Research on Steel Surface Defect Detection with Improved YOLOv7 Algorithm

doi:10.3778/j.issn.1002-8331.2308-0414

Abstract

Abstract: At present, the intelligent inspection technology based on deep learning is gradually applied to the field of steel surface defect detection. Aiming at the problem of low precision of steel surface defect detection, a high-precision and real-time defect detection algorithm CDN-YOLOv7 is proposed. Firstly, CARAFE lightweight up-sampling operator is added to improve the feature fusion capability of the network. Then, the YOLOv7 detection head network is redesigned by integrating the cascade attention mechanism and decoupling heads, aiming to solve the problem of low feature utilization efficiency of the original head network and make full use of multi-dimensional information of different scales, channels and spaces, improve the ability of model representation in complex scenarios. Finally, normalized Wasserstein distance is introduced to redesign Focal-EIoU loss function, and NF-EIoU is proposed to replace CIoU loss, balance the contribution of defect samples at different scales to loss, and reduce the missed detection rate of defects at different scales. The experimental results show that the detection accuracy of CDN-YOLOv7 can reach 80.3%, which is 6.0 percentage points higher than that of the original YOLOv7, and the model reasoning speed can reach 60.8 frame/s, meeting the real-time requirements. While improving the detection accuracy of defects at various scales, CDN-YOLOv7 significantly reduces the missed detection rate of defects.

Key words: machine vision, steel surface, defect detection, CDN-YOLOv7

摘要： 当前，基于深度学习的智能检测技术逐步应用于钢材表面缺陷检测领域，针对钢材表面缺陷检测精度低的问题，提出一种高精度实时的缺陷检测算法CDN-YOLOv7。加入CARAFE轻量化上采样算子来改善网络特征融合能力，融合级联注意力机制和解耦头重新设计YOLOv7检测头网络，旨在解决原始头网络特征利用效率不高的问题，使其充分利用各尺度、通道、空间的多维度信息，提升复杂场景下模型表征能力。引入归一化Wasserstein距离重新设计Focal-EIoU损失函数，提出NF-EIoU替换CIoU损失，平衡各尺度缺陷样本对Loss的贡献，降低各尺度缺陷的漏检率。实验结果表明，CDN-YOLOv7的检测精度可达80.3%，较于原YOLOv7精度提升了6.0个百分点，模型推理速度可达60.8帧/s，满足实时性需求，CDN-YOLOv7在提升各尺度缺陷检测精度的同时显著降低了缺陷的漏检率。

关键词: 机器视觉, 钢材表面, 缺陷检测, CDN-YOLOv7

GAO Chunyan, QIN Shen, LI Manhong, LYV Xiaoling. Research on Steel Surface Defect Detection with Improved YOLOv7 Algorithm[J]. Computer Engineering and Applications, 2024, 60(7): 282-291.

高春艳, 秦燊, 李满宏, 吕晓玲. 改进YOLOv7算法的钢材表面缺陷检测研究[J]. 计算机工程与应用, 2024, 60(7): 282-291.

References

[1] 杨泽青, 张明轩, 陈英姝, 等. 基于机器视觉的表面缺陷检测方法研究进展[J]. 现代制造工程, 2023(4): 143-156.
YANG Z Q, ZHANG M X, CHEN Y S, et. al. Review of surface defect detection methods based on machine vision[J]. Modern Manufacturing Engineering, 2023(4): 143-156.
[2] 杨传礼, 张修庆. 基于机器视觉和深度学习的材料缺陷检测应用综述[J]. 材料导报, 2022, 36(16): 226-234.
YANG C L, ZHANG X Q. Survey of applications of material defect detection based on machine vision and deep learning[J]. Materials Reports, 2022, 36(16): 226-234.
[3] CZIMMERMANN T, CIUTI G, MILAZZO M, et al. Visual-based defect detection and classification approaches for industrial applications—a survey[J]. Sensors, 2020, 20(5): 1459.
[4] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015.
[5] 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.
[6] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 2016: 21-37.
[7] 杨珂, 方诚, 段黎明. 基于深度学习模型融合的铸件缺陷自动检测[J]. 仪器仪表学报, 2021, 42(11): 150-159.
YANG K, FANG C, DUAN L M. Automatic detection of casting defects based on deep learning model fusion[J]. Chinese Journal of Instrument, 2021, 42(11): 150-159.
[8] SHI X, ZHOU S, TAI Y, et al. An improved Faster R-CNN for steel surface defect detection[C]//2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP), 2022: 1-5.
[9] 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.
[10] 窦智, 胡晨光, 李庆华, 等. 改进YOLOv7的小样本钢板表面缺陷检测算法[J]. 计算机工程与应用, 2023, 59(23): 283-292.
DOU Z, HU C G, LI Q H, et al. Improved YOLOv7 algorithm for small sample steel plate surface defect detection[J]. Computer Engineering and Applications, 2023, 59(23): 283-292.
[11] WANG Y, WANG H, XIN Z. Efficient detection model of steel strip surface defects based on YOLO-V7[J]. IEEE Access, 2022, 10: 133936-133944.
[12] YE G, QU J, TAO J, et al. Autonomous surface crack identification of concrete structures based on the YOLOv7 algorithm[J]. Journal of Building Engineering, 2023, 73: 106688.
[13] 翟永杰, 赵晓瑜, 王璐瑶, 等. IDD-YOLOv7: 一种用于输电线路绝缘子多缺陷的轻量化检测方法[J/OL]. 图学学报, 1-12[2023-12-01]. http://kns.cnki.net/kcms/detail/10.1034.T.20231101.1642.006.html.
ZHAI Y J, ZHAO X Y, WANG L Y, et. al. IDD-YOLOv7: a lightweight method for multiple defect detection of insulators in transmission lines[J/OL]. Journal of Graphics: 1-12[2023-12-01]. http://kns.cnki.net/kcms/detail/10.1034.T.
20231101.1642.006.html.
[14] HUANG P, WANG S, CHEN J, et al. Lightweight model for pavement defect detection based on improved YOLOv7[J]. Sensors, 2023, 23(16): 7112.
[15] WANG J, CHEN K, XU R, et al. Carafe: content-aware reassembly of features[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 3007-3016.
[16] DAI X, CHEN Y, XIAO B, et al. Dynamic head: unifying object detection heads with attentions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 7373-7382.
[17] CHEN Y, DAI X, LIU M, et al. Dynamic relu[C]//European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 351-367.
[18] WANG J, XU C, YANG W, et al. A normalized Gaussian Wasserstein distance for tiny object detection[J]. arXiv:2110.13389, 2021.
[19] ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 12993-13000.
[20] ZHANG Y F, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. arXiv:2101.08158, 2021.
[21] 向宽, 李松松, 栾明慧, 等. 基于改进Faster RCNN的铝材表面缺陷检测方法[J]. 仪器仪表学报, 2021, 42(1): 191-198.
XIANG K, LI S S, LUAN M H, et al. Aluminum product surface defect detection method based on improved Faster RCNN[J]. Chinese Journal of Instrument, 2021, 42(1): 191-198.
[22] GE Z, LIU S, WANG F, et al. Yolox: exceeding yolo series in 2021[J]. arXiv:2107.08430, 2021.