Towards simulating non-lane based heterogeneous road traffic of less developed countries using authoritative polygonal GIS map

Microscopic traffic simulators have become efficient tools to conduct different analytic studies on roads, vehicles, behavior of drivers, and critical intersections, which lead towards a well-planned traffic solution. Devising a realistic and sustainable traffic solution requires replication of the real traffic scenario in a simulator. For example, to simulate the traffic stream of less developed countries, we need to simulate non-lane based heterogeneous traffic stream, i.e., motorized and non-motorized vehicles, with their on road behaviors such as irregular pedestrian, illegal parking, violation of laws pertaining lanes, etc. However, most of the existing traffic simulators are unable to mimic the unstructured road traffic stream of less developed countries with their diversified behaviors. We also need to represent the corresponding geographical maps as a list of nodes and edges with relevant geographic information such as length and width of the edges to feed the simulator. However, we lack a Geographic Information System (GIS) protocol to construct an effective simulator readable road network from authoritative polygonal GIS maps. State-of-the-art GIS protocol often converts the geographical maps using polyline data collected from less-credible OpenStreetMap. Although polyline data has length information (for example, length of a street), it lacks width information limiting its capability of being an effective simulator readable road network map. Therefore, in this work, we propose a new microscopic traffic simulator to handle unstructured road traffic stream of less developed countries with their diversified behaviors. To feed the simulator, we also propose a novel parsing algorithm to construct an effective simulator-readable road network from GIS maps through extracting both length and width information of the edges and develop parser based on the algorithm. Our parsing algorithm realizes a delicate blending of geometry with computation over road points to eventually generate the simulator-readable road network. Our simulator receives the network topology generated by our parser, traffic routes, and traffic demand flow rates as input, visualizes the traffic flows, and provides relevant traffic statistics. To evaluate sustainability of our proposed parser and simulator in real-life scenarios, we evaluate our parser by parsing GIS street maps of four different areas resulting in 86% accuracy on an average and evaluate our simulator after necessary calibration using real traffic data resulting in 99% accuracy in terms of travel time.