Alternative approach to traffic state analysis on Indian roads using image processing

Abstract

In India, video monitoring of urban roads in order to estimate traffic condition parameters (volume, speed and density) is difficult due to the heterogeneous nature of the traffic and poor lane discipline. As an alternative, a methodology to estimate levels of traffic congestion on urban roads using image processing of monitored video recordings was developed. Four levels of congestion, from completely congested to free-flow conditions, were identified utilising surrogates such as area occupancy or average velocity along with additional attributes such as the number of corner features extracted using image processing. The algorithm was adjusted for changes in lighting and camera angles. The performance of the framework was evaluated on videos recorded from a major road in Chennai, India. The findings indicated that the proposed framework is well-suited for real-time identification of traffic states and has potential as a cost-effective tool for updating traveller information systems in similar road transport networks.