摘要
车辆异常行为是造成高速公路交通隐患的主要原因之一。为了提高高速公路的安全管理,通过对车辆GPS数据进行分析,将连续11次定位的车辆速度、加速度作为输入参数,进行神经网络分类器的设计与训练,设计基于GPS数据的车辆异常行为分级检测算法。通过GPS实验和VISSIM模拟仿真各类车辆异常行为,分析检验检测算法,结果表明提出的分级检测算法具有较高的检测率,能够有效的识别各类车辆异常行为。
Vehicle abnormal behavior is one of the main causes of freeway traffic accident. In order to improve the safety management of the freeway,the vehicle global positioning system( GPS) data were analyzed. The vehicle speed and acceleration of 11 time of consecutive positioning were taken as input parameters,and the designing and training of neural network classifier was carried out. Finally,a hierarchical detection algorithm for vehicle abnormal behavior of freeway based on GPS data was designed. Through GPS experiments and VISSIM simulation,various types of vehicle abnormal behaviors were simulated,and the proposed detection algorithm was analyzed and verified. The results show that the proposed hierarchical detection algorithm has a high detection rate and can effectively identify all kinds of vehicle abnormal behaviors.
作者
杨龙海
徐洪
张春
YANG Longhai;XU Hong;ZHANG Chun(School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, Heilongjiang, P. R. China;Cbongqing Transport Planning and Research Institute, Chongqing 401147, P. R. China)
出处
《重庆交通大学学报(自然科学版)》
CAS
北大核心
2018年第5期97-103,共7页
Journal of Chongqing Jiaotong University(Natural Science)
关键词
交通工程
高速公路
车辆异常行为检测
GPS定位
分级检测算法
神经网络
traffic engineering
freeway
vehicle abnormal behavior detection
global positioning system (GPS)positioning
hierarchical detection algorithm
neural network