Researchers develop algorithm to turn a smartphone into an echolocation device

A group of researchers at the University of Glasgow developed a machine-learning algorithm that uses reflected echoes to create three-dimensional images of the surrounding environment.

According to the inventors, it could, for example, be used to catch burglars or to monitor patients without the use of cameras.

The system analyzes sounds from speakers or radio waves emitted by antennas. The algorithm measures how long these signals take to bounce off a wall and return to the sensor.

It then computes the room’s shape, size and layout, and detects the presence of objects or people. The resulting data are transformed by the system into three-dimensional images in the form of a video stream.

The developers compared the algorithm’s principle to the senses of bats and said it could run on any smartphone or laptop.

“First, to create three-dimensional images, data from only one input — a microphone or an antenna — are required. Second, we believe that the algorithm we developed can turn any device with one of these elements into an echolocation device,” said the study’s lead author, Dr. Alex Terpin.

Researchers also believe that their algorithm could substantially reduce the cost of creating 3D images.

In April 2021, MIT researchers see through walls using radio-frequency identification.

In March, the US Food and Drug Administration AI device for detecting hidden signs of COVID-19 in asymptomatic carriers of the infection.

In February, Google unveiled a technology for measuring heart rate and breathing rate using a smartphone camera.

Subscribe to ForkLog News on Telegram: ForkLog AI — all the news from the world of AI!