Finding and Indexing of Eccentric Events in Video Emanates

Abstract

We propose a methodology that first extracts features of video emanates and detects eccentric events in a crowded environment. Afterwards eccentric events are indexed for retrieval. The motivation of the framework is the discrimination of features which are independent from the application domains. Low-level as well as midlevel features are generic and independent of the type of abnormality. High-level features are dependent and used to detect eccentric events, whereas both mid-level and highlevel features are run through the indexing scheme for retrieval. To demonstrate the interest of the methodology, we primarily present the obtained results on collapsing events in real videos amassed by single camera installed an airport escalator exits to monitor the circumstances of those regions.