Mobile video annotation for enhanced rich media communication during emergency handling

Abstract

In this work we present a novel video annotation and media enrichment methodology for enhanced visual communication among first responders (FRs) and their command centers complementing voice communications in order to overcome current shortcomings of the latter. For this purpose, an initial taxonomy of emergency cases and sub-cases handled by a variety of FR teams has been defined along with a core set of associated rich media annotation templates to enrich captured video footage with commonly-agreed alert signs and messages. The primary aim is to define a fully-functional, extensible and self-descriptive visual language for fast and self-explanatory emergency communication. FRs on site equipped with mobile devices (PDAs) are able to quickly author content enriched video alerts to effectively communicate the arisen situation to their Command centers using the subsequently proposed video annotation prototype. Both qualitative and quantitative system evaluation in lab tests and field trials with the participation of real end users prove the effectiveness of the proposed system.