基于YOLOv4-tiny-SR的涂层表面缺陷嵌入式检测方法

doi:10.3778/j.issn.1002-8331.2312-0180

摘要/Abstract

摘要： 提出一种涂层表面缺陷检测方法，解决涂层表面缺陷嵌入式检测过程中的检测精度低、速度慢以及对硬件配置要求高等难题。YOLOv4-tiny-SR中使用了新模型块DSRBlock，该模型块的局部结构能够在保证检测精度的同时大幅降低内存消耗并提升检测速度；提出几何平均聚类方法，将聚类中心的更新方式由算术平均转换为几何平均，以避免聚类中心向大目标框偏移；同时针对难检测样本，设计包围盒聚焦损失函数，以增大网络对其学习强度，改善检测效果。基于涂层表面缺陷实测数据的比对实验结果显示，该方法与其他方法相比在参数量、模型大小、检测速度及精度上均具有明显优势，其中与目前主流的YOLOv4-tiny相比，参数量降低51.82%，模型大小减小46%，速度提升39.47%，精度也提升了1.25个百分点。该方法检测速度更快、检测精度更高、内存消耗更小，在面向工业应用的嵌入式设备上实时检测表面缺陷实用价值高，可向相关领域推广应用。

关键词: 涂层表面缺陷, YOLOv4-tiny-SR, 几何平均聚类, 包围盒聚焦损失

Abstract: A detection method for coating surface defects is proposed to solve the problems of low detection accuracy, slow speed and high requirements for hardware configuration in the process of coating surface defect embedded detection. The YOLOv4-tiny-SR uses a new model block DSRBlock. The local structure of the model block can greatly reduce memory consumption and increase detection speed while ensuring detection accuracy. A geometric average clustering method is proposed, which converts the update method of cluster centers from arithmetic average to geometric average to avoid the deviation of cluster centers to the large target frame. At the same time, for difficult-to-detect samples, a hard sample loss function is designed to increase the learning intensity of the network and improve the detection effect. The comparison experiment results based on the measured data of coating surface defects show that the method in this paper has obvious advantages compared with other methods in terms of parameter quantity, model size, detection speed and accuracy. Compared with the current mainstream YOLOv4-tiny, the parameter amount is reduced by 51.82%, the model size is reduced by 46%, the speed is increased by 39.47%, and the accuracy is also increased by 1.25?percentage points. The method in this paper has faster detection speed, higher detection accuracy, and less memory consumption, it has high practical value for real-time detection of surface defects on embedded devices for industrial applications, and can be popularized and applied to related fields.

Key words: coating surface defects, YOLOv4-tiny-SR, geometric mean clustering, hard sample loss function

赵辉, 侯旭涛, 宋龙, 徐可, 沙建军, 陈宗阳. 基于YOLOv4-tiny-SR的涂层表面缺陷嵌入式检测方法[J]. 计算机工程与应用, 2025, 61(8): 239-249.

ZHAO Hui, HOU Xutao, SONG Long, XU Ke, SHA Jianjun, CHEN Zongyang. Embedded Detection Method of Coating Surface Defects Based on YOLOv4-tiny-SR[J]. Computer Engineering and Applications, 2025, 61(8): 239-249.

