非限制场景下铁路机车车号定位检测方法  

Method for locating and detecting railway locomotive number in unrestricted scenarios

作　　者：陈虎林 王焕民[2] 米奡蔚 CHEN Hulin;WANG Huanmin;MI Aowei(Department of Science,Technology and Information Technology,China Railway Lanzhou Group Co.Ltd.,Lanzhou 730000,China;Institute of Electronic Machinery Technology,Lanzhou Jiaotong University,Lanzhou 730070,China)

机构地区：[1]中国铁路兰州局集团有限公司科技和信息化部,兰州730000 [2]兰州交通大学机电技术研究所,兰州730070

出　　处：《铁路计算机应用》2023年第4期18-23,共6页Railway Computer Application

基　　金：国家自然科学基金项目(61563027)。

摘　　要：针对传统铁路机车车号定位检测模型泛化性较低,不适用于多种检测应用场景等问题,提出一种适用于非限制场景、基于YOLO(You Only Look Once)v4-tiny模型的铁路机车车号定位检测方法。文章采用空洞卷积代替标准卷积,增大机车车号特征提取感受野,提升传统YOLOv4-tiny模型的检测精度;建立铁路机车车号数据集(RLND,Railway Locomotive Number Dataset),用于模型训练,并对模型的检测效果进行验证。验证结果表明,该方法对铁路机车车号的定位检测精度为99.44%,检测速度为50帧/s,能够应对非限制场景下的机车车号定位检测需求。In response to the low generalization of traditional railway locomotive number localization and detection models and their inability to adapt to various detection application scenarios,this paper proposed a method for locating and detecting railway locomotive number in unrestricted scenarios based on YOLO(You Only Look Once)v4-tiny model.The paper used cavity convolution instead of standard convolution to increase the receptive field of locomotive number feature extraction,improve the detection accuracy of the traditional YOLOv4 tiny model,established the Railway Locomotive Number Data set(RLND)for model training,and verified the detection effect of the model.The validation results show that the positioning and detection accuracy of this method for railway locomotive numbers is 99.44%,with a detection speed of 50 frames/s.It can meet the needs of locomotive number positioning and detection in unrestricted scenarios.

关 键 词：图像识别 机车车号定位 YOLOv4-tiny 非限制场景 轻量化 

分 类 号：U269[机械工程—车辆工程] TP391[交通运输工程—载运工具运用工程]