English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a method to track the precise shape of an object in video based onnew modeling and optimization on a new Riemannian manifold of parameterizedregions.  Joint dynamic shape and appearance models, in which a template of the objectis propagated to match the object shape and radiance in the next frame, areadvantageous over methods employing global image statistics in cases of complexobject radiance and cluttered background. In cases of 3D object motion andviewpoint change, self-occlusions and dis-occlusions of the object areprominent, and current methods employing joint shape and appearance models areunable to adapt to new shape and appearance information, leading to inaccurateshape detection. In this work, we model self-occlusions and dis-occlusions in ajoint shape and appearance tracking framework.  Self-occlusions and the warp to propagate the template are coupled, thus ajoint problem is formulated. We derive a coarse-to-fine optimization scheme,advantageous in object tracking, that initially perturbs the template by coarseperturbations before transitioning to finer-scale perturbations, traversing allscales, seamlessly and automatically. The scheme is a gradient descent on anovel infinite-dimensional Riemannian manifold that we introduce. The manifoldconsists of planar parameterized regions, and the metric that we introduce is anovel Sobolev-type metric defined on infinitesimal vector fields on regions.The metric has the property of resulting in a gradient descent thatautomatically favors coarse-scale deformations (when they reduce the energy)before moving to finer-scale deformations.  Experiments on video exhibiting occlusion/dis-occlusion, complex radiance andbackground show that occlusion/dis-occlusion modeling leads to superior shapeaccuracy compared to recent methods employing joint shape/appearance models oremploying global statistics.

Shape Tracking With Occlusions via Coarse-To-Fine Region-Based Sobolev Descent