面向工业场景带钢表面缺陷检测的LF-YOLO

doi:10.3778/j.issn.1002-8331.2404-0411

摘要/Abstract

摘要： 针对工业场景下带钢表面缺陷尺寸大小不一、采集图像模糊导致传统缺陷检测算法在实际应用中精度低的问题，提出一种面向工业场景带钢表面缺陷检测的LF-YOLO算法。模型通过设计一种局部填充上采样模块对输入像素进行上采样，提高模型对模糊图片的识别能力，降低模型对小目标缺陷的漏检率。通过引入专注视觉任务的FReLU激活函数，提高模型定位缺陷的准确率。提出一种轻量级的漏斗注意力机制并与特征提取模块C2f进行结合，增强模型对不同尺寸缺陷的特征提取能力。在开源数据集NEU-DET与GC10-DET上的实验结果表明，改进后的模型平均检测精度比原始YOLOv8算法精度分别高7.0和15.4个百分点，且相较于其他目标缺陷检测模型在平均检测精度方面具有优势，并进一步通过消融实验验证了每个模块的有效性。

关键词: 带钢表面缺陷检测, 深度学习, 上采样, 注意力机制, 激活函数

Abstract: Aiming at the problem of low accuracy of traditional defect detection algorithms in practical applications due to the small size of strip surface defects and blurry collected images in industrial scenarios, an LF-YOLO algorithm for strip surface defect detection in industrial scenarios is proposed. The model upsamples the input pixels by designing a local filling upsampling module to improve the recognition ability of blurred images, and reduce the missed detection rate of small target defects. The FReLU activation function that focuses on visual tasks is introduced to improve the accuracy of model location defects. In addition, a lightweight local attention mechanism is proposed and combined with the feature extraction module C2f to enhance the feature extraction capability of defects of different sizes during the feature extraction process of the model. Experimental results on the Northeastern University open source strip steel dataset NEU-DET and GC10-DET show that the average detection accuracy of the improved model is 7.0 and 15.4 percentage points higher than the accuracy of the original YOLOv8 algorithm, and is better than other classic target detection models. It has advantages in average detection accuracy, and the validity of each module is further verified through ablation experiments.

Key words: strip surface defect detection, deep learning, upsampling, attention mechanism, activation function

马肖瑶, 黎睿, 李自力, 翟文正. 面向工业场景带钢表面缺陷检测的LF-YOLO[J]. 计算机工程与应用, 2024, 60(18): 78-87.

MA Xiaoyao, LI Rui, LI Zili, ZHAI Wenzheng. LF-YOLO for Strip Surface Defect Detection in Industrial Scenes[J]. Computer Engineering and Applications, 2024, 60(18): 78-87.

