Length-based vehicle classification data are important inputs for traffic operation, pavement design, and transportation planning. However, such data are not directly measurable by singleloop detectors, the most widely deployed type of traffic sensor in the existing roadway infrastructure. In this study a Video-based Vehicle Detection and Classification (VVDC) system was developed for truck data collection using wide-ranging available surveillance cameras. Several computer-vision based algorithms were developed or applied to extract background image from a video sequence, detect presence of vehicles, identify and remove shadows, and calculate pixel-based vehicle lengths for classification. Care was taken to robustly handle negative impacts resulting from vehicle occlusions in the horizontal direction and slight camera vibrations. The pixel-represented lengths were exploited to relatively distinguish long vehicles from short vehicles, and hence the need for complicated camera calibration can be eliminated. These algorithms were implemented in the prototype VVDC system using Microsoft Visual C#. As a plug & play system, the VVDC system is capable of processing both digitized image streams and live video signals in real time. The system was tested at three test locations under different traffic and environmental conditions. The accuracy for vehicle detection was above 97 percent and the total truck count error was lower than 9 percent for all three tests. This indicates that the video image processing method developed for vehicle detection and classification in this study is indeed a viable alternative for truck data collection.
Vehicle headway distribution is fundamental for several important traffic research and simulation issues. Many headway models have been developed over the past decades. Each has its own strength and weakness. Selection of the most suitable model for a certain traffic condition remains an open issue. A comprehensive study of the performance of typical headway distribution models on urban freeways is presented. With the advanced loop event data analyzer system, many accurate headway observations were obtained from I-5 in the area of Seattle, Washington. These headway data were used to calibrate and examine the performance of various headway models. The goodness of fit for several most commonly used headway distribution models was investigated by using headways observed on regular lanes and high-occupancy-vehicle (HOV) lanes from different time periods of day. To evaluate the performance of these headway models, the analytical Kolmogorov-Smirnov test statistic and visualized comparison curves were used to measure and reflect their overall goodness of fit to the collected headway data. Although each model has its own practicability to a certain extent, the test results showed that the double-displaced negative exponential distribution model provided the best fit to these urban freeway headway data, especially for HOV lanes at wideranging flow levels. The shifted lognormal distribution also fits the general purpose lane headways very well. As a byproduct, a new standard parameter estimation method was developed for calibrating complex multiparameter headway models.
A multi-agent reinforcement learning for adaptive traffic signal control optimization.• Consider control unit at intersection as agent that can communicate with others through knowledge-sharing protocol.• Proposed algorithm achieves consistent improvements over baselines on both simulated and real-world data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.