原文传递 Evaluation of Incident Detection Methodologies; Project summary rept. Sep 97-Sep 99
题名: Evaluation of Incident Detection Methodologies; Project summary rept. Sep 97-Sep 99
作者: Mahmassani, H. S.; Haas, C.; Peterman, J.; Zhou, S.
关键词: Traffic surveillance; Closed cicuit television; Image velocity sensors; Speed estimation; Monitoring; Traffic law enforcement; Freeway congestion; Highway management; Data acquisition
摘要: The detection of freeway incidents is an essential element of an area's traffic management system. Incidents need to be detected and handled as promptly as possible in order to minimize traffic delays. Various algorithm and detection technologies are examined to determine which combination offer optimized detection performance. This study represents an effort to compile, and rank available incident detection strategies. Based on an extensive literature review, as well as on interviews with traffic management personnel, the California algorithm No. 8, McMaster algorithm, Minnesota (DELOS), and Texas algorithms were selected for testing. The performance of these algorithms was assessed using extensive incident and traffic data from San Antonio, Texas. For training purposes, the data were separated into subsets for calibration and testing. During calibration, algorithm parameters were optimized via a Monte Carol estimation process. Trained algorithms were then tested and evaluated according to traffic data aggregation (smoothing) and incident type. Results verify the validity of the calibration process, though algorithm performance varied slightly between calibration and testing phases. Each algorithm performed differently under different situations.
总页数: 18p
报告类型: 科技报告
检索历史
应用推荐