Attention Mechanism-Based Method for Intrusion Target Recognition in Railway  

基于注意力机制的铁路入侵目标识别方法

作　　者：SHI Jiang BAI Dingyuan GUO Baoqing WANG Yao RUAN Tao 石江;白丁元;郭保青;王尧;阮涛(国能朔黄铁路发展有限责任公司,北京100080;北京交通大学机械与电子控制工程学院,北京100044)

机构地区：[1]CHN Energy ShuoHuang Railway Development Company Ltd,Beijing 100080,P.R.China [2]School of Mechanical and Electronic Control Engineering,Beijing Jiaotong University,Beijing 100044,P.R.China

出　　处：《Transactions of Nanjing University of Aeronautics and Astronautics》2024年第4期541-554,共14页南京航空航天大学学报（英文版）

基　　金：supported in part by the Science and Technology Innovation Project of CHN Energy Shuo Huang Railway Development Company Ltd(No.SHTL-22-28);the Beijing Natural Science Foundation Fengtai Urban Rail Transit Frontier Research Joint Fund(No.L231002);the Major Project of China State Railway Group Co.,Ltd.(No.K2023T003)。

摘　　要：The detection of foreign object intrusion is crucial for ensuring the safety of railway operations.To address challenges such as low efficiency,suboptimal detection accuracy,and slow detection speed inherent in conventional comprehensive video monitoring systems for railways,a railway foreign object intrusion recognition and detection system is conceived and implemented using edge computing and deep learning technologies.In a bid to raise detection accuracy,the convolutional block attention module(CBAM),including spatial and channel attention modules,is seamlessly integrated into the YOLOv5 model,giving rise to the CBAM-YOLOv5 model.Furthermore,the distance intersection-over-union_non-maximum suppression(DIo U_NMS)algorithm is employed in lieu of the weighted nonmaximum suppression algorithm,resulting in improved detection performance for intrusive targets.To accelerate detection speed,the model undergoes pruning based on the batch normalization(BN)layer,and Tensor RT inference acceleration techniques are employed,culminating in the successful deployment of the algorithm on edge devices.The CBAM-YOLOv5 model exhibits a notable 2.1%enhancement in detection accuracy when evaluated on a selfconstructed railway dataset,achieving 95.0%for mean average precision(m AP).Furthermore,the inference speed on edge devices attains a commendable 15 frame/s.异物入侵检测对于保障铁路运营安全十分重要,针对传统铁路综合视频监控效率低、检测精度差以及现有智能检测算法检测速度慢等问题,结合注意力机制和目标检测模型在边端进行入侵目标检测。在提高检测精度方面,将包括空间注意力模块和通道注意力模块的卷积注意力模块(Convolutional block attention module,CBAM)模块融合到YOLOv5模型当中,构建了CBAM-YOLOv5模型,并采用距离交并比非极大值抑制(Distance intersection-over-union_non-maximum suppression,DIo U_NMS)算法代替加权非极大值抑制算法,从而改善模型对入侵目标的检测效果;在提升检测速度方面,基于批量归一化(Bath normalization,BN)层对模型网络裁剪并对Tensor RT推理加速,最终将算法移植到边缘设备。CBAM-YOLOv5模型在自建的铁路数据集上的检测精度提升了2.1%,平均精度均值(mean Average precision,m AP)达到了95.0%,在边缘设备上的推理速度达到了15帧/s。

关 键 词：foreign object detection railway protection edge computing spatial attention module channel attention module 

分 类 号：TN925[电子电信—通信与信息系统]