2010 | OriginalPaper | Buchkapitel
Propagating Uncertainty in Petri Nets for Activity Recognition
verfasst von : Gal Lavee, Michael Rudzsky, Ehud Rivlin
Erschienen in: Advances in Visual Computing
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Petri Nets is a formalism that has recently been proposed for the specification of models for use in activity recognition . This formalism is attractive because of its inherent ability to model partial ordering, concurrency, logical and temporal relations between the events that compose activities. The main novelty of this work is a probabilistic mechanism (based on the particle filter) for recognizing activities modeled as Petri Nets in video. This mechanism takes into account the observation and semantic uncertainty inherent in low-level events and propagates it into a probabilistic activity recognition.