摘要
提出一种口罩佩戴检测模型,引入多注意力机制,提升了网络特征挖掘能力;利用柔性非极大抑制方法,消除多余目标检测框.在公共数据库上的仿真实验表明,该模型检测人脸口罩佩戴的平均精度达到93.81%,帧率达到11.8 fps,能有效地进行人脸口罩佩戴检测.
A mask in public places can effectively control the transmission of the coronavirus.To this end,a mask wearing detection model is proposed.The model introduces a multi-attention mechanism to improve the network feature mining ability and uses soft-NMS methods to eliminate redundant target detection boxes.A simulation experiment is conducted on a public database.The average accuracy of the proposed face mask wearing detection reaches 93.81%,and the frame rate reaches 11.8 fps.The experimental results show that the model can effectively detect the face mask wearing.
作者
余阿祥
李承润
于书仪
李洪均
Yu Axiang;Li Chengrun;Yu Shuyi;Li Hongjun(School of Information Science and Technology,Nantong University,Nantong 226019,China;State Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210023,China)
出处
《南京师范大学学报(工程技术版)》
CAS
2021年第1期23-29,共7页
Journal of Nanjing Normal University(Engineering and Technology Edition)
基金
国家自然科学基金项目(61871241、61976120)
南京大学计算机软件新技术国家重点实验室基金项目(KFKT2019B015)
江苏省研究生科研与实践创新计划项目(KYCX19_2056)
南通大学大学生创新训练计划项目(2020109).