Edge level vehicular traffic estimation using cellular infrastructure and other sources

Intelligent Transportation Systems (ITS) play major role in generating fine grained vehicular traffic information for city wide or larger region. However, in developing countries like India, limited ITS infrastructure is available. On the other hand, cellular infrastructure is widely deployed in India with more than 867 million cellular connections and more than 70% cellular teledensity [1]. Also, on some major arterial roads, video cameras are deployed for surveillance purpose. The aim of this study is to assess feasibility of using these alternate sources to generate accurate traffic information for all the edges in a road network. The simulation results show that, even with large location error of 250-500 meters, edge level vehicle flow estimation with good accuracy (less than 10% error) is feasible using cellular network data. Using cellular network data alone, the edges can be classified as congested or uncongested. For edge level speed estimation, we propose a simple and novel approach for fusing widely available but erroneous flow data from cellular network with the spatially sparse but accurate flow-speed data from other sources (e.g. loop detectors or video cameras). The simulation results show that edge level speed estimation with good accuracy (less than 15% median error) is feasible using the proposed approach.