Region based pose tracking with occlusions using 3D models

C. Schmaltz, B. Rosenhahn, Thomas Brox, J. Weickert
Machine Vision and Applications, 23(3): 557-577, 2012
Abstract: Despite great progress achieved in 3-D pose tracking during the past years, occlusions and self-occlusions are still an open issue. This is particularly true in silhouette-based tracking where even visible parts cannot be tracked as long as they do not affect the object silhouette. Multiple cameras or motion priors can overcome this problem. However, multiple cameras or appropriate training data are not always readily available. We suggest to handle occlusions and self-occlusions by tracking multiple objects and object parts simultaneously, where each part is described by its own region. This allows to deal with occlusions explicitly, which includes self-occlusions between different parts of the same object as well as occlusions between different objects. The results we present for simulations and real-world scenes demonstrate the improvements achieved in monocular and multi-camera settings. These improvements are substantiated by quantitative evaluations, e.g., based on the HumanEVA benchmark.
Publisher's link

Other associated files : schmaltz_mva11.pdf [8.7MB]  

Images and movies


BibTex reference

  author       = "C. Schmaltz and B. Rosenhahn and T. Brox and J. Weickert",
  title        = "Region based pose tracking with occlusions using 3D models",
  journal      = "Machine Vision and Applications",
  number       = "3",
  volume       = "23",
  pages        = "557-577",
  year         = "2012",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2012/Bro12a"

Other publications in the database