Phase-based video motion processing

Abstract

We introduce a technique to manipulate small movements in videos based on an analysis of motion in complex-valued image pyramids. Phase variations of the coefficients of a complex-valued steerable pyramid over time correspond to motion, and can be temporally processed and amplified to reveal imperceptible motions, or attenuated to remove distracting changes. This processing does not involve the computation of optical flow, and in comparison to the previous Eulerian Video Magnification method it supports larger amplification factors and is significantly less sensitive to noise. These improved capabilities broaden the set of applications for motion processing in videos. We demonstrate the advantages of this approach on synthetic and natural video sequences, and explore applications in scientific analysis, visualization and video enhancement.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jul 21, 2013
Source ID
10.1145/2461912.2461966

Entities

People

  • Frédo Durand
  • Michael Rubinstein
  • Neal Wadhwa
  • William T. Freeman

Organizations

  • Defense Advanced Research Projects Agency
  • Massachusetts Institute of Technology
  • Microsoft Research
  • National Science Foundation
  • United States Department of Defense

Tags

Readers

  • Atmospheric Science / Meteorology, specifically Wind Wave Turbulence.
  • Computer Vision.
  • Image Processing and Computer Vision.