轨道交通视频中乘客口罩佩戴检测算法研究  

Detection Algorithm of Passengers Wearing Masks in Rail Transit Video

作　　者：李永玲 秦勇[1] 曹志威 谢征宇[2] 吴志宇 LI Yongling;QIN Yong;CAO Zhiwei;XIE Zhengyu;WU Zhiyu(State Key Laboratory of Rail Traffic Control and Safety,Beijing Jiaotong University,100044,Beijing,China;不详)

机构地区：[1]北京交通大学轨道交通控制与安全国家重点实验室,北京100044 [2]北京交通大学交通运输学院,北京100044 [3]北京交通大学软件学院,北京100044

出　　处：《城市轨道交通研究》2022年第12期76-81,87,共7页Urban Mass Transit

基　　金：中央高校基本科研业务费专项资金资助“科技领军人才团队项目”(2022JBQY007);交通运输部“交通运输行业高层次技术人才培养项目”(I18I00010)。

摘　　要：为应对新冠疫情下乘客乘坐轨道交通时必须佩戴口罩的情况,提出一种基于深度学习的轻量化口罩检测算法(Mask-Det算法)。首先,使用轻量化骨干网络EfficientNet提取图像特征;然后,利用高效的特征融合模块增强用于检测小目标的浅层特征图的语义信息;最后,算法在公共场景数据集上训练,并使用迁移学习在轨道交通数据集上做进一步优化。Mask-Det算法检测准确率高、模型参数小、检测速度快,可以实时检测各场所乘客是否佩戴口罩,有效减轻工作人员压力,提高进站速度。In response to the mandatory situation of passengers wearing masks on rail transit during COVID-19 pandemic period,a lightweight mask detection algorithm(Mask-Det)based on deep learning is proposed.First,the lightweight backbone network EfficientNet is used to extract image features.Then,a highly efficient feature fusion module is used to enhance the semantic information of the shallow feature map for detecting small targets.Finally,the algorithm is trained on the dataset of public scenarios,and then further optimized on the dataset of rail transit scenarios using transfer learning.Mask-Det algorithm has high detection accuracy,small model parameters,and fast detection speed.The algorithm can detect in real time whether passengers are wearing masks at various places,thus effectively alleviate personnel stress and improve passenger entry speed.

关 键 词：车站安全 轨道交通视频 口罩佩戴检测 新冠疫情 

分 类 号：F530.7[经济管理—产业经济] R126.4[医药卫生—环境卫生学]