FLM-YOLOv8：一种轻量级的口罩佩戴检测算法

doi:10.3778/j.issn.1002-8331.2402-0226

摘要/Abstract

摘要： 针对现有的口罩佩戴检测模型无法较好平衡检测精度与速度，参数量较大，漏检和误检率高等问题，提出了一种轻量级的口罩佩戴检测算法FLM-YOLOv8。使用轻量级FasterNet替换YOLOv8n的主干特征提取网络，提升网络检测速度；融合FasterNet Block改进C2f模块，降低模型计算复杂度；提出SPPF-LSKA结构，增强模型的特征表达能力和感知能力，提高网络检测精度；设计Inner-MPDIoU边界框回归损失函数，提高回归预测精度，加快收敛速度。创建标注了一个复杂多元场景下的口罩佩戴数据集，并使用马赛克数据增强，以提高网络泛化能力。实验结果表明，该算法在正确佩戴口罩、未正确佩戴口罩和未佩戴口罩目标上的mAP@0.5达到了91.3%，FPS达到了143.6，实现了更加实时准确的口罩佩戴检测。

关键词: 口罩佩戴检测, YOLOv8, FasterNet, 轻量级, 损失函数

Abstract: Aiming at the problems that the existing mask wearing detection model can’t balance the detection accuracy and speed well, the parameters are large, and the rate of missed and false detection is high, a lightweight mask wearing detection algorithm FLM-YOLOv8 is proposed. Firstly, the lightweight FasterNet is used to replace the backbone feature extraction network of YOLOv8n to improve the network detection speed. Secondly, the C2f module is improved by combining FasterNet Block to reduce the computational complexity of the model. Then, the structure of SPPF-LSKA is proposed to enhance the feature expression ability and perception ability of the model and improve the network detection accuracy. Finally, the Inner-MPDIoU bounding box regression loss function is designed to improve the regression prediction accuracy and accelerate the convergence speed. In addition, a mask wearing data set marked with a complex and diverse scene is created and enhanced with mosaic data to improve the network generalization ability. The experimental results show that the mAP@0.5 of the algorithm on the targets wearing masks correctly, not wearing masks correctly and not wearing masks reaches 91.3%, and the FPS reaches 143.6, which realizes more real-time and accurate mask wearing detection.

Key words: mask wearing detection, YOLOv8, FasterNet, lightweight, loss function

高民, 陈高华, 古佳欣, 张春美. FLM-YOLOv8：一种轻量级的口罩佩戴检测算法[J]. 计算机工程与应用, 2024, 60(17): 203-215.

GAO Min, CHEN Gaohua, GU Jiaxin, ZHANG Chunmei. FLM-YOLOv8：Lightweight Mask Wearing Detection Algorithm[J]. Computer Engineering and Applications, 2024, 60(17): 203-215.

