中山大学学报（自然科学版）2011，Vol.50Issue(4)：56-60,64,6.
基于视频车辆轨迹模型的交通事件自动检测方法研究
Study on the Methods of Automatic Incident Detection based on the Video Vehicle Trajectory Model
摘要
Abstract
Five dangerous traffic incidents including vehicle retrograding, parking, turning round, reversing, and changing lanes are studied. Object detection, vehicle tracking, incident apprehension and description are used to detect incident automatically based on video. The great emphasis is placed on analyses and researches of the vehicle's tracking trajectory. Complicated vehicle trajectory is separated into four elements: ahead, backward, stop, and left or right; then vehicle behavior model is built to analyze vehicle's motion based on them. Finally, reasonable algorithms to detect above five traffic incidents are proposed. Experiments show that the normal and the abnormal vehicles can be distinguished, and the five traffic incidents can be detected quickly and effectively by the algorithms.关键词
交通事件检测/目标提取/车辆跟踪/车辆行驶行为模型Key words
traffic incident detection/ object detection/ vehicle tracking/ vehicle behavior model分类
计算机与自动化引用本文复制引用
赵有婷,李熙莹,罗东华..基于视频车辆轨迹模型的交通事件自动检测方法研究[J].中山大学学报（自然科学版）,2011,50(4):56-60,64,6.基金项目
国家自然科学基金资助项目(51078362) （51078362）
