A Layered Motion Representation with Occlusion and Compact Spatial Support

We describe a 2.5D layered representation for visual motion analysis. The representation provides a global interpretation of image motion in terms of several spatially localized foreground regions along with a background region. Each of these regions comprises a parametric shape model and a parametric motion model. The representation also contains depth ordering so visibility and occlusion are rightly included in the estimation of the model parameters. Finally, becausethe number of objects, their positions, shapesand sizes, and their relative depths are all unknown, initial models are drawn from a proposal distribution, and then compared using a penalized likelihood criterion. This allows us to automatically initialize new models, and to compare different depth orderings.

• Type: Conference
• Year: 2002
• Where: ECCV
• Authors: Allan D. Jepson, David J. Fleet, Michael J. Black
• Keywords: 2.5D Layered Representation, Computer Vision, ECCV 2002, Parametric Motion Model, Parametric Shape Model, Penalized Likelihood Criterion, Visual Motion Analysis