On line predictive appearance-based tracking

We present a novel predictive statistical framework to improve the performance of an eigentracker. In addition, we use fast and efficient eigenspace updates to learn new views of the object being tracked on the fly. We also incorporate a new importance sampling mechanism which increases the robustne...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Gupta, N., Mittal, P., Patwardhan, K.S., Dutta Roy, S., Chaudhury, S., Banerjee, S.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Active appearance model Active shape model Applied sciences Artificial intelligence Computer science control theory systems Exact sciences and technology Image reconstruction Monte Carlo methods Parameter estimation Pattern recognition. Digital image processing. Computational geometry Robustness State estimation Symbiosis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	We present a novel predictive statistical framework to improve the performance of an eigentracker. In addition, we use fast and efficient eigenspace updates to learn new views of the object being tracked on the fly. We also incorporate a new importance sampling mechanism which increases the robustness of the eigentracker and enables it to track nonconvex objects better. Our eigentracker is flexible-it is possible to use it symbolically with other trackers. We show its successful application in hand gesture analysis; and face and person tracking.
ISSN:	1522-4880 2381-8549
DOI:	10.1109/ICIP.2004.1419480