基于图像技术的城市轨道交通大客流辨识  

Identification of Urban Rail Transit Mass Passenger Flow Based on Image Technology

作　　者：张霖 韩宝明[2] 李得伟[2] 

机构地区：[1]北京市城乡规划标准办公室,北京100045 [2]北京交通大学交通运输学院,北京100044

出　　处：《都市快轨交通》2012年第1期72-77,共6页Urban Rapid Rail Transit

基　　金：国家自然科学基金项目(61004105)

摘　　要：通过分析我国城市轨道交通发展的现状,说明"大客流"状态已逐渐成为城市轨道交通运营中的常态化现象。为了对城市轨道交通车站内客流进行更准确的辨识与监控,保证运营安全,尝试将图像技术引入轨道交通的客流辨识与安全管理中:建立客流图像特征值与客流特征值的联动关系,给出客流辨识的函数,并开发客流辨识系统。北京地铁雍和宫站的实际视频数据的辨识应用结果表明,该方法的识别准确度较高,具有一定的可用性。With the rapid development of urban rail transit,the ＂mass passenger flow＂ has become a normal phenomenon in urban rail transit operation.For more accurate identification and monitoring of passenger flow to ensure safety operation,this article attempts to introduce image technology into passenger identification and safety management,to establish the relationship between passenger flow characteristics and the image characteristic value of passengers,to determine the identification function of passengers,and to develop the passenger identification system.The identification video data obtained in Beijing subway Lama Temple station indicated that the method of identification is feasible with high degree of accuracy.

关 键 词：城市轨道交通 客流辨识 图像技术 特征值 

分 类 号：U293.6[交通运输工程—交通运输规划与管理]