In the last few years, we witnessed numerous episodes of terrorist attacks and menaces in public crowded places. The necessity of better surveillance in these places pushed the development of new automated solutions to spot and notify possible menaces as fast as possible. In this work, we propose a novel approach to create a decentralized architecture to manage patrolling drones and cameras exploiting lightweight protocols used in the internet of things (IoT) domain. Through the adoption of the mist computing paradigm it is possible to give to all the object of the smart ecosystem a cognitive intelligence to speed up the recognition and analysis tasks. Distributing the intelligence among all the objects of the surveillance ecosystem allows a faster recognition and reaction to possible warning situations. The recognition of unusual objects in certain areas, e.g., airports, train stations and bus stations, has been made using computer vision algorithms. The adoption of the IoT protocols in a hierarchical architecture provides high scalability allowing an easy and painless join of other smart objects. Also a study on the soft real-time feasibility has been conducted and is herein presented.
Keywords: OpenCV; computer vision; drones; internet of things; lightweight protocols; mist computing; surveillance.