2012 | OriginalPaper | Buchkapitel
Parallel Clustering of Videos to Provide Real Time Location Intelligence Services to Mobile Users
verfasst von : Alfio Costanzo, Alberto Faro, Simone Palazzo
Erschienen in: Advances in Future Computer and Control Systems
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
Clustering of large datasets has been widely used to retrieve relevant data or to discover novel data associations. Topology preservation of the original dataset is not always mandatory, unless the dataset has a temporal-spatial nature since, in this case, the data in the same cluster as well as the ones of the closest clusters should be related as in the real system. However, only few existing parallel methods preserve the original dataset topology. Also, few times such methods have been used to help the management of real time systems due to their limited parallelism degree. Aim of the paper is to illustrate how such requisites may be fulfilled by using a SOM based parallel clustering method developed recently by the authors. In particular, the clustering of relevant video sequences that helps the management of real time location systems are discussed to point out how this allows us to provide novel location intelligence services to the mobile users.