Wi-fi signals have been used to ‘see’ through walls, and the technology could be used to protect the elderly.
MIT computer science researchers have developed a sensor that sends radio signals through a wall and can identify the shapes of people who are on the other side.
They plan to launch a start-up company in 2016 to commercialise the technology, and say one of the main uses could be to determine whether an older person has had a fall in their home.
MIT professor Dina Katabi said: ‘We’re working to turn this technology into an in-home device that can call 911 if it detects that a family member has fallen unconscious.
‘You could also imagine it being used to operate your lights and TVs, or to adjust your heating by monitoring where you are in the house.’
It works by monitoring the radio signals as they bounce back off a person, and the device stitches these signals together to create an identifiable silhouette.
The system isn’t perfect – yet. It can identify between five people with 95.7% accuracy and 15 people with 88.2% accuracy.
Researchers also managed to identify which body part someone was moving while standing almost three metres away.
The technology currently only works when a person is walking towards the sensor. People travelling at angles are much harder to pick out.
it will be presented at a conference in Japan next month, when the team is likely to address privacy concerns.
The team says the sensor could be improved so that it can see through multiple walls and see as far as 12m away.