Layered Active Contours for Tracking

View/ Open
Date
2007-09Author
Pryor, Gallagher D.
Vela, Patricio A.
Rehman, Tauseef ur
Tannenbaum, Allen R.
Metadata
Show full item recordAbstract
This paper deals with the task of object tracking in the presence of occlusions and clutter by fitting a layered appearance model to data. Four major problems must be overcome: (1) the association of each pixel to a particular layer (layer segmentation), (2) the determination of layer support, (3) the determination of layer appearance, and (4) determination of layer location. Tao, Sawhney, and Kumar successfully proposed a generalized expectation maximization algorithm solving these problems by directly inferring masks representing layer segmentation in conjunction with a deforming elliptical shape prior defining layer support. We extend their work with the introduction of active contours: instead of directly inferring these masks, we evolve a series of curves to obtain a layer segmentation. These curves provide a natural shape prior by constraining segmentations to a family of curves local to layer supports and allow for non-rigid layer deformations through the prediction of unobserved appearance information during inference. A benefit of this extension is the ability to track through massive occlusions and clutter, as demonstrated on a series of difficult real-world video sequences.