改进YOLOX网络的轴承缺陷小目标检测方法

doi:10.3778/j.issn.1002-8331.2206-0100

摘要/Abstract

摘要： 针对深度学习模型在工业轴承表面缺陷检测中多目标情形下的小目标漏检率高、模型特征融合不充分的问题，基于YOLOX提出一种多注意力特征加权融合的小目标缺陷检测算法。在骨干网络引入特征提取更加细粒度的Res2Block模块，同时嵌入自注意力机制，增加隐性小目标的区域特征，减少漏检率；设计内嵌坐标注意力并作为加权条件的双路金字塔特征融合网络，提升浅层细节特征和深层高级语义特征的交互融合能力；后处理阶段引入Focal Loss损失函数，增加模型对正样本目标的学习，进一步减少漏检率。实验结果表明，与原YOLOX算法相比，改进算法在自制小型列车轴承表面缺陷数据集上mAP提高了4.04个百分点，对小目标的识别率明显提升。

关键词: 轴承表面缺陷检测, YOLOX, 自注意力, 特征加权融合, 坐标注意力

Abstract: Aiming at the problems of high miss detection rate of small targets and insufficient model feature fusion in multi-target case of deep learning model in industrial bearing surface defect detection, a small target defect detection algorithm based on multi-attention feature weighted fusion is proposed based on YOLOX. In the backbone network, a more fine-grained Res2Block module for feature extraction is introduced, and a self-attention mechanism is embedded to increase the regional features of hidden small targets and reduce the missed detection rate. It designs a two-way Pyramid feature fusion network with embedded coordinate attention as a weighting condition to improve the interactive fusion ability of shallow detail features and deep high-level semantic features. In the post-processing stage, the Focal Loss function is introduced to increase the learning of the model on the target of positive samples and further reduce the missed detection rate. The experimental results show that compared with the original YOLOX algorithm, the improved algorithm improves the mAP by 4.04 percentage points on the self-made small train bearing surface defect dataset, which significantly improves the recognition rate of dense small targets.

Key words: bearing surface defect detection, YOLOX, self-attention, feature weighted fusion, coordinate attention

李亚东, 马行, 穆春阳, 李建东. 改进YOLOX网络的轴承缺陷小目标检测方法[J]. 计算机工程与应用, 2023, 59(1): 100-107.

LI Yadong, MA Xing, MU Chunyang, LI Jiandong. Improved Small Target Detection Method of Bearing Defects in YOLOX Network[J]. Computer Engineering and Applications, 2023, 59(1): 100-107.

参考文献

[1] 陈金贵，陈昊，张奔.基于改进Niblack算法的轴承滚子表面缺陷检测[J].组合机床与自动化加工技术，2018（12）：82-85.
CHEN J G，CHEN H，ZHANG B.Research on surface defect detection of bearing roller based on improved niblack algorithm[J].Modular Machine Tool & Automatic Manufacturing Technique，2018（12）：82-85.
[2] 魏利胜，丁坤，段志达，等.融合单应性约束SIFT特征匹配的轴承滚子检测[J].电子测量与仪器学报，2019，33（9）：107-113.
WEI L S，DING K，DUAN Z D，et al.Bearing roller detection based on SIFT feature matching with homography constraints[J].Journal of Electronic Measurement and Instrument，2019，33（9）：107-113.
[3] 陈硕，林志敏，吴岳彬，等.轴承套圈端面缺陷在线视觉检测的研究与实现[J].轴承，2022（2）：48-54.
CHEN S，LIN Z M，WU Y B，et al.Research and implementation of on-line visual inspection of defects on end face of bearing rings[J].Bearing，2022（2）：48-54.
[4] KRIZHEVSKY A，SUTSKEVER I，HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM，2017，60（6）：84-90.
[5] 徐镪，朱洪锦，范洪辉，等.改进的YOLOv3网络在钢板表面缺陷检测研究[J].计算机工程与应用，2020，56（16）：265-272.
XU Q，ZHU H J，FAN H H，et al.Study on detection of steel plate surface defects by improved YOLOv3 network[J].Computer Engineering and Applications，2020，56（16）：265-272.
[6] REDMON J，FARHADI A.YOLOv3：An incremental improvement[C]//Proceedings of the IEEE Computer Vision and Pattern Recognition（CVPR），2018：1-4.
[7] 程婧怡，段先华，朱伟.改进YOLOv3的金属表面缺陷检测研究[J].计算机工程与应用，2021，57（19）：252-258.
CHENG J Y，DUAN X H，ZHU W.Research on metal surface defect detection by improved YOLOv3[J].Computer Engineering and Applications，2021，57（19）：252-258.
[8] 王紫玉，张果，杨奇，等.基于YOLOv4的铜带表面缺陷识别研究[J].光电子激光，2022，33（2）：163-170.
WANG Z Y，ZHANG G，YANG Q，et al.Research on surface defect recognition of copper strip based on YOLOv4[J].Journal of Optoelectronics·Laser，2022，33（2）：163-170.
[9] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：Optimal speed and accuracy of object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2020.
[10] 石振华，陈杰.改进YOlOv3算法在工件缺陷检测中的应用[J].机械设计与制造，2021（4）：62-65.
SHI Z H，CHEN J.Research on the detection of workpiece surface defects based on YOLOv3[J].Machinery Design & Manufacture，2021（4）：62-65.
[11] GE Z，LIU S，WANG F，et al.YOLOX：Exceeding YOLO series in 2021[J].arXiv：2107.08430，2021.
[12] WANG C Y，MARK LIAO H Y，WU Y H，et al.CSPNet：A new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，2020：1571-1580.
[13] 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，2021，43（2）：652-662.
[14] LI Y H，YAO T，PAN Y W，et al.Contextual transformer networks for visual recognition[J].arXiv：2107.12292，2021.
[15] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[16] WOO S，PARK J，LEE J Y，et al.CBAM：Convolutional block attention module[C]//Proceedings of the 2018 European Conference on Computer Vision，2018：3-19.
[17] LIU S，QI L，QIN H F，et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：8759-8768.
[18] TAN M，PANG R，LE Q V.EfficientDet：Scalable and efficient object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2020：10778-10787.
[19] HOU Q，ZHOU D，FENG J.Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：13713-13722.
[20] SZEGEDY C，VANHOUCKE V，IOFFE S，et al.Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：2818-2826.
[21] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（2）：318-327.