有轨电车异物侵限检测及预警方法研究  

Research on detection and early warning method of foreign objects intrusion for tram

作　　者：叶超 陈新[1] Ye Chao;Chen Xin

机构地区：[1]南京理工大学,江苏南京210094

出　　处：《现代城市轨道交通》2022年第7期91-96,共6页Modern Urban Transit

摘　　要：文章融合混合高斯模型与三帧差分法对有轨电车线路进行异物侵限检测,并结合有轨电车位置、速度、异物运动轨迹等参数,采用T-S模糊神经网络进行预警等级划分。以某有轨电车公司提供的视频监控数据作为实例,开展实例仿真研究,仿真结果表明该异物侵限检测算法能够较好地检测出行人、汽车等异物,T-S模糊神经网络能够用于有轨电车异物侵限预警。In this paper,the gaussian mixture model and three-frame difference method are combined to detect the foreign objects intrusion on tram line,and the T-S fuzzy neural network is used to classify the early warning level in combination with the parameters such as the tram position,speed and foreign object trajectory.Taking the video surveillance data provided by a tram company as an example,case simulation research was carried out.The simulation results show that the foreign object intrusion detection algorithm can better detect foreign objects such as travelers and cars,and T-S fuzzy neural network can be used as an early warning method for foreign object intrusion on tramway tracks.

关 键 词：有轨电车 异物侵限 混合高斯模型 三帧差分法 T-S模糊神经网络 

分 类 号：U298.1[交通运输工程—交通运输规划与管理]