参考文献

[1] LI F, WANG X, SUN Y, et al. Transfer learning based cascaded deep learning network and mask recognition for COVID-19[J]. World Wide Web, 2023, 26: 1-16.
[2] HIMEUR Y, AL-MAADEED S, ALMAADEED N, et al. Deep visual social distancing monitoring to combat COVID-19: a comprehensive survey[J]. Sustainable Cities and Society, 2022, 85: 104064.
[3] FANELLI D, PIAZZA F. Analysis and forecast of COVID-19 spreading in China, Italy and France[J]. Chaos, Solitons & Fractals, 2020, 134: 109761.
[4] GALBADAGE T, PETERSON B M, GUNASEKERA R S. Does COVID-19 spread through droplets alone?[J]. Frontiers in Public Health, 2020, 8: 546353.
[5] LIU Y, GAYLE A A, WILDER-SMITH A, et al. The reproductive number of COVID-19 is higher compared to SARS coronavirus[J]. Journal of Travel Medicine, 2020, 27(2): 1-4.
[6] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
[7] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[8] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[9] 李泽琛, 李恒超, 胡文帅, 等. 多尺度注意力学习的 Faster R-CNN口罩人脸检测模型[J]. 西南交通大学学报, 2021, 56(5): 1002-1010.
LI Z C, LI H C, HU W S, et al. Masked face detection model based on multi-scale attention-driven Faster RCNN[J]. Journal of Southwest JiaoTong University, 2021, 56(5): 1002-1010.
[10] GAO S H, CHENG M M, ZHAO K, et al. Res2Net: a new multi-scale backbone architecture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43(2): 652-662.
[11] GUPTA P, SHARMA V, VARMA S. A novel algorithm for mask detection and recognizing actions of human[J]. Expert Systems with Applications, 2022, 198: 116823.
[12] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
[13] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017: 6517-6525.
[14] FARHADI A, REDMON J. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[15] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLO v4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[16] LI C, LI L, JIANG H, et al. YOLOv6: a single-stage object detection framework for industrial applications[J]. arXiv:2209.02976, 2022.
[17] 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 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 7464-7475.
[18] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[J]. arXiv:1512.02325, 2015.
[19] 任小康, 刘行行. 基于改进的YOLOv3口罩佩戴检测和识别[J]. 计算机工程与科学, 2022, 44(10): 1812-1821.
REN X K, LIU X X. Mask wearing detection and recognition based on the improved YOLOv3[J]. Computer Engineering & Science, 2022, 44(10): 1812-1821.
[20] 项融融, 李博, 赵桥. 基于改进YOLOv5s的口罩佩戴检测算法[J]. 国外电子测量术, 2022, 41(7): 39-44.
XIANG R R, LI B, ZHAO Q. Mask wearing detection algorithm based on improved YOLOv5s[J]. Foreign Electronic Measurement Technology, 2022, 41(7): 39-44.
[21] WANG Y, DING H, LI B, et al. Mask wearing detection algorithm based on improved YOLOv3 in complex scenes[J]. Computer Engineer, 2020, 46(11): 12-22.
[22] WANG C, ZHANG B, CAO Y, et al. Mask detection method based on YOLO-GBC network[J]. Electronics, 2023, 12(2): 408.
[23] WANG J, WANG J, ZHANG X, et al. A mask-wearing detection model in complex scenarios based on YOLOv7-CPCSDSA[J]. Electronics, 2023, 12(14): 3128.
[24] 程浩然, 王薪陶, 李俊燃, 等. 改进YOLOv4-tiny的疫情协同口罩佩戴检测方法[J]. 计算机工程与应用, 2023, 59(20): 208-218.
CHENG H R, WANG X T, LI J R, et al. Improved YOLOv4-tiny epidemic collaborative mask wearing detection method[J]. Computer Engineering and Applications, 2023, 59(20): 208-218.
[25] 叶茂, 马杰, 王倩, 等. 多尺度特征融合的轻量化口罩佩戴检测算法[J]. 计算机工程, 2022, 48(7): 42-50.
YE M, MA J, WANG Q, et al. Lightweight mask-wearing detection algorithm with multi-scale feature fusion[J]. Computer Engineering, 2022, 48(7): 42-50.
[26] 李莉, 刘阳, 王巍, 等. 多尺度通道注意力机制的口罩佩戴检测算法[J]. 计算机工程与设计, 2023, 44(2): 598-604.
