Events in crowded places: A smart service management

Abstract

• We present eSERVANT, an IT infrastructure for smart management of event venues • eSERVANT provides vision-based dynamic routing preventing crowds indoor and outdoor • Through social media data we recommend similar users attending the event • We evaluated user satisfaction of the eSERVANT app based on a 6 months experimentation In this work we present eSERVANT (eventS in crowdEd places: a smaRt serVice mANagemenT), an ICT hardware and software infrastructure that allows the management of services tied to big events such as concerts, sport matches or fairs that take place in dedicated facilities. Among the main features of eSERVANT there is a vision-based dynamic routing that exploits computer vision techniques to detect people and track their movements within a facility. Thanks to an estimate of room occupancies and inbound/outbound flows, we propose an algorithm for dynamically selecting the best indoor route and avoid hazardous situations. At the same time, we perform user profiling finalized to promoting social networking through recommendation. To assess the usefulness of our infrastructure we established a test case over a six month experimentation and quantitatively evaluated user satisfaction.