Forgot your password?
Input Devices Technology

Gesture Recognition Without Batteries 22

Posted by Soulskill
from the how-talking-with-your-hands-becomes-untenable dept.
An anonymous reader sends this news from the University of Washington: "[C]omputer scientists have built a low-cost gesture recognition system that runs without batteries and lets users control their electronic devices hidden from sight with simple hand movements. The prototype, called 'AllSee,' uses existing TV signals as both a power source and the means for detecting a user's gesture command (PDF). 'This is the first gesture recognition system that can be implemented for less than a dollar and doesn't require a battery,' said Shyam Gollakota, a UW assistant professor of computer science and engineering. 'You can leverage TV signals both as a source of power and as a source of gesture recognition.' The researchers built a small sensor that can be placed on an electronic device such as a smartphone. The sensor uses an ultra-low-power receiver to extract and classify gesture information from wireless transmissions around us. When a person gestures with the hand, it changes the amplitude of the wireless signals in the air. The AllSee sensors then recognize unique amplitude changes created by specific gestures."

This discussion has been archived. No new comments can be posted.

Gesture Recognition Without Batteries

Comments Filter:
  • To the Arduino! (Score:2, Informative)

    by Anonymous Coward on Saturday March 01, 2014 @04:08PM (#46377369)

    I'm throwing things down on my breadboard as I speak.

    Think about it this way, Radio waves are just electromagnetic waves like light. It's all around us. Our eyes can detect it bouncing off other things. This is just a eye that can detect the radio waves reflecting off of things. Astronomers do this all the time with radio telescopes, which I would figure these guys used a bunch of their concepts for this.
    The really major part of doing this is knocking out the noise to be able to discern the motion. That, I expect, would have to be using doppler effect techniques. All of these things have been really been developed for meteorology, astronomy, radar, etc. This is just bringing the idea to the near field.
    Looking at the oscilloscope is really very cool how well it's filtered out and is really only the motion signal.

Whoever dies with the most toys wins.