{"title":"FCOSMask:基于MobileNetV3的全卷积单阶段口罩佩戴检测","authors":"Yang Yu, Jie Lu, Chao Huang, Bo Xiao","doi":"10.1145/3487075.3487078","DOIUrl":null,"url":null,"abstract":"Wearing masks correctly in public is one major self-prevention method against the worldwide Coronavirus disease 2019 (COVID-19). This paper proposes FCOSMask, a fully convolutional one-stage face mask wearing detector based on the lightweight network, for emergency epidemic control and long-term epidemic prevention work. MobileNetV3 is applied as the backbone network to reduce computational overhead. Thus, complex calculation related to anchor boxes is avoided in the anchor-free method, and Complete Intersection over Union (CIoU) loss is selected as the bounding box regression loss function to speed up model convergence. Experiments show that compared to other anchor-based methods, detection speed of FCOSMask is improved around 3 to 4 times on self-established datasets and mean average precision (mAP) achieves 92.4%, which meets the accuracy and real-time requirements of the face mask wearing detection task in most public areas. Finally, a Web-based face mask wearing system is developed that can support public epidemic prevention and control management.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"56 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FCOSMask: Fully Convolutional One-Stage Face Mask Wearing Detection Based on MobileNetV3\",\"authors\":\"Yang Yu, Jie Lu, Chao Huang, Bo Xiao\",\"doi\":\"10.1145/3487075.3487078\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Wearing masks correctly in public is one major self-prevention method against the worldwide Coronavirus disease 2019 (COVID-19). This paper proposes FCOSMask, a fully convolutional one-stage face mask wearing detector based on the lightweight network, for emergency epidemic control and long-term epidemic prevention work. MobileNetV3 is applied as the backbone network to reduce computational overhead. Thus, complex calculation related to anchor boxes is avoided in the anchor-free method, and Complete Intersection over Union (CIoU) loss is selected as the bounding box regression loss function to speed up model convergence. Experiments show that compared to other anchor-based methods, detection speed of FCOSMask is improved around 3 to 4 times on self-established datasets and mean average precision (mAP) achieves 92.4%, which meets the accuracy and real-time requirements of the face mask wearing detection task in most public areas. Finally, a Web-based face mask wearing system is developed that can support public epidemic prevention and control management.\",\"PeriodicalId\":354966,\"journal\":{\"name\":\"Proceedings of the 5th International Conference on Computer Science and Application Engineering\",\"volume\":\"56 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-10-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 5th International Conference on Computer Science and Application Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3487075.3487078\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3487075.3487078","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
在公共场合正确佩戴口罩是应对2019冠状病毒病(COVID-19)的主要自我预防方法之一。本文提出了一种基于轻量化网络的全卷积一级口罩佩戴检测器FCOSMask,用于突发疫情防控和长期疫情防控工作。采用MobileNetV3作为骨干网,减少计算开销。因此,在无锚方法中避免了与锚盒相关的复杂计算,并选择CIoU (Complete Intersection over Union)损失作为边界盒回归损失函数,加快了模型的收敛速度。实验表明,与其他基于锚点的方法相比,FCOSMask在自建数据集上的检测速度提高了3 ~ 4倍左右,平均精度(mAP)达到92.4%,满足了大多数公共区域口罩佩戴检测任务的准确性和实时性要求。最后,开发了一个基于web的支持公共疫情防控管理的口罩佩戴系统。
FCOSMask: Fully Convolutional One-Stage Face Mask Wearing Detection Based on MobileNetV3
Wearing masks correctly in public is one major self-prevention method against the worldwide Coronavirus disease 2019 (COVID-19). This paper proposes FCOSMask, a fully convolutional one-stage face mask wearing detector based on the lightweight network, for emergency epidemic control and long-term epidemic prevention work. MobileNetV3 is applied as the backbone network to reduce computational overhead. Thus, complex calculation related to anchor boxes is avoided in the anchor-free method, and Complete Intersection over Union (CIoU) loss is selected as the bounding box regression loss function to speed up model convergence. Experiments show that compared to other anchor-based methods, detection speed of FCOSMask is improved around 3 to 4 times on self-established datasets and mean average precision (mAP) achieves 92.4%, which meets the accuracy and real-time requirements of the face mask wearing detection task in most public areas. Finally, a Web-based face mask wearing system is developed that can support public epidemic prevention and control management.