Traffic demand estimation for lane groups at signal-controlled intersections using travel times from video-imaging detectors

The purpose of this study is to present a new method for lane-based traffic demand estimation using travel times from video-imaging detectors. The method overcomes the following two shortcomings of loop-detector-based algorithms: the fact that the actual demand is unknown when detectors are located upstream from the stop lines within a short distance; and the difficulty in calculating the ratio between streams in different lane groups if detectors are located at the upper reaches of the links. First, the authors analyse a variety of travel time patterns and introduce the concept of a virtual cycle that satisfies the criteria that all vehicles entering into a link in one virtual cycle have just departed from a downstream stop line within a single signal cycle. Next, the authors improve the travel time reduction rate model for queued vehicles in each cycle, and enhance the algorithms to estimate the lane-based traffic demand under different conditions. Finally, all parameters are calibrated and the new models are evaluated. The results show that: the maximum, minimum and average deviations over 12 cycles are 38.50, 0.02 and 16.19%, respectively. The findings in this study have potential applicability for use in traffic control systems, especially where oversaturated conditions are present.