基于隧道监控视频的列车通过探测方法研究  

Research on Train Passage Detection Method Based on Tunnel Surveillance Video

作　　者：胡开麟 李家平 张明 HU Kai-lin;LI Jia-ping;ZHANG Ming(Shanghai Survey,Design and Research Institute(Group)Co.,Ltd.,Shanghai 200438,China;Shanghai Metro Monitoring Management Co.,Ltd.,Shanghai 200070,China)

机构地区：[1]上海勘察设计研究院(集团)有限公司,上海200438 [2]上海地铁监护管理有限公司,上海200070

出　　处：《价值工程》2023年第31期138-141,共4页Value Engineering

摘　　要：城市交通轨道的发展,尤其是地铁的发展非常重要,而对隧道列车进行通过监测无论是对运营商、监控部门还是用户都是很重要的。相较于传统的接触式列车通过监测,通过视频对列车是否通过进行监测更安全,成本更低。在许多学者的视频监测研究中,都用到了图像处理、深度学习的方法,而对于隧道列车的研究而言,这些方法大都有准确率低、数据集采集成本较高等缺点。本文通过隧道固定的监控摄像头视频进行数据集人工标注,通过实验对比多种图像分类卷积神经网络的表现后选择最优网络模型,再通过卡尔曼滤波进行优化得到列车通过的时间段,是一种更简单、便捷,且可移植性强的方法。The development of urban transit rail,especially subway,is very important,and the tunnel train monitoring is very important for operators,monitoring departments and users.Compared with the traditional contact train monitoring,it is safer and cheaper to monitor whether the train passes by video.Many scholars have used image processing and deep learning methods in video monitoring research,but for the study of tunnel train,most of these methods have the disadvantages of low accuracy and high cost of data set collection.In this paper,the data set is manually marked through the fixed surveillance camera video of the tunnel.After comparing the performance of various image classification convolution neural networks through experiments,the optimal network model is selected,and the time period of train passing is optimized through Kalman filter.This is a simpler,more convenient and more portable method.

关 键 词：深度学习 隧道监控视频 列车通过探测 GPU 

分 类 号：U495[交通运输工程—交通运输规划与管理]