参考文献

[1] 张金玉, 马永超. 基于锁相法的涂层缺陷检测识别的仿真研究[J]. 激光与红外, 2017, 47(3): 313-318.
ZHANG J Y, MA Y C. Simulation on detection and recognition of coating defect based on lock-in thermography[J]. Laser & Infrared, 2017, 47(3): 313-318.
[2] 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.
[3] 刘卫光, 刘东, 王璐. 可变形卷积网络研究综述[J]. 计算机科学与探索, 2023, 17(7): 1549-1564.
LIU W G, LIU D, WANG L. Survey of deformable convolutional networks[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(7): 1549-1564.
[4] LOWE D G. Object recognition from local scale-invariant features[C]//Proceedings of the 17th IEEE International Conference on Computer Vision, 1999: 1150-1157.
[5] 赵珊, 郑爱玲, 刘子路, 等. 通道分离双注意力机制的目标检测算法[J]. 计算机科学与探索, 2023, 17(5): 1112-1125.
ZHAO S, ZHENG A L, LIU Z L, et al. Object detection algorithm based on channel separation dual attention mechanism[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(5): 1112-1125.
[6] 赵振兵, 王帆帆, 刘良帅, 等. 基于注意力特征融合YOLOv5模型的无人机输电线路航拍图像金具检测方法[J]. 电测与仪表, 2023, 60(3): 145-152.
ZHAO Z B, WANG F F, LIU L S, et al. Hardware detection method of aerial image of UAV transmission line based on attention feature fusion YOLOv5 model[J]. Electrical Measurement & Instumentation, 2023, 60(3): 145-152.
[7] 于璐, 朱海红, 李思宇, 等. 基于图像自适应增强与特征融合的目标检测方法[J]. 测绘工程, 2024, 33(1): 32-40.
YU L, ZHU H H, LI S Y et al. Object detection method based on image adaptive enhancement and feature fusion[J]. Engineering of Surveying and Mapping, 2024, 33(1): 32-40.
[8] GUO C W, ZHANG Z W. The design on surface defects detection system of cylindrical diode based on decision tree learning[J]. Microcomputer & Its Applications, 2015, 119: 1933-1949.
[9] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005: 886-893.
[10] OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.
[11] LIAN J, JIA W K, ZAREAPOOR M, et al. Deep-learning-based small surface defect detection via an exaggerated local variation-based generative adversarial network[J]. IEEE Transactions on Industrial Informatics, 2019, 16(2): 1343-1351.
[12] TAO X, WANG Z H, ZHANG Z T, et al. Wire defect recognition of spring-wire socket using multitask convolutional neural networks[J]. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2018, 8(4): 689-698.
[13] LIU B, ZHANG X Y, GAO Z Y, et al. Weld defect images classification with VGG16-Based neural network[C]//Proceedings of the International Forum on Digital TV and Wireless Multimedia Communications, 2017: 215-223.
[14] HU B, WANG J. Detection of PCB surface defects with improved faster-RCNN and feature pyramid network[J]. IEEE Access, 2020, 8: 108335-108345.
[15] TABERNIK D, ?ELA S, SKVARC J, et al. Segmentation-based deep-learning approach for surface-defect detection[J]. Journal of Intelligent Manufacturing, 2020, 31(3): 759-776.
[16] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv: 2004.10934, 2020.
[17] LIN T Y, DOLLAR 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.
[18] LYRA S, MAYER L, OU L, et al. A deep learning-based camera approach for vital sign monitoring using thermography images for ICU patients[J]. Sensors, 2021, 21(4): 1495.
[19] AYOUB N, SCHNEIDER-KAMP P. Real-time on-board deep learning fault detection for autonomous UAV inspections[J]. Electronics, 2021, 10(9): 1091.
[20] JIANG Z, ZHAO L, LI S, et al. Real-time object detection method based on improved YOLOv4-tiny[J]. arXiv:2011. 04244, 2020.
[21] LI F, LIU Z, SHEN W, et al. A remote sensing and airborne edge-computing based detection system for pine wilt disease[J]. IEEE Access, 2021, 9: 66346-66360.
[22] HUI T, XU Y L, JARHINBEK R. Detail texture detection based on YOLOv4‐tiny combined with attention mechanism and bicubic interpolation[J]. IET Image Processing, 2021, 15(8): 12228.
[23] LI Z, LI J, DAI W. A two-stage multiscale residual attention network for light guide plate defect detection[J]. IEEE Access, 2020, 9: 2780-2792.
[24] 陈宗阳. 面向工业应用的涂层缺陷视觉检测技术研究[D]. 哈尔滨: 哈尔滨工程大学, 2022.
CHEN Z Y. Research on visual inspection technology of coating defects for industrial applications[D]. Harbin: Harbin Engineering University, 2022.
[25] 陈宗阳, 赵辉, 吕永胜, 等. 基于改进MobileNetV2网络的涂层表面缺陷识别方法[J]. 哈尔滨工程大学学报, 2022, 43(4): 572-579.
CHEN Z Y, ZHAO H, LYU Y S, et al. A recognition method of coating surface defects based on the improved MobileNetV2 network[J]. Journal of Harbin Engineering University, 2022, 43(4): 572-579.
[26] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
[27] 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.
[28] KINGMA D P, BA J. Adam: a method for stochastic optimization[J]. arXiv:1412.6980, 2014.