LI L, LIU Y, WANG W, et al. Mask wearing detection algorithm based on multi-scale channel attention mechanism[J]. Computer Engineering and Design, 2023, 44(2): 598-604.
[27] 黄家興, 南新元, 张文龙, 等. 基于改进YOLOv5的轻量化口罩检测算法研究[J]. 计算机仿真, 2023, 40(5): 541-547.
HUANG J X, NAN X Y, ZHANG W L, et al. Research on lightweight mask detection algorithm based on improved YOLOv5[J]. Computer Simulation, 2023, 40(5): 541-547.
[28] 刘翀豪, 潘理虎, 杨帆, 等. 改进YOLOv5的轻量化口罩检测算法[J]. 计算机工程与应用, 2023, 59(7): 232-241.
LIU C H, PAN L H, YANG F, et al. Improved YOLOv5 lightweight mask detection algorithm[J]. Computer Engineering and Applications, 2023, 59(7): 232-241.
[29] 李梦茹, 肖秦琨, 韩泽佳. 基于改进YOLOv5的人脸口罩佩戴检测[J]. 计算机工程与设计, 2023, 44(9): 2811-2821.
LI M R, XIAO Q K, HAN Z J. Face mask wearing detection based on improved YOLOv5 algorithm[J]. Computer Engineering and Design, 2023, 44(9): 2811-2821.
[30] 孙龙, 张荣芬, 刘宇红, 等. 监控视角下密集人群口罩佩戴检测算法[J]. 计算机工程, 2023, 49(9): 313-320.
SUN L, ZHANG R F, LIU Y H, et al. Mask wearing detection algorithm for dense crowds from a monitoring perspective[J]. Computer Engineering, 2023, 49(9): 313-320.
[31] 付惠琛, 高军伟, 车鲁阳. 基于改进YOLOv7的口罩佩戴检测[J]. 液晶与显示, 2023, 38(8): 1139-1147.
FU H C, GAO J W, CHE L Y. Mask wearing detection based on improved YOLOv7[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(8): 1139-1147.
[32] ZHOU J, ZHANG B, YUAN X, et al. YOLO-CIR: the network based on YOLO and ConvNeXt for infrared object detection[J]. Infrared Physics & Technology, 2023, 131: 104703.
[33] 王春梅, 刘欢. YOLOv8-VSC: 一种轻量级的带钢表面缺陷检测算法[J]. 计算机科学与探索, 2024, 18(1): 151-160.
WANG C M, LIU H. YOLOv8-VSC: lightweight algorithm for strip surface defect detection[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(1): 151-160.
[34] 张华卫, 张文飞, 蒋占军, 等. 引入上下文信息和Attention Gate的GUS-YOLO遥感目标检测算法[J]. 计算机科学与探索, 2024, 18(2): 453-464.
ZHANG H W, ZHANG W F, JIANG Z J, et al. GUS-YOLO remote sensing target detection algorithm introducing context information and attention gate[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(2): 453-464.
[35] ZHANG S, CHI C, YAO Y, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 9759-9768.
[36] CHEN J, KAO S, HE H, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 12021-12031.
[37] GUO M H, LU C Z, LIU Z N, et al. Visual attention network[J]. Computational Visual Media, 2023, 9(4): 733-752.
[38] LAU K W, PO L M, REHMAN Y A U. Large separable kernel attention: rethinking the large kernel attention design in CNN[J]. Expert Systems with Applications, 2024, 236: 121352.
[39] ZHENG Z, WANG P, REN D, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J]. IEEE Transactions on Cybernetics, 2021, 52(8): 8574-8586.
[40] ZHANG H, XU C, ZHANG S. Inner-IoU: more effective intersection over union loss with auxiliary bounding box[J]. arXiv:2311.02877, 2023.
[41] ZHANG Y F, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.
[42] GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[J]. arXiv:2205.12740, 2022.
[43] SILIANG M, YONG X. MPDIoU: a loss for efficient and accurate bounding box regression[J]. arXiv:2307.07662, 2023.
[44] CHEN H, WANG Y, GUO J, et al. VanillaNet: the power of minimalism in deep learning[J]. arXiv:2305.12972, 2023.
[45] LIU Z, LIN Y, CAO Y, et al. Swin Transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 10012-10022.
[46] LI Y, HOU Q, ZHENG Z, et al. Large selective kernel network for remote sensing object detection[J]. arXiv:2303.09030, 2023.
[47] CAI Y, ZHOU Y, HAN Q, et al. Reversible column networks[J]. arXiv:2212.11696, 2022.
[48] CAI H, LI J, HU M, et al. EfficientViT: multi-scale linear attention for high-resolution dense prediction[J]. arXiv:2205.14756, 2022.