Sign In

Communications of the ACM

ACM TechNews

Software Detects Motion That the Human Eye Can't See

MIT Associate Professor Fredo Durand

Fredo Durand, associate professor of computer science at MIT, developed an algorithm that can highlight slight variations in the visual elements in nearly any video.

Credit: Technology Review

Massachusetts Institute of Technology (MIT) researchers have developed the Eulerian video magnification process, a set of software algorithms that can amplify certain aspects of a video and reveal what is normally undetectable to the human eye. The process deconstructs the visual elements of each frame of a video and reconstructs them with the algorithm.

"Just like optics has enabled [someone] to see things normally too small, computation can enable people to see things not visible to the naked eye," says MIT's Fredo Durand. He predicts the primary application will be for remote medical diagnostics, but it also could be used to detect any small motion. Durand notes that any video footage can be deconstructed, although the outcome of using the program varies according to the footage's quality.

"What's really nice about this technique is that it can just take standard video, from just about any device, and then process it in a way that finds this hidden information in the signal," says University of California, Berkeley professor Maneesh Agrawala.

From Technology Review
View Full Article


Abstracts Copyright © 2012 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account