Video search makes phone a ‘second pair of eyes’

October 26, 2007 | Source: NewScientist.com news service

Researchers at Accenture Technology Labs in France have developed the “Pocket Supercomputer,” which automatically identifies objects in a video, using any ordinary 3G cellphone equipped with a video camera.

Live video footage is fed from the cellphone to a central server, which rapidly matches on-screen objects to images previously entered into a database, using a scale-invariant feature transform algorithm. The server then sends relevant information back to the user.