A Novel Management Approach for Urban Emergency Based on Surveillance Videos and Public Opinions

Abstract

With the acceleration of urban modernization process, it’s urgent to construct an efficient and comprehensive system for managing the urban emergency. Surveillance videos obtained by monitors in multiple locations in cities, and public opinions on the official and individual websites are two kinds of indispensable input data of emergency management system. However, these videos and opinions are processed by human with high costs and poor results. To rectify this, this paper proposes an intelligent approach based on open source computer vision libraries and natural language processing techniques. For the purpose of analyzing and forewarning emergency, the proposed approach performs effectively in utilizing huge amount of surveillance videos and public opinions, hence opening up a new way in emergency management