基于YOLOv5s的密集多人脸检测算法  

A dense multi-face detection algorithm based on YOL

作　　者：董子平 陈世国[1] 廖国清 DONG Zi-ping;CHEN Shi-guo;LIAO Guo-qing(School of Physics and Electronic Science,Guizhou Normal University,Guiyang 550025,China)

机构地区：[1]贵州师范大学物理与电子科学学院,贵州贵阳550025

出　　处：《计算机工程与科学》2023年第10期1838-1846,共9页Computer Engineering & Science

基　　金：贵州省科学技术基金(黔科合J字[2010]2145)。

摘　　要：针对在密集场景下多人脸检测容易漏检,小尺度人脸检测率不高的问题,提出了基于YOLOv5s改进的多人脸检测算法IYOLOv5s-MF。首先,在特征融合部分引入FTT模块,以获取小尺度人脸更多的特征表征;然后,改进正负样本采样策略,通过增加有效正样本,增强算法的模型泛化能力;最后,将Focal-EIoU作为定位损失函数,在加速模型收敛的同时提升人脸检测率。在WIDER FACE数据集上进行人脸检测实验,实验结果表明,相比较其他对比算法,IYOLOv5s-MF算法拥有较高的人脸检测精度,且具有较好的实时性能。To address the problem of missed detection in dense scenes and low detection rate for small-scale faces,an improved multi-face detection algorithm based on YOLOv5s,named IYOLOv5s-MF,is proposed.First,the feature texture transfer(FTT)module is introduced into the feature fusion part to obtain more feature representations for small-scale faces.Then,the positive and negative sample sampling strategy is improved by increasing the number of effective positive samples to enhance the model's generalization ability.Finally,Focal-EIoU is adopted as the localization loss function to accelerate model convergence and improve face detection accuracy.Experimental results on the WIDER FACE dataset show that compared with other comparison algorithms,IYOLOv5s-MF has higher face detection accuracy and good real-time performance.

关 键 词：人脸检测 YOLOv5s 特征融合 Focal-EIoU 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]