基于Faster-RCNN的站台端部人员入侵检测研究

杨栋; 黄文政; 张秋亮; 李依诺; 张亚伟

基于Faster-RCNN的站台端部人员入侵检测研究

1. 中国铁道科学研究院集团有限公司电子计算技术研究所, 北京 100081;
2. 中国铁路南宁局集团有限公司客运部, 南宁 530029

基金项目:

中国铁路总公司科技研究开发计划课题（P2018G049；J2018X006）

详细信息

作者简介:
杨栋,助理研究员;黄文政,工程师。

中图分类号: U291.65;TP39
计量
- 文章访问数: 165
- HTML全文浏览量: 17
- PDF下载量: 24
出版历程
- 收稿日期: 2019-07-10
- 刊出日期: 2020-08-03

Personnel intrusion detection of platform end based on Faster-RCNN

1. Institute of Computing Technologies, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China;
2. China Railway Nanning Group Co. Ltd., Passenger Transport Department, Nanning 530029, China

摘要

摘要: 铁路客运站的站台端部为非封闭式环境,存在人员非法入侵的风险。在阐述Faster-RCNN算法原理的基础上,详细描述了VGG16模型、RPN网络以及分类回归的过程。采集现场数据制作样本集,训练了可区分普通人员、施工人员以及防护人员的站端入侵检测模型。测试分析了5组不同参数下的实验数据,确定候选区队列长度等于300,推荐候选区数量等于15时为最优参数。模型对普通人员、施工人员以及防护人员3种样本的识别精确率分别为95%、99%、100%,识别召回率分别为97%、99%、100%,平均精确率均值为0.983 6,单帧检测时间为0.069 s。结果表明:算法可有效地检测普通人员、施工人员以及防护人员,满足实时检测需求,为站台端部人员入侵检测提供了新思路。
- 站台端部入侵检测 /
- Faster-RCNN /
- VGG16 /
- 卷积神经网络 /
- 深度学习
Abstract: The platform ends of the railway passenger station are non closed environment, which has the risk of illegal invasion.On the basis of explaining the principle of Faster-RCNN algorithm, this paper described the VGG16 model, RPN network and classified regression process in detail.The paper collected field data to make a sample set, and trained the station end intrusion detection model which could distinguish ordinary personnel, construction personnel and protection personnel.Five groups of experimental data with different parameters were tested and analyzed.It was determined that when the queue length of candidate area was equal to 300 and the number of recommended candidate area was equal to 15, it was the optimal parameter.The recognition accuracy rate of the model for ordinary personnel, construction personnel and protection personnel was 95%, 99% and 100%, the recognition recall rate was 97%, 99% and 100%, the average accuracy rate was 0.983 6, and the single frame detection time was 0.069 s.The results show that the algorithm can effectively detect ordinary personnel, construction personnel and protection personnel, meet the needs of real-time detection, and provide a new idea for platform end personnel intrusion detection.
- intrusion detection of platform end /
- Faster-RCNN /
- VGG16 /
- convolution neural network /
- deep learning

HTML全文

参考文献(10)

[1]	李琳. 站台两端入侵报警系统的研究与应用[J]. 中国高新区, 2019(2):45-46
[2]	张秋亮,杨国元. 基于微波雷达技术的站台两端监测告警系统研究[J]. 铁路计算机应用, 2019, 28(2):7-11.
[3]	卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6):1229-1251.
[4]	Krizhevsky A, Sutskever I, Hinton G. ImageNet Classification with Deep Convolutional Neural Networks[C]//NIPS. Curran Associates Inc, 2012.
[5]	Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Cvpr, 2015.
[6]	Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition[C]//ICLR, 2014.
[7]	Ren S, He K, Girshick R, et al. Faster R-CNN:towards realtime object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems, 2015.
[8]	王晓媛,张文涛,韩磊. 基于Faster RCNN的屏幕防手机拍摄算法的研究[J]. 航天控制, 2019(2):66-72
[9]	张汇,杜煜,宁淑荣, et al. 基于Faster RCNN的行人检测方法[J]. 传感器与微系统, 2019, 38(2):153-155 , 159.
[10]	姜晓伟,王春平,付强. 基于卷积神经网络的空中红外飞机检测[J]. 激光与红外, 2018, 48(12):1541-1546.

施引文献(9)

期刊类型引用(4)

1.	潘东亮. 基于智能视觉的铁路大桥人员入侵防护系统设计研究. 铁路计算机应用. 2023(09): 48-53 . 本站查看
2.	徐鑫，潘杰，曹利安，罗伟，谢松. 基于深度学习的铁路异物侵限检测模型. 铁路计算机应用. 2023(10): 7-12 . 本站查看
3.	张秋亮，杨栋，王建超. 铁路客运站客流监测系统设计及关键技术研究. 铁道运输与经济. 2022(07): 56-63 . 百度学术
4.	魏秀琨，所达，魏德华，武晓梦，江思阳，杨子明. 机器视觉在轨道交通系统状态检测中的应用综述. 控制与决策. 2021(02): 257-282 . 百度学术