nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg qikanlogo popupnotification paper
2024 03 v.39;No.122 61-72
基于改进YOLOv7的防护用品穿戴检测
基金项目(Foundation):
邮箱(Email):
DOI:
中文作者单位:

广东潮州卫生健康职业学院;

摘要(Abstract):

为缓解YOLOv7在检测个人防护用品时面临标签重写、标签分配不平衡和特征耦合等问题,提出一种基于改进YOLOv7的检测方法.首先去除YOLOv7的大尺度和中尺度输出层,以降低标签重写率,且保证输出层得到充分训练;其次将输出层的定位和分类解耦,避免不同任务的特征表示互相影响,并选择在边界框级别检测防护服,在关键点级别检测防护帽和防护手套;最后引入部分卷积,实现实时检测.为验证该方法的有效性,使用实验人员穿戴防护用品的图像数据对所提方法进行验证.结果表明,相比YOLOv7,该方法的精确率和召回率分别提高了4.1和4.5个百分点,FPS(Frames Per Second)提升了1.3帧,可满足实验室场景下的个人防护用品穿戴检测需求.

关键词(KeyWords): 个人防护用品;;穿戴检测;;YOLOv7;;单尺度输出;;特征解耦;;部分卷积
参考文献 [1] WU T C,LIU C W,LU M C. Safety climate in university and college laboratories:Impact of organizational and individual factors[J]. Journal of Safety Research,2007,38(1):91-102.
[2] ALI L,ALNAJJAR F,PARAMBIL M M A,et al. Development of YOLOv5-based real-time smart monitoring system for increasing lab safety awareness in educational institutions[J]. Sensors, 2022,22(22):8820.
[3] NUGRAHA K O P P,RIFAI A P. Convolutional neural network for identification of personal protective equipment usage compliance in manufacturing laboratory[J]. Jurnal Ilmiah Teknik Industri, 2023,22(1):11-24.
[4] KUMAR S,GUPTA H,YADAV D,et al. YOLOv4 algorithm for the real-time detection of fire and personal protective equipments at construction site s[J]. Multimedia Tools and Applications, 2022,81(16):22163-22183.
[5] DELHI V S K,SANKARLAL R,THOMAS A. Detection of personal protective equipment(PPE)compliance on construction site using computer vision based deep learning techniques[J]. Frontiers in Built Environment,2020,6:136.
[6] IANNIZZOTTO G,BELLO L L,PATTI G. Personal protection equipment detection system for embedded devices based on DNN and fuzzy logic[J]. Expert Systems with Applications,2021,184:115447.
[7] WU Y,CHEN Y,YUAN L,et al. Rethinking classification and localization for object detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,2020:10186-10195.
[8] JIANG B,LUO R,MAO J,et al. Acquisition of localization confidence for accurate object detection[C]//Proceedings of the European conference on computer vision(ECCV),2018:784-799.
[9] SONG G,LIU Y,WANG X. Revisiting the sibling head in object detector[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,2020:11563-11572.
[10] HURTIK P,MOLEK V,HULA J,et al. Poly-YOLO:higher speed,more precise detection and instance segmentation for YOLOv3[J]. Neural Computing and Applications,2022,34(10):8275-8290.
[11] 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.
[12] WANG C Y,BOCHKOVSKIY A,LIAO H Y M. YOLOv7:Trainable bag-of-freebies sets new stateof-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2023:7464-7475.
[13] 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&Machine Intelligence,2017,39(6):1137-1149.
[14] CARION N,MASSA F,SYNNAEVE G,et al. End-to-end object detection with transformers[C]//European conference on computer vision. Cham:SpringerInternational Publishing,2020:213-229.
[15] LI D,CHEN X,HUANG K. Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios[C]//2015 3rd IAPR Asian Conference on Pattern Recognition(ACPR). IEEE,2015:111-115.
[16] HOWARD A G,ZHU M,CHEN B,et al. Mobilenets:efficient convolutional neural networks for mobile vision applications[J/OL].[2023-11-01]. http://arxiv preprint arxiv:1704.04861,2017.
[17] ZHANG X,ZHOU X,LIN M,et al. Shufflenet:an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2018:6848-6856.
[18] HAN K,WANG Y,TIAN Q,et al. Ghostnet:More features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2020:1580-1589.
[19]程荣标,方向尧,曾思伟,等.基于Adaboost和回归树集合技术的疲劳识别研究[J].汕头大学学报(自然科学版),2017,32(2):66-74.
[20] YANG Y,RAMANAN D. Articulated human detection with flexible mixtures of parts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,35(12):2878-2890.
[21] TAN M,PANG R,LE Q V. Efficientdet:scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2020:10781-10790.
[22] TIAN Z, SHEN C, CHEN H, et al. FCOS:fully convolutional one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision,2019:9627-9636.
[23] HE K,GKIOXARI G,DOLLáR P,et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision,2017:2961-2969.
[24] MAO W,GE Y,SHEN C,et al. Poseur:direct human pose regression with transformers[C]//European Conference on Computer Vision,Cham:Springer Nature Switzerland,2022:72-88.
[25] YUAN K,GUO S,LIU Z,et al. Incorporating convolution designs into visual transformers[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision,2021:579-588.

基本信息:

DOI:

中图分类号:TP391.41

引用信息:

[1]杨晓帆,韦少钗.基于改进YOLOv7的防护用品穿戴检测[J].汕头大学学报(自然科学版),2024,39(03):61-72.

基金信息:

检 索 高级检索