Effective incident detection and management on freeways is vital in order to maximize road system performance and minimize the problems associated with growing traffic congestion. This study contains a review and assessment of the latest developments in freeway incident detection technologies and algorithms, with the intention of providing a guide to the different approaches used in implementing a freeway incident detection system. The various components of a freeway incident management system discussed in this study include: vehicle sensors (such as, inductive loop detectors, video image processing and microwave sensors), variable message signs, communication systems, automatic incident detection algorithms, and incident management plans and procedures using case studies. A comparative study of freeway incident detection algorithms was undertaken on the California algorithm, the University of California, Berkeley (UCB) algorithm, the ARRB-VicRoads algorithm, Detection Logic with Smoothing (DELOS) algorithm, and an artificial neural network (ANN) model. It was found that the ANN model performs better than the other rule-based algorithms. The California and DELOS algorithms performed the best out of the four rule-based algorithms that were evaluated. An optimization software FRIO has also been developed to optimize the calibration and, thus, maximize the performance of rule-based algorithms.
|Number of pages||49|
|Journal||Research Report ARR|
|Publication status||Published - 1 Dec 1999|
ASJC Scopus subject areas
- Civil and Structural Engineering