Material Detail

MoT - Mixture of Trees Probabilistic Graphical Model for Video Segmentation

MoT - Mixture of Trees Probabilistic Graphical Model for Video Segmentation

This video was recorded at British Machine Vision Conference (BMVC), Surrey 2012. We present a novel mixture of trees (MoT) graphical model for video segmentation. Each component in this mixture represents a tree structured temporal linkage between super-pixels from the first to the last frame of a video sequence. Our time-series model explicitly captures the uncertainty in temporal linkage between adjacent frames which improves segmentation accuracy. We provide a variational inference scheme for this model to estimate super-pixel labels and their confidences in nearly realtime. The efficacy of our approach is demonstrated via quantitative comparisons on the challenging SegTrack joint segmentation and tracking dataset.

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Browse...

Disciplines with similar materials as MoT - Mixture of Trees Probabilistic Graphical Model for Video Segmentation

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.