Dense point trajectories by GPU-accelerated large displacement optical flow

N. Sundaram, Thomas Brox, K. Keutzer
European Conference on Computer Vision (ECCV), Springer, LNCS, Sept. 2010
Abstract: Dense and accurate motion tracking is an important requirement for many video feature extraction algorithms. In this paper we provide a method for computing point trajectories based on a fast parallel implementation of a recent optical ow algorithm that tolerates fast motion. The parallel implementation of large displacement optical ow runs about 78x faster than the serial C++ version. This makes it practical to use in a variety of applications, among them point tracking. In the course of obtaining the fast implementation, we also proved that the fixed point matrix obtained in the optical ow technique is positive semi-definite. We compare the point tracking to the most commonly used motion tracker - the KLT tracker - on a number of sequences with ground truth motion. Our resulting technique tracks up to three orders of magnitude more points and is 46% more accurate than the KLT tracker. It also provides a tracking density of 48% and has an occlusion error of 3% compared to a density of 0.1% and occlusion error of 8% for the KLT tracker. Compared to the Particle Video tracker, we achieve 66% better accuracy while retaining the ability to handle large displacements while running an order of magnitude faster.

Other associated files : sundaram_eccv10.pdf [5.1MB]  

Images and movies


BibTex reference

  author       = "N. Sundaram and T. Brox and K. Keutzer",
  title        = "Dense point trajectories by GPU-accelerated large displacement optical flow",
  booktitle    = "European Conference on Computer Vision (ECCV)",
  series       = "Lecture Notes in Computer Science",
  month        = "Sept.",
  year         = "2010",
  publisher    = "Springer",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2010/Bro10e"

Other publications in the database