Fast video-based queue length detection approach for self-organising traffic control

摘要

With the development of traffic control theory, self-organising control has become one of the most promising techniques for traffic control. Among the various parameters of self-organising control, the queue length (number of vehicles) is a key one. Compared to the approaches using other detectors, vision-based approaches have a greater potential in queue length detection. However, the complicated traffic conditions (such as the changeable weather and the vehicle occlusion) and the large calculation of image processing have posed great challenges to the real-time application. Here, a fast video-based queue length detection approach is proposed. For each lane, according to the level of traffic congestion evaluated by the foreground area ratio, the corresponding vehicle counting method is adopted. When the traffic is determined congested, a fast area-based method for estimating the number of vehicles is adopted. Otherwise, a fast vehicle detection and counting method combining background difference and Adaboost classifier is adopted. The experiment results demonstrate that the proposed approach can handle actual traffic environment and has great potential for real-time application.