改进轻量高效FMG-YOLOv8s的钢材表面缺陷检测算法

doi:10.3778/j.issn.1002-8331.2406-0358

摘要/Abstract

摘要： 针对当前钢材表面缺陷检测存在效率低和精度差等问题，以及现有缺陷检测模型结构复杂、参数量庞大、检测精度和实时性较差的挑战，基于YOLOv8s模型，提出一种轻量高效的钢材缺陷检测算法(FMG-YOLOv8s)。该方法采用轻量级的FasterNet网络作为骨干网络，降低模型复杂度并更好地处理多尺度特征信息，以提升检测性能；重构特征交互模块(M-C2f)，有效保留空间和通道特征，抑制冗余信息，促进检测精度和速度的提升；设计GS-Detect模块作为整体模型的检测网络，降低模型复杂度，提升训练和推理速度。在Severstal钢材缺陷数据集进行实验验证，相较于YOLOv8s算法，FMG-YOLOv8算法的mAP提升3.3个百分点，参数量和计算量分别降低8.2×106和2.21×1010，检测速度达到250?帧/s，召回率提升6.9个百分点。实验结果表明，该算法在检测精度、速度和轻量化方面取得更好的平衡，为边缘终端设备提供较高精度、轻量化和实时性的可靠参考。在NEU-DET缺陷数据集上进行泛化性验证，相较于原模型，mAP和检测速度分别提升3.1个百分点和185帧/s，结果显示该算法具备良好的鲁棒性。

关键词: 缺陷检测, 轻量化YOLOv8s, FasterNet, M-C2f, GS-Detect

Abstract: In response to the current challenges of low efficiency and poor accuracy in steel surface defect detection, as well as the complexity, large parameter size, and subpar detection accuracy and real-time performance of existing defect detection models, this paper proposes a lightweight and efficient steel defect detection algorithm (FMG-YOLOv8s) based on the YOLOv8s model. This method utilizes the lightweight FasterNet network as the backbone network to reduce model complexity and better handle multi-scale feature information for improved detection performance. The feature interaction module (M-C2f) is restructured to effectively preserve spatial and channel features, suppress redundant information, and enhance detection accuracy and speed. The GS-Detect module is designed as the detection network of the overall model to reduce model complexity and enhance training and inference speed. Experimental validation on the Severstal steel defect dataset shows that compared to the YOLOv8s algorithm, the FMG-YOLOv8 algorithm achieves a 3.3 percentage points improvement in mAP, while reducing parameter size and computational complexity by 8.2×106 and 2.21×1010 respectively, and reaching a detection speed of 250 frames per second with a 6.9 percentage points improvement in recall rate. Experimental results demonstrate that this algorithm strikes a better balance in terms of detection accuracy, speed, and lightweight design, providing reliable references for high-precision, lightweight, and real-time performance on edge-terminal devices. Generalization validation on the NEU-DET defect dataset shows a 3.1 percentage points improvement in mAP and 185 frames per second improvement in detection speed compared to the original model, indicating good robustness of the algorithm.

Key words: defect detection, lightweight YOLOv8s, FasterNet, M-C2f, GS-Detect

梁礼明, 龙鹏威, 李俞霖. 改进轻量高效FMG-YOLOv8s的钢材表面缺陷检测算法[J]. 计算机工程与应用, 2025, 61(3): 84-93.

LIANG Liming, LONG Pengwei, LI Yulin. Improved Lightweight and Efficient FMG-YOLOv8s Algorithm for Steel Surface Defect Detection[J]. Computer Engineering and Applications, 2025, 61(3): 84-93.

