Online domain-shift learning and object tracking based on nonlinear dynamic models and particle filters on Riemannian manifolds.
Zulfiqar Hassan KhanIrene Yu-Hua GuPublished in: Comput. Vis. Image Underst. (2014)
Keyphrases
- object tracking
- particle filter
- mean shift
- dynamic model
- visual tracking
- particle filtering
- kalman filter
- multiple object tracking
- image sequences
- robust tracking
- appearance modeling
- video sequences
- data association
- riemannian manifolds
- appearance model
- computer vision
- learning algorithm
- reinforcement learning
- bayesian filtering
- sparse representation
- state space
- tracking framework
- moving objects
- motion model
- experimental data
- higher order
- optical flow
- search algorithm