Given the importance of the freight transportation system, opportunities to utilize state of the art Intelligent Transportation Systems (ITS) technologies are increasing to improve the operation of the existing infrastructure to promote the efficient and safe transportation of freight. Among these technologies, a Truck Signal Priority (TkSP) strategy gives priority to a traffic signal approach when trucks are detected. By using the rich data available through the use of video sensors, the use such a strategy can improve the efficiency and safety of freight movement by reducing truck travel time and the number of truck stops at the intersection. This paper presents a prototype TkSP system using video sensors to detect, identify and track trucks. A classification module takes the road users' trajectories as input, and classifies them as either truck or non-truck. Using a mixture of Gaussians to model the background, the appearance and shape of road users in each frame is extracted. Using labeled shape data, a classifier is trained. A road user will be classified as a truck if its shape is classified as such in enough frames. The system is tested on real world data from the Next Generation SIMulation project (NGSIM). The truck recall reaches 78% to 95%, with a false alarm rate below the 0.5% value (used to test different scenarios in traffic simulation not presented in this document). This shows that the performance required for effective advanced truck signal priority is reached or within reach of automated video-based sensors. For the covering abstract of this conference see ITRD number E217481.
Abstract