Home
Uni-Logo
 

Large displacement optical flow: descriptor matching in variational motion estimation

Thomas Brox, J. Malik
IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3): 500-513, 2011
Abstract: Optical flow estimation is classically marked by the requirement of dense sampling in time. While coarse-to-fine warping schemes have somehow relaxed this constraint, there is an inherent dependency between the scale of structures and the velocity that can be estimated. This particularly renders the estimation of detailed human motion problematic, as small body parts can move very fast. In this paper, we present a way to approach this problem by integrating rich descriptors into the variational optical flow setting. This way we can estimate a dense optical flow field with almost the same high accuracy as known from variational optical flow, while reaching out to new domains of motion analysis where the requirement of dense sampling in time is no longer satisfied.
Publisher's link Downloads

Other associated files : brox_tpami10_ldof.pdf [19.1MB]  

Images and movies

 

BibTex reference

@Article{Bro11a,
  author       = "T. Brox and J. Malik",
  title        = "Large displacement optical flow: descriptor matching in variational motion estimation",
  journal      = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
  number       = "3",
  volume       = "33",
  pages        = "500-513",
  year         = "2011",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2011/Bro11a"
}

Other publications in the database