MPEG-7 Pictorially Enriched Ontologies for Video Annotation
Costantino Grana, Roberto Vezzani, Daniele Bulgarelli, Rita Cucchiara · 2006
A system for the automatic creation of Pictorially Enriched Ontologies is presented, that is ontologies for context-based video digital libraries, enriched by pictorial concepts for video annotation, summarization and similarity-based retrieval. Extraction of pictorial concepts with video clips clustering, ontology storing with MPEG-7, and the use of the ontology for stored video annotation are described. Results on sport videos and TRECVID2005 video material are reported.