The Department for Digital, Culture, Media and Sport (DCMS) and the National Cyber Security Centre (NCSC)

Chrome 70 arrives with fingerprint login for websites, extension controls, and 23 security fixes

Google has released Chrome 70, which addresses several high severity security issues, and brings new support 

17 10 2018

Malwarebytes says business cyberattacks surged 55% in Q3, but malicious cryptocurrency mining fell 26%

Cybercriminals seem to be increasingly concentrating their significant firepower on businesses and their treasure

Chinese Scientists Develop Nanogenerator to Power Wearable Electronics

Chinese scientists have developed a new nanogenerator that can harvest energy from human motions to continuously

TSA lays out plans to use facial recognition for domestic flights

The airport security experience is about to see facial recognition technology taking on a bigger role, as TSA today

IBM will use AI to address problems of cybersecurity

In recent years, hackers and other cybercriminals invent new means to steal data or harm to companies and

Facebook Messenger soon to add option to Unsend messages

Facebook promised to bring users the option to delete/unsend messages for some time now, but the social network 

Huawei Mate 20 And Mate 20 Pro Are Official: Features Different Notch Designs, Triple-Lens Camera And More

After resting in the rumor mill for quite some time, Huawei’s Mate 20 is now official with a bunch of