计算机科学与探索 ›› 2014, Vol. 8 ›› Issue (1): 111-120.DOI: 10.3778/j.issn.1673-9418.1306016

• 人工智能与模式识别 • 上一篇    下一篇

离群点挖掘技术在交通事件检测中的应用

诸彤宇+,王  奇,高梦丹   

  1. 北京航空航天大学 软件开发环境国家重点实验室,北京 100191
  • 出版日期:2014-01-01 发布日期:2014-01-03

Research on Traffic Incident Detection with Outlier Mining Technology

ZHU Tongyu+, WANG Qi, GAO Mengdan   

  1. State Key Laboratory of Software Development Environment, Beihang University, Beijing 100191, China
  • Online:2014-01-01 Published:2014-01-03

摘要: 交通事件的检测与确认是交通事件管理中的首要问题。基于线圈和视频数据的检测方法由于成本高,检测效果不明显,在实际应用中受到限制。提出了一种基于离群点挖掘的交通事件检测算法。该算法通过使用浮动车(floating car data,FCD)技术得到路况信息,并提取交通事件特征,建立特征向量。算法简单、高效、易于部署。实验结果表明,同模式识别方法相比,该算法具有较高的准确度,能有效区分常规拥堵与交通事件。

关键词: 交通事件, 浮动车, 特征分析, 离群检测

Abstract: Traffic incident detection and confirmation is the primary problem in traffic incident management, but detection method based on loop detector and video data is restricted in practical applications due to the high cost and inefficiency. This paper proposes a traffic incident detection algorithm based on outlier mining by use of feature vector related to traffic incident. The feature vector is obtained from the traffic information processed by the float car technology. The algorithm is simple, efficient, and easy to deploy. The experimental results show that the algorithm has higher accuracy than the pattern recognition method, and can effectively distinguish between the conventional congestion and traffic incident.

Key words: traffic incident, floating car data, feature analysis, outlier mining