AI smart home system sees through walls
The project, called “RF-Pose,” uses artificial intelligence (AI) to teach wireless devices to sense people’s postures and movement, even from the other side of a wall. Such a system, say the researchers, could serve as a health care system used to monitor diseases and help the elderly “age in place.”
For example, they say, RF-Pose could be used to monitor diseases like Parkinson’s, multiple sclerosis (MS), and muscular dystrophy, and provide a better understanding of disease progression while allowing doctors to adjust medications accordingly. It could also help elderly people live more independently, while providing the security of monitoring for falls, injuries, and changes in activity patterns.
“We’ve seen that monitoring patients’ walking speed and ability to do basic activities on their own gives health care 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 from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), who 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.”
The system is based on wireless signals in the Wi-Fi frequencies that can traverse walls and reflect off the human body. The researchers use a neural network to analyze such radio signals, and then create a dynamic stick figure that walks, stops, sits, and moves its limbs as the person performs those actions.
To train their neural network, the researchers used both their wireless device and a camera to gather thousands of images of people doing activities like walking, talking, sitting, opening doors, and waiting for elevators. They then used the images from the camera to extract the stick figures, which they showed to the neural network along with the corresponding radio signal, enabling the system to learn the association between the radio signal and the stick figures of the people in the scene.
The researchers also showed that, in addition to sensing movement, the wireless signals could be used to accurately identify somebody 83% of the time out of a line-up of 100 individuals. This ability could be particularly useful for applications such as search-and-rescue operations, say the researchers, when it may be helpful to know the identity of specific people.
The researchers are currently working with doctors to explore RF-Pose’s applications in health care. They are also working to create 3D representations – rather than the 2D models used in the paper – that would be able to reflect even smaller micromovements, such as a person’s hands shaking.
For future real-world applications, the researchers plan to implement a “consent mechanism” in which the person who installs the device is cued to do a specific set of movements in order for it to begin to monitor the environment. Besides health care, say the researchers, RF-Pose could also be used for new classes of video games where players move around the house.
For more, see “Through-Wall Human Pose Estimation Using Radio Signals.” (PDF)
Related articles:
3D through-wall imaging achieved with drones and Wi-Fi
Through-Wall sensing system uses software-defined radio
Laser imaging technology sees around corners
MIT system lets Wi-Fi locate users within tens of centimeters
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
