Traffic Congestion Estimation Based on Crowd-Sourced Data

Abstract

Traffic congestion still challenges large cities, causing not only economic loss but also pollution and other social issues. This issue is more serious in developing countries since the transportation infrastructures have not been developed well to satisfy quick growing demands. However, traffic data can be collected from crowd sources including fixed-IoT and human-sensing systems. This paper proposes a novel framework for crowd-sourcing based traffic state estimation that efficiently integrates human-sensed data (e.g., data shared by mobile users via mobile devices), and data from available fixed-sensor systems. We propose a framework to describe this method in details by a process from data collection phase, to data fusion and integration phase, and finally to traffic status analysis, prediction and mining phases. Then, we discuss about feasibility, effectiveness, and flexibility of the proposed system.