参考文献

[1] 梁礼明, 陈鑫, 余洁, 等. 多尺度注意力细化视网膜分割算法[J]. 计算机工程与应用, 2023, 59(6): 212-220.
LIANG L M, CHEN X, YU J, et al. Multi-scale attention refinement retinal segmentation algorithm[J]. Computer Engineering and Applications, 2023, 59(6): 212-220.
[2] 窦智, 高浩然, 刘国奇, 等. 轻量化YOLOv8的小样本钢板缺陷检测算法[J]. 计算机工程与应用, 2024, 60(9): 90-100.
DOU Z, GAO H R, LIU G Q, et al. Small sample steel plate defect detection algorithm of lightweight YOLOv8[J]. Computer Engineering and Applications, 2024, 60(9): 90-100.
[3] 高春艳, 秦燊, 李满宏, 等. 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.
GAO C Y, QIN S, LI M H, et al. Research on steel surface defect detection with improved YOLOv7 algorithm[J]. Computer Engineering and Applications, 2024, 60(7): 282-291.
[4] LIANG F T, ZHOU Y, CHEN X, et al. Review of target detection technology based on deep learning[C]//Proceedings of the 5th International Conference on Control Engineering and Artificial Intelligence. New York: ACM, 2021: 132-135.
[5] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Washington: IEEE Computer Society, 2015: 1440-1448.
[6] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[7] QIAN H, WANG H, FENG S, et al. FESSD: SSD target detection based on feature fusion and feature enhancement[J]. Journal of Real-Time Image Processing, 2023, 20(1): 2.
[8] JIANG P Y, ERGU D, LIU F Y, et al. A review of YOLO algorithm developments[J]. Procedia Computer Science, 2022, 199: 1066-1073.
[9] HUSSAIN M. YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection[J]. Machines, 2023, 11(7): 677.
[10] 卢俊哲, 张铖怡, 刘世鹏, 等. 面向复杂环境中带钢表面缺陷检测的轻量级DCN-YOLO[J]. 计算机工程与应用, 2023, 59(15): 318-328.
LU J Z, ZHANG C Y, LIU S P, et al. Lightweight DCN-YOLO for strip surface defect detection in complex environments[J]. Computer Engineering and Applications, 2023, 59(15): 318-328.
[11] QIN R, CHEN N, HUANG Y. EDDNet: an efficient and accurate defect detection network for the industrial edge environment[C]//Proceedings of the 2022 IEEE 22nd International Conference on Software Quality, Reliability and Security. Piscataway: IEEE, 2022: 854-863.
[12] YANG L, HUANG X, REN Y, et al. Steel plate surface defect detection based on dataset enhancement and lightweight convolution neural network[J]. Machines, 2022, 10(7): 523.
[13] 梁礼明, 龙鹏威, 冯耀, 等. 改进轻量化VTG-YOLOv7-tiny的钢材表面缺陷检测[J]. 光学精密工程, 2024, 32(8): 1227-1240.
LIANG L M, LONG P W, FENG Y, et al. Improved detection of steel surface defects with lightweight VTG-YOLOv7-tiny[J]. Optical Precision Engineering, 2024, 32(8): 1227-1240.
[14] ZHOU S, ZENG Y, LI S, et al. Surface defect detection of rolled steel based on lightweight model[J]. Applied Sciences, 2022, 12(17): 8905.
[15] 蔡剑锋, 柏俊杰, 张雪, 等. 基于改进Mask R-CNN 的金属板材表面缺陷检测[J]. 重庆科技学院学报 (自然科学版), 2023, 25(2): 110-116.
CAI J F, BO J J, ZHANG X, et al. Research on surface defect recognition of metal sheet based on improved Mask R-CNN[J]. Journal of Chongqing University of Science and Technology (Natural Science Edition), 2023, 25(2): 110-116.
[16] REDMON J, FARHADI A. Yolov3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[17] 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.
[18] WAN D, LU R, SHEN S, et al. Mixed local channel attention for object detection[J]. Engineering Applications of Artificial Intelligence, 2023, 123: 106442.
[19] LI H, LI J, WEI H, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[J]. arXiv:2206.02424, 2022.
[20] 曹义亲, 伍铭林, 徐露. 基于改进YOLOv5算法的钢材表面缺陷检测[J]. 图学学报, 2023, 44(2): 335-345.
CAO Y Q, WU M L, XU L. Steel surface defect detection based on improved YOLOv5 algorithm[J]. Journal of Graphics, 2023, 44(2): 335-345.
[21] 赵林熔, 甄国涌, 储成群, 等. 基于CBE-YOLOv5的钢材表面缺陷检测方法[J]. 电子测量技术, 2023, 46(15): 73-80.
ZHAO L R, ZHEN G Y, CHU C Q, et al. Detection method of steel surface defects based on CBE-YOLOv5[J]. Electronic Measurement Technology, 2023, 46(15): 73-80.
[22] GUO Z, WANG C, YANG G, et al. MSFT-YOLO: improved YOLOv5 based on transformer for detecting defects of steel surface[J]. Sensors, 2022, 22(9): 3467.