CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2011 vol.33 Issue No.03 - March
Issue No.03 - March (2011 vol.33)
Thomas Brox , University of California at Berkeley, Berkeley
Jitendra Malik , University of California at Berkeley, Berkeley
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.
Motion, video, optical flow.
Thomas Brox, Jitendra Malik, "Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.33, no. 3, pp. 500-513, March 2011, doi:10.1109/TPAMI.2010.143