Shape tracking with occlusions via coarse-to-fine region-based sobolev descent

Yanchao Yang, Ganesh Sundaramoorthi

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

Abstract

We present a method to track the shape of an object from video. The method uses a joint shape and appearance model of the object, which is propagated to match shape and radiance in subsequent frames, determining object shape. Self-occlusions and dis-occlusions of the object from camera and object motion pose difficulties to joint shape and appearance models in tracking. They are unable to adapt to new shape and appearance information, leading to inaccurate shape detection. In this work, we model self-occlusions and dis-occlusions in a joint shape and appearance tracking framework. Self-occlusions and the warp to propagate the model are coupled, thus we formulate a joint optimization problem. We derive a coarse-to-fine optimization method, advantageous in tracking, that initially perturbs the model by coarse perturbations before transitioning to finer-scale perturbations seamlessly. This coarse-to-fine behavior is automatically induced by gradient descent on a novel infinite-dimensional Riemannian manifold that we introduce. The manifold consists of planar parameterized regions, and the metric that we introduce is a novel Sobolev metric. Experiments on video exhibiting occlusions/dis-occlusions, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy. © 2014 IEEE.
Original languageEnglish (US)
Pages (from-to)1053-1066
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume37
Issue number5
DOIs
StatePublished - May 1 2015

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Software
  • Applied Mathematics
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Shape tracking with occlusions via coarse-to-fine region-based sobolev descent'. Together they form a unique fingerprint.

Cite this