参考文献

[1] 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.
[2] 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.
[3] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[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] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, October 11-14, 2016.[S.l.]: Springer International Publishing, 2016: 21-37.
[6] JIANG P, ERGU D, LIU F, et al. A review of Yolo algorithm developments[J]. Procedia Computer Science, 2022, 199: 1066-1073.
[7] XIE Y, HU W, XIE S, et al. Surface defect detection algorithm based on feature-enhanced YOLO[J]. Cognitive Computation, 2023, 15(2): 565-579.
[8] ZHAO C, SHU X, YAN X, et al. RDD-YOLO: a modified YOLO for detection of steel surface defects[J]. Measurement, 2023, 214: 112776.
[9] 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.
[10] KOU X, LIU S, CHENG K, et al. Development of a YOLO-V3 based model for detecting defects on steel strip surface[J]. Measurement, 2021, 182: 109454.
[11] QIAN X, WANG X, YANG S, et al. LFF-YOLO: a YOLO algorithm with lightweight feature fusion network for multi-scale defect detection[J]. IEEE Access, 2022, 10: 130339-130349.
[12] HUANG Y, TAN W, LI L, et al. WFRE-YOLOv8s: a new type of defect detector for steel surfaces[J]. Coatings, 2023, 13(12): 2011.
[13] ZHANG J, WEI X, ZHANG L, et al. YOLO v7-ECA-PConv-NWD detects defective insulators on transmission lines[J]. Electronics, 2023, 12(18): 3969.
[14] XIE W, SUN X, MA W. A light weight multi-scale feature fusion steel surface defect detection model based on YOLOv8[J]. Measurement Science and Technology, 2024, 35(5): 055017.
[15] 何湘杰, 宋晓宁. YOLOv4-Tiny的改进轻量级目标检测算法[J]. 计算机科学与探索, 2024, 18(1): 138-150.
HE X J, SONG X N. Improved YOLOv4-Tiny lightweight target detection algorithm[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(1): 138-150.
[16] 王春梅, 刘欢. YOLOv8-VSC：一种轻量级的带钢表面缺陷检测算法[J]. 计算机科学与探索, 2024, 18(1): 151-160.
WANG C M, LIU H. YOLOv8-VSC: lightweight algorithm for strip surface defect detection[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(1): 151-160.
[17] ZHOU J, ZHANG B, YUAN X, et al.YOLO-CIR: the network based on YOLO and ConvNeXt for infrared object detection[J].Infrared Physics and Technology, 2023, 131: 104703.
[18] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117-2125.
[19] LI H, XIONG P, AN J, et al. Pyramid attention network for semantic segmentation[J]. arXiv:1805.10180, 2018.
[20] GE Z, LIU S, WANG F, et al. Yolox: exceeding yolo series in 2021[J]. arXiv:2107.08430, 2021.
[21] ELFWING S, UCHIBE E, DOYA K. Sigmoid-weighted linear- units for neural network function approximation in reinforcement learning[J]. Neural Networks, 2018, 107: 3-11.
[22] RUKUNDO O, CAO H. Nearest neighbor value interpol-ation[J]. arXiv:1211.1768, 2012.
[23] KIRKLAND E J. Bilinear interpolation[C]//Advanced Computing in Electron Microscopy, 2010: 261-263.
[24] MCKINLEY S, LEVINE M. Cubic spline interpolation[J]. College of the Redwoods, 1998, 45(1): 1049-1060.
[25] GAO H, YUAN H, WANG Z, et al. Pixel transposed convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 42(5): 1218-1227.
[26] 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.
[27] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics,2011: 315-323.
[28] XU J, LI Z, DU B, et al. Reluplex made more practical: leaky ReLU[C]//Proceedings of the 2020 IEEE Symposium on Computers and Communications (ISCC), 2020: 1-7.
[29] CRNJANSKI J, KRSTI? M, TOTOVI? A, et al. Adaptive sigmoid-like and PReLU activation functions for all-optical perceptron[J]. Optics Letters, 2021, 46(9): 2003-2006.
[30] MA N, ZHANG X, SUN J. Funnel activation for visual recognition[C]//Proceedings of the 16th European Conference on Computer Vision(ECCV 2020), Glasgow, UK, August 23-28, 2020.[S.l.]: Springer International Publishing, 2020: 351-368.
[31] HU J, SHEN L, SUN G. Squeeze-and-excitation network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
[32] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 3-19.
[33] WANG Q, WU B, ZHU P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 11534-11542.
[34] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017.
[35] LI Z, WEI X, HASSABALLAH M, et al. A deep learning model for steel surface defect detection[J]. Complex & Intelligent Systems, 2023,10: 885-897.
[36] LV X, DUAN F, JIANG J, et al. Deep metallic surface defect detection: the new benchmark and detection network[J]. Sensors, 2020, 20(6): 1562.
[37] LIU J J, HOU Q, CHENG M M, et al. Improving convolutional networks with self-calibrated convolutions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 10096-10105.
[38] WANG C Y, YEH I H, LIAO H Y M. YOLOv9: learning what you want to learn using programmable gradient information[J]. arXiv:2402.13616, 2024.