Communications of the ACM
Footstep Sensors Identify People by Gait
A team of researchers has developed remote sensors that analyze footsteps by measuring minute floor vibrations.
Credit: Thinkstok
Researchers at Carnegie Mellon University (CMU) have developed sensors that analyze footsteps by measuring minute floor vibrations.
The vibrations can be used to identify specific individuals, and to test a new method of hands-off health monitoring.
The sensors are cylindrical devices a few centimeters tall that sit on the floor and can sense a walker up to 20 meters away.
The sensors are distributed as an array throughout the area where they are to detect footsteps.
The sensitive detectors pick up a lot more noise in a busy building, so the researchers had to teach the system to distinguish footsteps from background noise.
Said researcher Hae Young Noh, "We do various signal-processing and machine-learning [techniques] to learn what is the human-related signal versus other noise that we’re not interested in."
From Scientific American
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found