Your humble Wi-Fi router (opens in a new tab) the signal can be used to track your movements around the room, like a bat, a new report claims.
Researchers at Carnegie Mellon University recently published a report detailing an experiment using ordinary off-the-shelf Wi-Fi routers to detect people’s locations as well as their position in a room.
The experiment, while not without its flaws, was an overall success, proving that endpoints could be used to track people. It is described as an ethical and privacy-sensitive way to monitor (mostly elderly and lonely) people.
In layman’s terms, the Wi-Fi signal transmitted through routers can be used as a type of sonar where an AI-based program analyzes the difference in density between outgoing and incoming signals and returns with skeletal images of people in the room.
In some cases, the images returned incomplete or showed people in strange, unnatural poses, showing that the method obviously still needs work. But in many cases, the images created by the AI were quite accurate. The positions of the people in the room were accurate, their measurements were accurate, their poses were accurate.
Aside from the occasional rendering glitch, another major challenge is being able to track more people. So far, routers are able to successfully track up to three people.
For the experiment, the researchers used TP-Link Archer A7 AC1750 devices, which cost a measly $ 32. Compared to other tracking technologies such as LIDAR or radar, using Wi-Fi routers for this purpose is much cheaper. In some cases, routers can even be a better solution than cameras, given that they work even when people are hidden behind objects such as furniture.
It looks like the researchers will continue their work trying to improve the solution through better public training data on Wi-Fi-based perception.
Through: Tom’s gear (opens in a new tab)