基于改进YOLOv5s的小人脸检测

周丽芳; 胡振; 刘波

doi:10.11959/j.issn.2096-6652.202438

您当前的位置：

首页 >

文章列表页 >

基于改进YOLOv5s的小人脸检测

学术论文 | 更新时间：2025-01-24

- 基于改进YOLOv5s的小人脸检测
- Small face detection based on improved YOLOv5s
- 智能科学与技术学报 2024年6卷第4期页码：456-465
- 作者机构：
  
  重庆邮电大学软件工程学院，重庆 400065
- 作者简介：
  
  [ "周丽芳（1974- ），女，博士，重庆邮电大学软件工程学院教授，主要研究方向为图像特征提取与识别、目标检测与跟踪。" ]
  [ "胡振（1999- ），男，重庆邮电大学软件工程学院硕士生，主要研究方向为深度学习、计算机视觉。" ]
  [ "刘波（1998- ），男，重庆邮电大学软件工程学院硕士生，主要研究方向为深度学习、计算机视觉。" ]
- 基金信息：
  
  国家自然科学基金项目(62276039);贵州大学开放基金(KY-2022（376）)
- DOI：10.11959/j.issn.2096-6652.202438
  中图分类号： TP311.5
- 收稿：2024-03-27，
  
  修回：2024-09-24，
  
  纸质出版：2024-12-15
- 稿件说明：
移动端阅览
周丽芳,胡振,刘波.基于改进YOLOv5s的小人脸检测[J].智能科学与技术学报,2024,06(04):456-465.

ZHOU Lifang,HU Zhen,LIU Bo.Small face detection based on improved YOLOv5s[J].Chinese Journal of Intelligent Science and Technology,2024,06(04):456-465.
周丽芳,胡振,刘波.基于改进YOLOv5s的小人脸检测[J].智能科学与技术学报,2024,06(04):456-465. DOI： 10.11959/j.issn.2096-6652.202438.

ZHOU Lifang,HU Zhen,LIU Bo.Small face detection based on improved YOLOv5s[J].Chinese Journal of Intelligent Science and Technology,2024,06(04):456-465. DOI： 10.11959/j.issn.2096-6652.202438.

摘要

目前在复杂的真实应用场景中，小人脸检测任务面临诸多挑战，如人脸尺度小、光照变化剧烈和精度较低等。针对现有模型容易忽视小人脸检测的问题，提出了一种基于卷积核注意力机制的小人脸检测模型SK-YOLOv5s。首先，设计一种小人脸增强模块，将浅层特征与深层特征进行融合与上采样，提高了小人脸特征图的分辨率，从而增强其特征；其次，在模型中引入SKNet注意力机制，能够多尺度自适应调节感受野大小，提高小人脸的检测率；最后，采用EIoU作为目标损失函数、FReLU作为激活函数，直接减小预测与真实边界框之间的宽度和高度差异，增强特征图的非线性表达能力，提高小人脸检测的精度和稳定性，相较于YOLOv5s，所改进模型在WIDER FACE数据集中的mAP提升了0.079。实验结果证明了所改进模型在真实场景下进行小人脸检测的可行性。

Abstract

At present

in the complex real-world application scenairos

the task of small face detection encounters numerous challenges

which include small face scale

abrupt lighting changes and low accuracy. In order to address the concerns of overlooking small face detection within existing models

this study introduced a novel small face detection model termed SK-YOLOv5s which was based on convolutional kernel attention mechanism. Firstly

we proposed a small face enhancement module to fuse and upsample multi-layer features

which enhances the resolution of small face feature maps and strengthens their distinctiveness. Subsequently

we incorporated the SKNet attention mechanism into the model

which can adaptively adjust receptive field sizes across multiple scales and enhance the detection efficacy of small face. Finally

EIoU was utilized as the loss function

which directly reduced the width and height discrepancies between predicted and actual bounding boxes

and FReLU was utilized as the activation function

which could enhance the nonlinear expressiveness of feature maps to improve the precision and stability of small face detection. The performance of the enhanced model on the WIDER FACE dataset demonstrated mean average precision improvement of 7.9% over YOLOv5s. The experimental results demonstrate the viability of the enhanced model for small face detection in real-world scenarios.

关键词

Keywords

references

郭凡, 卢铉宇, 李嘉怡, 等.基于深度神经网络的目标跟踪算法综述[J]. 航空兵器, 2024, 31(1): 1-12.

GUO F, LU X Y, LI J Y, et al. A review of target tracking algorithm based on deep neural network[J]. Aero Weaponry, 2024, 31(1): 1-12.

PANTIC M, ROTHKRANTZ L J M. Automatic analysis of facial expressions: the state of the art[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(12): 1424-1445.

KUMAR N, BERG A C, BELHUMEUR P N, et al. Attribute and simile classifiers for face verification[C]//Proceedings of the 2009 IEEE 12th International Conference on Computer Vision. Piscataway: IEEE Press, 2009: 365-372.

邱天衡, 王玲, 王鹏, 等.基于改进YOLOv5的目标检测算法研究[J]. 计算机工程与应用, 2022, 58(13): 63-73.

