基于深度学习的铁路异物侵限检测模型  

Railway foreign object intrusion detection model based on deep learning

作　　者：徐鑫 潘杰 曹利安 罗伟 谢松 XU Xin;PAN Jie;CAO Li'an;LUO Wei;XIE Song(Science and Technology Research Institute,China Railway Chengdu Group Co.Ltd.,Chengdu 610081,China)

机构地区：[1]中国铁路成都局集团有限公司科学技术研究所,成都610081

出　　处：《铁路计算机应用》2023年第10期7-12,共6页Railway Computer Application

基　　金：中国铁路成都局集团有限公司公司科技项目(〔2022〕25号)。

摘　　要：为保障铁路运营安全,防范行人、家畜、野生动物等侵入铁路线路,提出基于深度学习的铁路异物侵入界限(简称:侵限)检测模型。针对铁路异物侵限的图像数据(简称:数据)集缺乏且难以采集的现实情况,通过多种途径自建铁路场景专用的异物侵限数据集,并引入多种数据增强技术,对数据集进行扩增,既增强了样本的多样性、又能有效避免训练阶段过拟合现象的发生;针对铁路场景的特殊性,对YOLO(You Only Look Once)v5深度学习模型结构进行一些适应性改进,将其作为铁路异物侵限检测模型,在自制数据集样本上进行训练和测试。测试结果表明,该模型的检测准确率达到88%以上,能够用于铁路现场对异物侵限的检测。To ensure the safety of railway transport and prevent pedestrians,livestock,wild animals,and other objects from invading the railway,this paper proposed a method of using deep learning technology to detect railway foreign object intrusion on monitoring video along the railway.In response to the reality of the lack and difficulty in collecting image dataset for railway foreign object intrusion limits,the paper constructed a dedicated foreign object intrusion limit dataset for railway scenes through various means,and introduced various data augmentation techniques to expand the dataset.This not only enhanced the diversity of the samples,but also effectively avoided overfitting during the training stage;The paper focused on the particularity of railway scenes and made some adaptive improvements to the YOLO(You Only Look Once) v5 deep learning model structure.It was used as a railway foreign object intrusion detection model and trained and tested on self-made dataset samples.The test results show that the detection accuracy of this model reaches over 88%,and it can be used for detecting foreign object intrusion in railway sites.

关 键 词：铁路异物侵限 检测模型 YOLOv5模型 图像识别 数据增强 图像数据集 

分 类 号：U229[交通运输工程—道路与铁道工程] TP391.4[自动化与计算机技术—计算机应用技术]