No abstract

No abstract

Most automatic incident detection algorithms were successfully developed using loop-detector-based traffic measurements collected from their own localities. But their detection performances were not satisfactory when applied on data collected using a video-based detector system. The video-based detector system is gaining popularity as it was reported to be cost-effective, less prone to damage compared to loop detectors embedded in road pavement, and possesses surveillance capability. It is able to provide the homogeneity of traffic measurements with greater reliability in non-incident situations. In this study, a simple detection rule was used to develop algorithms that use video-based data for detecting lane-blocking incidents. A set of 96 incidents from Singapore's Central Expressway was used for calibrating these algorithms, with another 64 incidents for validation. Two single-station algorithms, named dual-variable (DV) and flow-based DV algorithms were developed. They have similar detection logic, but the latter includes a pre-incident traffic flow condition in its detection framework. On average, the flowbased DV algorithm outperformed the DV algorithm, and both proved to be effective techniques when compared to some existing loop-detector-based algorithms.

No abstract

Timely detection of accidents, vehicle breakdowns, and events that obstruct normal traffic flow is critical to successful implementation of an incident management system in combating traffic congestion along expressways. The purpose of this study is to enhance the performance of existing expressway automatic incident detection algorithms in detecting lane-blocking incidents. In this study, a video-based vehicle detector system was used along the Central Expressway (CTE) in Singapore to collect 160 incidents. Two main tasks were carried out with the CTE incident database to investigate factors that influence incident detection performance and to investigate the use of these findings to enhance existing CTE-calibrated incident detection algorithms. Results indicated that the inclusion of preincident traffic flow or occupancy conditions and the use of traffic speed together with occupancy in an algorithm would yield enhanced detection performance. Of the algorithms studied, the dual variable algorithm, which uses traffic speed and occupancy, can consistently give the best detection performance. From an efficiency perspective, there were no significant changes in time lag in the detection of an incident. A comparative evaluation suggested that the occupancy-based algorithms were generally more effective than the flow-based algorithms in detecting incidents.