Self-Aiming Camera

Posted 9 May 2001 at 14:01 UTC by steve Share This

Researchers at the Beckman Institute's AI Group and Robot Vision Lab have developed a new camera system that uses both audio and visual cues to point itself toward "interesting" activity. The camera is controlled by a neural network that simulates the superior colliculus of the human brain. A wide angle camera and two microphones are used to localize activity and a second camera with a tighter view is then directed towards the desired area. The system contains a database of sounds to help it determine what types of sound are interesting and, over time, it learns to associate sounds with the visual targets that make them.

See more of the latest robot news!

Recent blogs

30 Sep 2017 evilrobots (Observer)
10 Jun 2017 wedesoft (Master)
9 Jun 2017 mwaibel (Master)
25 May 2017 AI4U (Observer)
25 Feb 2017 steve (Master)
16 Aug 2016 Flanneltron (Journeyer)
27 Jun 2016 Petar.Kormushev (Master)
2 May 2016 motters (Master)
10 Sep 2015 svo (Master)
14 Nov 2014 Sergey Popov (Apprentice)
Share this page