Title :
Boosted Tracking in Video
Author :
Boccignone, Giuseppe ; Campadelli, Paola ; Ferrari, Alessandro ; Lipori, Giuseppe
Author_Institution :
Dipt. di Sci. dellTnformazione, Univ. degli Studi di Milano, Milan, Italy
Abstract :
We discuss how a probabilistic interpretation of the output provided by a cascade of boosted classifiers can be exploited for Bayesian tracking in video streams. In particular, real-time face and body detection can be achieved by relying on such a Bayesian framework. Results show that such integrated approach is appealing with respect both to robustness and computational efficiency.
Keywords :
belief networks; face recognition; object detection; probability; tracking; video streaming; Bayesian tracking; boosted video tracking; real-time body detection; real-time face detection; video streams; Boosted classifiers; face detection; object tracking; particle filtering; pedestrian detection;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2009.2030862
