Probabilistic data association methods for tracking complex visual objects

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 23, Issue 6, 2001, Pages 560-576

  Rasmussen, Christopher ^a,b   Hager, Gregory D ^a,c  

^a IEEE   (United States)

^b NATIONAL INSTITUTE OF STANDARDS AND TECHNOLOGY   (United States)

^c Johns Hopkins University   (United States)

Author keywords

Color regions; Data association; Snakes; Textured regions; Visual tracking

Indexed keywords

DATA ASSOCIATION; TEXTURED REGIONS; VISUAL TRACKING;

ALGORITHMS; CONSTRAINT THEORY; IMAGING TECHNIQUES; MOTION COMPENSATION; PROBABILISTIC LOGICS; RANDOM PROCESSES; ROBUSTNESS (CONTROL SYSTEMS); TRACKING (POSITION);

COMPUTER VISION;

EID: 0035363738     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/34.927458     Document Type: Article

References (35)

1. A new approach to linear filtering and prediction problems
2. Pattern theory: A unifying perspective
3. Condensation-conditional density propagation for visual tracking
4. Introduction: A bayesian formulation of visual perception
5. A physical approach to color image understanding
6. An iterative image registration technique with an application to stereo vision
7. Good features to track
8. Efficient region tracking with parametric models of geometry and illumination
9. Learning to track the visual motion of contours
10. Tracking with kalman snakes
11. A computational approach to edge detection
12. An isotropic 3 × 3 image gradient operator
13. Contour tracking by stochastic propagation of conditional density
14. Hierarchical model-based motion estimation
15. A review of statistical data association techniques for motion correspondence
16. Robust multiple car tracking with occlusion reasoning
17. Model-based tracking of self-occluding articulated objects
18. Tracking people with twists and exponential maps
19. Human motion analysis based on a robot arm model
20. Motion regularization for model-based head tracking
21. Singularity analysis for articulated object tracking
22. Recovery of nonrigid motion and structure
23. A probabilistic exclusion principle for tracking multiple objects
24. A multiple hypothesis approach to figure tracking