A V2I-Based Real-Time Traffic Density Estimation System in Urban Scenarios

Road traffic is experiencing a drastic increase in recent years, thereby increasing the every day traffic congestion problems, especially in metropolitan areas. Governments are making efforts to alleviate the increasing traffic pressure, being vehicular density one of the main metrics used for assessing the road traffic conditions. However, vehicle density is highly variable in time and space, making it difficult to be estimated accurately. Currently, most of the existing vehicle density estimation approaches, such as inductive loop detectors, or traffic surveillance cameras, require very specific infrastructure to be installed on the road. In this paper, we present a novel solution to accurately estimate the density of vehicles in urban scenarios. Our proposal, that has been specially designed for Vehicular Networks, allows Intelligent Transportation Systems to continuously estimate vehicular density by accounting for the number of beacons received per Road Side Unit (RSU), and also considering the roadmap topology where the RSUs are located. Simulation results reveal that, unlike previous proposals solely based on the number of beacons received, our approach accurately estimates the vehicular density, and therefore our approach can be integrated within automatic traffic controlling systems to predict traffic jams, and thus introducing countermeasures.