卷烟厂卷包车间工人违规作业行为检测方法

doi:10.11896/jsjkx.230700123

摘要/Abstract

摘要： 小目标检测一直是目标检测领域的难点,针对卷烟厂卷包车间摄像头安装位置较高、小目标检测精度低和总体检测精度较低的问题,提出了一种改进的YOLOv8n目标检测算法 YOLOv8n-FIAL。首先使用添加通道重排机制的C2fg模块代替原本C2f模块,提高特征学习能力,使用自适应通道特征融合模块代替YOLOv8n算法Neck部分的Concate操作,使特征融合更加充分;然后增加小目标检测层,提高小目标检测精度,降低漏检率;最后使用Focal-EIOU损失函数替换原来的CIOU损失函数,平衡锚框与真实框重叠较大的高质量锚框的数量远少于低质量锚框训练实例不平衡的问题。实验结果表明,在自制的卷烟厂工人违规作业数据集上,所提出的YOLOv8n-FIAL检测方法相比原始的YOLOv8n方法的总体平均精度均值提升了7.6%,对口鼻、手拿手机和衣服领口这3类小目标平均精度均值提升最大,分别提升了8.3%,8%和9.6%;在公共数据集VOC2007上,YOLOv8n-FIAL算法相比YOLOv8n算法的总体平均精度均值提升了1.6%。

关键词: 卷包车间, 小目标检测, YOLOv8n, YOLOv8n-FIAL, 自适应通道特征融合模块

Abstract: Small object detection has always been a difficult point in the field of object detection.In response to the high installation of cameras in cigarette factory packaging rooms,low accuracy of small object detection,and overall low detection accuracy,an improved YOLOv8n object detection algorithm YOLOv8n FIAL has been proposed.Firstly,the C2fg module with added channel rearrangement mechanism is used to replace the original C2f module to improve feature learning ability.The adaptive channel feature fusion module is used to replace the Concate operation in the Neck section of the YOLOv8n algorithm,making feature fusion more comprehensive;then,add a small target detection layer to improve the accuracy of small target detection and reduce the missed detection rate;finally,the Focal EIOU loss function is used to replace the original CIOU loss function.The number of high-quality anchor boxes with a large overlap between the balanced anchor box and the real box is much less than the problem of imbalanced training instances of low-quality anchor boxes.The experimental results show that on the self-made cigarette factory worker violation operation dataset,the YOLOv8n FIAL detection method proposed in this article has an overall average accuracy improvement of 7.6% compared to the original YOLOv8n method.The average accuracy improvement for the three types of small targets,namely mouth,nose,handheld phone,and clothing collar,is the largest,with increases of 8.3%,8%,and 9.6%,respectively;On the public dataset VOC2007,the YOLOv8n FIAL algorithm has an overall average accuracy improvement of 1.6% compared to the YOLOv8n algorithm.

Key words: Rolling car room, Small target detection, YOLOv8n, YOLOv8n FIAL, Adaptive channel feature fusion module

中图分类号:

TS48

刘恒, 林虹宇, 吴涛. 卷烟厂卷包车间工人违规作业行为检测方法[J]. 计算机科学, 2024, 51(6A): 230700123-8. https://doi.org/10.11896/jsjkx.230700123

LIU Heng, LIN Hongyu, WU Tao. Detection Method for Workers’ Illegal Operation Behavior in PackagingWorkshop of CigaretteFactory[J]. Computer Science, 2024, 51(6A): 230700123-8. https://doi.org/10.11896/jsjkx.230700123

参考文献

[1]HUANG Q L,HE X,CUI Y S.Reflections and suggestions on improving the operational efficiency of packaging equipment[J].China Equipment Engineering,2021(9):54-55.
[2]ZHANG Y T,HUANG D Q,WANG D W,et al.A Review on Research and Application of Deep Learning-based Target Detection Algorithms[J/OL].Computer engineering and Application:1-15.[2023-07-11].http://kns.cnki.net/kcms/detail/11.2127.TP.20230620.1746.002.html.
[3]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.
[4]HE K,GKIOXARI G,DOLLÁR P,et al.Mask r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2961-2969.
[5]HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[6]GIRSHICK R.Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision.2015:1440-1448.
[7]REN S,HE K,GIRSHICK R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[J].Advances in Neural Information Processing Systems,2015,28.
[8]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.
[9]REDMON J,FARHADI A.YOLO9000:better,faster,stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:7263-7271.
[10]REDMON J,FARHADI A.Yolov3:An incremental improve-ment[J].arXiv:1804.02767,2018.
[11]BOCHKOVSKIYA,WANG C Y,LIAO H Y M.Yolov4:Optimal speed and accuracy of object detection[J].arXiv:2004.10934,2020.
[12]JOCHER G,STOKEN A,BOROVEC J,et al.YOLOv5:v3.1-Bug Fixes and Performance Improvements[J].2020.
[13]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.
[14]LIU W,ANGUELOV D,ERHAN D,et al.Ssd:Single shotmultibox detector[C]//Computer Vision-ECCV 2016:14th European Conference,Amsterdam,The Netherlands,Part I 14.Springer International Publishing,2016:21-37.
[15]FU C Y,LIU W,RANGA A,et al.Dssd:Deconvolutional single shot detector[J].arXiv:1701.06659,2017.
[16]LI Z,ZHOU F.FSSD:feature fusion single shot multibox detector[J].arXiv:1712.00960,2017.
[17]TAN S Q,TANG G F,TU Y Y,et al.Classroom Monitoring Students Abnormal Behavior Detection System[J].Computer Engineering and Application,2022,58(7):176-184
[18]CHANG J,ZHANG G W,CHEN W J,et al.Gas station unsafe behavior detection based on YOLO-V3 algorithm[J].Chinese Journal of Safety Sciences,2023,33(2):31-37.
[19]ZHANG H M,ZHUANG X,ZHENG J T,et al.Optimizing Human Abnormal Behavior Detection Method of YOLO Network[J].Computer Engineering and Application,2023,59(7):242-249.
[20]YUAN B.Study of Unsafe Behavior Control Method for Improving Safety Production in Chemical Industry[J].Safety and Environmental Engineering,2015,22(6):95-98.
[21]ZHANG X,ZENG H,GUO S,et al.Efficient long-range attention network for image super-resolution[C]//European Conference on Computer Vision.Cham:Springer Nature Switzerland,2022:649-667.
[22]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.
[23]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.
[24]LIU S,HUANG D,WANG Y.Learning spatial fusion for single-shot object detection[J].arXiv:1911.09516,2019.
[25]WANG Q L,WU B G,ZHU P F,et al.ECA-Net:efficient channel attention for deep convolutional neural networks[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway.IEEE,2020:13708-13717.
[26]ZHOU X,WANG D,KRÄHENBÜHL P.Objectsaspoints[J].arXvi:1904.07850,2019.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed