Abstract | ||
---|---|---|
A novel system for long-term tracking of a human face in unconstrained videos is built on Tracking-Learning-Detection (TLD) approach. The system extends TLD with the concept of a generic detector and a validator which is designed for real-time face tracking resistent to occlusions and appearance changes. The off-line trained detector localizes frontal faces and the online trained validator decides which faces corre- spond to the tracked subject. Several strategies for build- ing the validator during tracking are quantitatively evaluated. The system is validated on a sitcom episode (23 min.) and a surveillance (8 min.) video. In both cases the system detects- tracks the face and automatically learns a multi-view model from a single frontal example and an unlabeled video. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICIP.2010.5653525 | IEEE Internet Computing |
Keywords | Field | DocType |
face recognition,object tracking,video signal processing,Face-TLD,generic detector,human face,long-term tracking,multiview model,occlusion,offline trained detector,online trained validator,real-time face tracking resistent,tracking-learning-detection,unconstrained video,unlabeled video,detection,learning,long-term face tracking,real-time,verification | Computer vision,Facial recognition system,Pattern recognition,Visualization,Computer science,Video tracking,Artificial intelligence,Detector,Facial motion capture,Trajectory,Validator | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4244-7993-1 | 978-1-4244-7993-1 | 49 |
PageRank | References | Authors |
1.89 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zdenek Kalal | 1 | 1023 | 36.85 |
Krystian Mikolajczyk | 2 | 7280 | 625.08 |
Jiri Matas | 3 | 53 | 2.35 |