Hierarchical Probabilistic Models for Video Object Segmentation and Tracking

  • Authors:

  • David Thirde;Graeme Jones

  • Affiliations:

  • Kingston University, UK;Kingston University, UK

  • Venue:
  • ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

When tracking and segmenting semantic video objects, different forms of representational model can be used to find the object region on a per-frame basis. We propose a novel hierarchical technique using parametric models to describe the appearance and location of an object and then use non-parametric methods to model the sub-object regions for accurate pixel-wise segmentation. Our motivation is to use parametric models to locate the object, improving the sensitivity of the non-parametric sub-object region models to background clutter. The results indicate this is a promising approach to extracting video objects.