Combining Foreground / Background Feature Points and Anisotropic Mean Shift For Enhanced Visual Object Tracking.
Sebastian HanerIrene Yu-Hua GuPublished in: ICPR (2010)
Keyphrases
- feature points
- visual object tracking
- mean shift
- foreground and background
- object tracking
- image sequences
- pose estimation
- robust tracking
- visual tracking
- graph cuts
- point correspondences
- partial occlusion
- particle filter
- feature space
- kalman filter
- background subtraction
- color histogram
- camera motion
- reinforcement learning
- face images
- dynamic programming
- feature selection
- feature extraction