Shape tracking with occlusions via coarse-to-fine region-based sobolev descent
Type
ArticleKAUST Department
Electrical Engineering ProgramApplied Mathematics and Computational Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Visual Computing Center (VCC)
Date
2015-05-01Preprint Posting Date
2012-08-21Permanent link to this record
http://hdl.handle.net/10754/564169
Metadata
Show full item recordAbstract
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.Sponsors
This work was funded by KAUST Baseline and Visual Computing Center funding.arXiv
arXiv:1208.4391Additional Links
http://arxiv.org/abs/arXiv:1208.4391v2ae974a485f413a2113503eed53cd6c53
10.1109/TPAMI.2014.2360380