DCD-YOLOv8n：一种高效的钢材表面缺陷检测算法

doi:10.3778/j.issn.1002-8331.2409-0248

摘要/Abstract

摘要： 针对现有钢材表面缺陷检测算法资源消耗较大、检测精度和效率较低等问题，提出一种基于YOLOv8n的高效钢材缺陷检测算法（DCD-YOLOv8n）。该方法一是设计轻量化的多分支特征聚合网络，有效精简模型体积并提升检测速度；二是利用跨维度聚合模块，通过自适应机制建模多维度特征，以提升检测精度；三是采用可变形多头注意力机制，动态调整注意力的形状和范围，有效应对形态多样和结构复杂的缺陷特征，从而提升检测性能。在Severstal和NEU-DET钢材缺陷数据集上进行实验验证，相较于YOLOv8n算法，DCD-YOLOv8n算法的mAP分别提高2.4个百分点和1.9个百分点；参数量和复杂度分别降低0.5×106和1.9×109；FPS分别提升22帧和7帧。实验结果表明，该算法在平衡计算开销、检测精度和效率方面表现优异，具有一定的实际部署应用价值。

关键词: 缺陷检测, YOLOv8n, 多分支特征聚合网络, 跨维度聚合模块, 可变形多头注意力机制

Abstract: To address the issues of high resource consumption, and low detection accuracy and efficiency in existing steel surface defect detection algorithms, a high-efficiency steel defect detection algorithm based on YOLOv8n, named DCD-YOLOv8n, is proposed. Firstly, a lightweight diverse branch block efficient layer aggregation network is designed to effectively reduce model size and enhance detection speed. Secondly, a cross-dimensional aggregation module is utilized to model multi-dimensional features via adaptive mechanisms, improving detection accuracy. Finally, a deformable multi-head attention mechanism is introduced to dynamically adjust the shape and scope of attention, effectively handling defects with diverse shapes and complex structures, and thus enhancing detection performance. Experimental validation on the Severstal and NEU-DET steel defect datasets shows that, compared to the YOLOv8n algorithm, the DCD-YOLOv8n algorithm achieves improvements in mAP of 2.4% and 1.9% respectively, reduces in parameters and computations of 0.5×106 and 1.9×109 respectively, and increases in FPS of 22 and 7 frames respectively. The experimental results demonstrate that the algorithm excels in balancing computational cost, detection accuracy, and efficiency, offering significant practical deployment value.

Key words: defect detection, YOLOv8n, diverse branch block efficient layer aggregation network, cross-dimensional integration module, deformable multi-head attention mechanism

梁礼明, 陈康泉, 钟奕, 龙鹏威, 冯耀. DCD-YOLOv8n：一种高效的钢材表面缺陷检测算法[J]. 计算机工程与应用, 2025, 61(7): 117-127.

LIANG Liming, CHEN Kangquan, ZHONG Yi, LONG Pengwei, FENG Yao. DCD-YOLOv8n：Efficient Algorithm for Steel Surface Defect Detection[J]. Computer Engineering and Applications, 2025, 61(7): 117-127.

参考文献

[1] 徐洪俊, 唐自强, 张锦东, 等. 钢材表面缺陷检测的YOLOv5s算法优化研究[J]. 计算机工程与应用, 2024, 60(7): 306-314.
XU H J, TANG Z Q, ZHANG J D, et al. Research on optimization of YOLOv5s detection algorithm for steel surface defect[J]. Computer Engineering and Applications, 2024, 60(7): 306-314.
[2] 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.
[3] 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. Improving the lightweight VTG-YOLOv7-tiny for steel surface defect detection[J]. Optics and Precision Engineering, 2024, 32(8): 1227-1240.
[4] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587.
[5] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference Computer Vision. Cham: Springer, 2016: 21-37.
[6] 徐彦威, 李军, 董元方, 等. YOLO系列目标检测算法综述[J]. 计算机科学与探索, 2024, 18(9): 2221-2238.
XU Y W, LI J, DONG Y F, et al. Survey of development of YOLO object detection algorithms[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(9): 2221-2238.
[7] 盛帅, 段先华, 胡维康, 等. Dynamic-YOLOX: 复杂背景下的苹果叶片病害检测模型[J]. 计算机科学与探索, 2024, 18(8): 2118-2129.
SHENG S, DUAN X H, HU W K, et al. Dynamic-YOLOX: detection model for apple leaf disease in complex background[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(8): 2118-2129.
[8] ZENG S, YANG W Z, JIAO Y Y, et al. SCA-YOLO: a new small object detection model for UAV images[J]. The Visual Computer, 2024, 40(3): 1787-1803.
[9] 周孟然, 王昊男, 高立鹏, 等. 基于YOLOv5s-FCS的钢材表面缺陷检测[J]. 科学技术与工程, 2024, 24(14): 5901-5910.
ZHOU M R, WANG H N, GAO L P, et al. Steel surface defect detection based on YOLOv5s-FCS[J]. Science Technology and Engineering, 2024, 24(14): 5901-5910.
[10] 刘毅, 蒋三新. 基于改进YOLOX的钢材表面缺陷检测研究[J]. 现代电子技术, 2024, 47(9): 131-138.
LIU Y, JIANG S X. Steel surface defect detection algorithm based on improved YOLOX[J]. Modern Electronics Technique, 2024, 47(9): 131-138.
[11] 李相垚, 侯红玲, 杨澳, 等. 面向钢材表面缺陷检测的DCS-YOLOv8算法研究[J/OL]. 机械科学与技术: 1-10[2024-11-07]. https://doi.org/10.13433/j.cnki.1003-8728.20240128.
LI X Y, HOU H L, YANG A, et al. Research on DCS-YOLOv8 algorithm for steel surface defect detection[J/OL]. Mechanical Science and Technology for Aerospace Engineering: 1-10[2024-11-07]. https://doi.org/10.13433/j.cnki.1003-8728.20240128.
[12] 徐薪羽, 沈通, 吕佳. 基于改进YOLOv8算法的钢材表面缺陷检测[J]. 自动化应用, 2024(15): 6-10.
XU X Y, SHEN T, LV J. Steel surface defect detection based on improved YOLOv8 algorithm[J]. Automation Application, 2024(15): 6-10.
[13] REIS D, KUPEC J, HONG J, et al. Real-time flying object detection with YOLOv8[J]. arXiv:2305.09972, 2023.
[14] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017.
[15] XIA Z F, PAN X R, SONG S J, et al. DAT++: spatially dynamic vision transformer with deformable attention[J]. arXiv:2309.01430, 2023.
[16] YU Y, ZHANG Y, CHENG Z Y, et al. MCA: multidimensional collaborative attention in deep convolutional neural networks for image recognition[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 107079.
[17] WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 7464-7475.
[18] WANG C Y, YEH I H, LIAO H M. YOLOv9: learning what you want to learn using programmable gradient information[J]. arXiv:2402.13616, 2024.
[19] DING X H, ZHANG X Y, HAN J G, et al. Diverse branch block: building a convolution as an inception-like unit[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 10881-10890.
[20] YEUNG C C, LAM K M. Efficient fused-attention model for steel surface defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 2510011.
[21] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141.
[22] YANG L, ZHANG R Y, LI L, et al. SimAM: a simple, parameter-free attention module for convolutional neural networks[C]//Proceedings of the International Conference on Machine Learning, 2021: 11863-11874.
[23] CAI X H, LAI Q X, WANG Y W, et al. Poly kernel inception network for remote sensing detection[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 27706-27716.
[24] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision, 2018: 3-19.