Visor: Video Surveillance Online Repository
Roberto Vezzani, Rita Cucchiara · IRIS UNIMORE (University of Modena and Reggio Emilia) · 2007
Aim of the Visor Project [1] is to gather and make freely available a repository of surveillance and video footages for the research community on pattern recognition and multimedia retrieval. The goal is to create an open forum and a free repository to exchange, compare and discuss results of many problems in video surveillance and retrieval. Together with the videos, the repository contains metadata annotation, both manually annotated as ground-truth and automatically obtained by video surveillance systems. Annotation refers to a large ontology of concepts on surveillance and security related objects and events. The ontology has been defined including concepts from LSCOM and MediaMill ontologies. As well as videos and annotations, Visor provides tools for enriching the ontology, annotating new videos, searching by textual queries, composing and downloading videos.