Related resources
Search for item elsewhere
University researcher(s)
Academic department(s)
An Efficient Event Definition Framework for Retail Sector Surveillance Systems
Fahad Anwar, Ilias Petrounias, Sandra Sampaio, Vassilis Kodogiannis, Tim Morris
In: Anwar, Fahad; Petrounias, Ilias; Sampaio, Sandra; Kodogiannis, Vassilis; Morris, Tim. The Sixth International Conferences on Advances in Multimedia MMEDIA ; 23 Feb 2014-27 Feb 2014; Nice, France. 2014.
Access to files
Full-text and supplementary files are not available from Manchester eScholar. Use our list of Related resources to find this item elsewhere. Alternatively, request a copy from the Library's Document supply service.
Abstract
Event representation models provide a framework in which we can reason about events so as to interpret the collective behaviour of objects over time and space domains. Many are context-specific and lack flexibility when faced with unstructured video. In the past many efforts have been made to define a comprehensive event description framework (EDF), which can provide a framework to develop ontologies for semantic annotation of video events. However, it is observed that there are some areas of event modelling that were not fully explored. Hence, we extended and modified the EDF and proposed the extended version of it (EDFE). Following are some of the major extensions we have proposed in EDFE. 1) EDFE extends the entity representation model of EDF by introducing three new entity classes: that of text entity, virtual entity and internal entity. II) EDFE introduces a new set of predicates for describing more complex event scenarios and facilitating the event detection process. It also introduces granularity as a feature of temporal predicates to capture the temporal association between sub-events. III) It introduces the event evidence feature to capture the full evidence for the detected events. IV) The data structure of EDF is extended and modified to capture the properties of EDFE and to store the results of the event detection process. V) We model complex events from real world surveillance videos using the proposed EDFE.
Keyword(s)