A novel smart camera network for real time public transport monitoring and surveillance

In this paper, we present the environment perception layer of the Smart Passenger Center (SPaCe), a novel integrated framework for public transport management. This layer is a pervasive vision architecture for improved safety and security in the context of public transportation. Privacy and technological constraints are still significant limitations for the real-time analysis of video streams from video capture devices installed on public transport vehicles. In fact, in almost all cases, this analysis is carried out offline and lacks any predictive processing, which is now potentially applicable to all transport sectors, thanks to machine learning and artificial vision techniques. The architecture described is designed to combine the output of a set of parallel processing, all running onboard in real-time, thus allowing the separation of the information collected from actual passengers' identities. The analysis highlights aspects that affect travel and travellers safety, such as people's behaviour and the state of maintenance of vehicles.