In this paper, the authors describe the successful combination of a low- level, vision-based surveillance system with a high-level, symbolic reasoner based on dynamic belief networks. This prototype system provides robust, high-level information about traffic scenes. The machine vision component...

This final report describes an advanced traffic surveillance technique based on pattern recognition and the use of current inductive loop technology. The focus of the investigation was a study of the feasibility of using inductive loop signatures for obtaining vehicle classification information...

In this paper, the authors address the problem of traffic surveillance in an Advanced Transportation Management System. They propose a new approach for detecting and tracking vehicles in road traffic scenes that attains a level of accuracy and reliability which lies beyond currently available...

This dissertation deals with the application of Advanced Traveler Information Systems (ATIS) in incident management. Using an idealized traffic corridor and deterministic queuing methods, conditions under which route guidance information is useful are identified. Benefits to traffic guided with...

The objective of this study is to evaluate alternative frameworks for Computer Integrated Transportation (CIT) from an institutional perspective. This was accomplished through site visits and interviews at existing Transportation Management Centers (TMCs), along with focus group sessions in...

This paper presents microscopic time-space diagrams for several shock waves over 100-200m distances. The primary focus of the paper is on presenting the data rather than analysis. The diagrams should be of general interest to researchers studying traffic congestion.

Transportation Management Centers (TMCs) are focal points for monitoring and operating traffic management systems. As new technologies are developed through research in Intelligent-Vehicle- Highway Systems (IVHS), these TMCs will assume increasingly more importance as command and control centers...

The objective of this study is to develop a methodology for incident duration prediction. The authors first developed an understanding of factors that influence incident duration. A series of truncated regression models is used to predict incident duration. The models account for the fact that...