QIU T H, WANG L, WANG P, et al. Research on object detection algorithm based on improved YOLOv5[J]. Computer Engineering and Applications, 2022, 58(13): 63-73.

QI D L, TAN W J, YAO Q, et al. YOLO5Face: why reinventing a face detector[M]. Cham: Springer Nature Switzerland, 2023: 228-244.

高强, 唐福兴, 李栋, 等.基于改进YOLOv5的密集场景行人检测方法研究[J]. 国外电子测量技术, 2023, 42(4): 125-130.

GAO Q, TANG F X, LI D, et al. Research on pedestrian detection method in dense scene based on improved YOLOv5[J]. Foreign Electronic Measurement Technology, 2023, 42(4): 125-130.

LI X, WANG W H, HU X L, et al. Selective kernel networks[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2019: 510-519.

YANG S, LUO P, LOY C C, et al. WIDER FACE: a face detection benchmark[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2016: 5525-5533.

SCHAPIRE R E. The strength of weak learnability[J]. Machine Learning, 1990, 5(2): 197-227.

FREUND Y, SCHAPIRE R E. A desicion-theoretic generalization of online learning and an application to boosting[M]. Heidelberg: Springer, 1995: 23-37.

LIENHART R, MAYDT J. An extended set of Haar-like features for rapid object detection[C]//Proceedings of the International Conference on Image Processing. Piscataway: IEEE Press, 2002.

VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2001.

MITA T, KANEKO T, HORI O. Joint haar-like features for face detection[C]//Proceedings of the Tenth IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2005: 1619-1626.

ZHANG K P, ZHANG Z P, LI Z F, et al. Joint face detection and alignment using multitask cascaded convolutional networks[J]. IEEE Signal Processing Letters, 2016, 23(10): 1499-1503.

ZHANG S F, ZHU X Y, LEI Z, et al. S3FD: single shot scale-invariant face detector[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2017: 192-201.

HU P Y, RAMANAN D. Finding tiny faces[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2017: 1522-1530.

DENG J K, GUO J, ZHOU Y X, et al. Retinaface: single-stage denseface localisation in the wild[EB]. arXiv preprint, 2019, arXiv: 1905.00641.

ZHANG B, LI J, WANG Y B, et al. ASFD: automatic and scalableface detector[EB]. arXiv preprint, 2003, arXiv: 2003.11228.

ZHU Y J, CAI H X, ZHANG S H, et al. Tinaface: strong but simplebaseline for face detection[EB]. arXiv preprint, 2020, arXiv: 2011.13183.

HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2016: 770-778.

REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2017: 6517-6525.

WANG C Y, YEH I H, MARK LIAO H Y. YOLOv9: learning what you want to learn using programmable gradient information[M]. Cham: Springer Nature Switzerland, 2024: 1-21.

WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2023: 7464-7475.

田庆, 胡蓉, 李佐勇, 等. 基于SE-YOLOv5s的绝缘子检测[J]. 智能科学与技术学报, 2021, 3(3): 312-321.

TIAN Q, HU R, LI Z Y, et al. Insulator detection based on SE-YOLOv5s[J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(3): 312-321.

谢椿辉, 吴金明, 徐怀宇. 改进YOLOv5的无人机影像小目标检测算法[J]. 计算机工程与应用, 2023, 59(9): 198-206.

XIE C H, WU J M, XU H Y. Small object detection algorithm based on improved YOLOv5 in UAV image[J]. Computer Engineering and Applications, 2023, 59(9): 198-206.

ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and betterlearning for bounding box regression[EB]. arXiv preprint, 2019, arXiv:1911.08287.

ZHANG Y F, REN W Q, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.

GUO J, DENG J K, LATTAS A, et al. Sample and computation redistributionfor efficient face detection[EB]. arXiv preprint, 2021, arXiv:2105.04714.

LIU Y, WANG F, DENG J K, et al. MogFace: towards a deeper appreciation on face detection[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2022: 4083-4092.

XU Y Y, YAN W, YANG G K, et al. CenterFace: joint face detection and alignment using face as point[J]. Scientific Programming, 2020, 2020: 7845384.

ALBIERO V, CHEN X Y, YIN X, et al. img2pose: face alignment and detection via 6DoF, face pose estimation[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2021: 7613-7623.

BABILONI F, MARRAS I, KOKKINOS F, et al. Poly-NL: linear complexitynon-local layers with polynomials[EB]. arXiv preprint, 2021,arXiv: 2107.02859.

YOO Y, HAN D, YUN S. EXTD: extremely tiny face detector viaiterative filter reuse[EB]. arXiv preprint, 2019, arXiv: 1906.06579.

SUN X D, WU P C, HOI S C H. Face detection using deep learning: an improved faster RCNN approach[J]. Neurocomputing, 2018, 299: 42-50.

WANG J F, YUAN Y, YU G. Face attention network: an effective facedetector for the occluded faces[EB]. arXiv preprint, 2017, arXiv:1711.07246.

浏览量

226

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进 YOLOv5s 的小人脸检测

小样本细粒度图像分类的Mamba-小波多尺度建模方法

HCANet：基于分层Transformer架构的微表情识别模型

基于自适应池化注意力Transformer的唇语识别方法

注意力机制增强的输煤传送带异物检测