Eulerian video magnification and analysis
Abstract
The world is filled with important, but visually subtle signals. A person's pulse, the breathing of an infant, the sag and sway of a bridge---these all create visual patterns, which are too difficult to see with the naked eye. We present Eulerian Video Magnification, a computational technique for visualizing subtle color and motion variations in ordinary videos by making the variations larger. It is a microscope for small changes that are hard or impossible for us to see by ourselves. In addition, these small changes can be quantitatively analyzed and used to recover sounds from vibrations in distant objects, characterize material properties, and remotely measure a person's pulse.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Dec 20, 2016
- Source ID
- 10.1145/3015573
Entities
People
- Abe Davis
- Eugene Shih
- Frédo Durand
- Gautham J. Mysore
- Hao-yu Wu
- John V. Guttag
- Justin G. Chen
- Michael Rubinstein
- Neal Wadhwa
- Oral Buyukozturk
- William T. Freeman
Organizations
- Adobe
- Defense Advanced Research Projects Agency
- Massachusetts Institute of Technology
- Microsoft Research
- National Science Foundation