Video Event Recognition for Surveillance Applications (VERSA)

TL;DR

VERSA is a flexible framework that uses declarative logic to define and recognize complex events in surveillance videos, enabling effective monitoring and alerting in security applications.

Contribution

The paper introduces VERSA, a novel framework that employs a declarative logic language for defining and recognizing events in surveillance video streams.

Findings

Supports live and recorded video analysis

Uses XML-based, service-oriented architecture

Potential for extending with fuzzy logic

Abstract

VERSA provides a general-purpose framework for defining and recognizing events in live or recorded surveillance video streams. The approach for event recognition in VERSA is using a declarative logic language to define the spatial and temporal relationships that characterize a given event or activity. Doing so requires the definition of certain fundamental spatial and temporal relationships and a high-level syntax for specifying frame templates and query parameters. Although the handling of uncertainty in the current VERSA implementation is simplistic, the language and architecture is amenable to extending using Fuzzy Logic or similar approaches. VERSA's high-level architecture is designed to work in XML-based, services- oriented environments. VERSA can be thought of as subscribing to the XML annotations streamed by a lower-level video analytics service that provides basic entity detection, labeling, and tracking. One or many VERSA Event Monitors could thus analyze video streams and provide alerts when certain events are detected.