改进YOLOv5n的管道DR缺陷图像检测方法

doi:10.3778/j.issn.1002-8331.2304-0397

摘要/Abstract

摘要： 近年来，数字射线成像技术(digital radiography, DR)由于其独有优势已被广泛应用于工业管道无损检测。为提高管道DR缺陷图像检测精度，提出了一种改进的YOLOv5n管道DR缺陷图像检测方法。该方法有两点贡献，针对目标检测网络中分类和回归两个任务存在冲突的问题，设计了任务独立解耦检测头，通过分别为两类任务构建独立的特征图实现解耦。为了缓解解耦检测头模块带来的参数量增加问题，引入了轻量化的深度可分离卷积替代标准卷积，在保证精度的同时，减少模型参数量。实验结果表明，在管道缺陷数据集上，该方法的mAP@0.5比YOLOv5n提高0.9个百分点。与YOLOv4、Faster-RCNN和SSD等其他几种目标检测模型的对比实验表明，该方法在mAP@0.5、参数量和计算量上都达到最优，有效提高了管道DR缺陷图像检测的性能。

关键词: 缺陷图像检测, 目标检测, 解耦检测头, 轻量化模型

Abstract: In recent years, digital radiography (DR) technology has been widely used for industrial pipelines defect detection due to its unique advantages. To improve the accuracy of pipeline DR defect image detection, an improved YOLOv5n is proposed. This method has two contributions. Firstly, to address the issue of conflicts between classification and regression tasks in target detection networks, a task independent decoupling detection head is designed, and decoupling is achieved by constructing independent feature maps for each type of task. Secondly, in order to alleviate the increase of parameters caused by the decoupling detection head module, a lightweight deep separable convolution is introduced to replace the standard convolution, which can effectively reduce the number of parameters while ensuring accuracy. The experimental results indicate that on the pipeline defect dataset, the mAP@0.5 of the proposed method is 0.9 percentage points higher than YOLOv5n. Comparative experiments with other object detection models such as YOLOv4, Faster-RCNN, and SSD show that the proposed method achieves superior performance in mAP@0.5, parameter quantity and computational complexity.

Key words: defect image detection, target detection, decoupling detection head, lightweight model

时亚南, 陈志远, 刘兆英, 陈迎春, 张婷, 范效礼, 苗锐, 叶伟. 改进YOLOv5n的管道DR缺陷图像检测方法[J]. 计算机工程与应用, 2024, 60(12): 366-372.

SHI Yanan, CHEN Zhiyuan, LIU Zhaoying, CHEN Yingchun, ZHANG Ting, FAN Xiaoli, MIAO Rui, YE Wei. Improved YOLOv5n Pipeline DR Defect Image Detection Method[J]. Computer Engineering and Applications, 2024, 60(12): 366-372.

参考文献

[1] 杨艳艳, 李雷孝, 林浩. 提取驾驶员面部特征的疲劳驾驶检测研究综述[J]. 计算机科学与探索, 2023, 17(6): 1249-1267.
YANG Y Y, LI L X, LIN H. Review of research on fatigue driving detection based on driver facial features[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(6): 1249-1267.
[2] 贾天豪, 彭力, 戴菲菲. 引入残差学习与多尺度特征增强的目标检测器[J]. 计算机科学与探索, 2023, 17(5): 1102-1111.
JIA T H, PENG L,DAI F F. Object detector with residual learning and multi-scale feature enhancement[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(5): 1102-1111.
[3] 曹阳, 曹存根, 资康莉, 等. 基于BiLSTM-CRF的中文分组单字错误识别方法研究[J]. 中文信息学报, 2023, 37(4): 156-165.
CAO Y, CAO C G, ZI K L, et al. Chinese typos recognitionby character grouping and BiLSTM-CRF[J]. Journal of Chinese Information Processing, 2023, 37(4): 156-165.
[4] REN S Q, HE K M,GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[5] HE K, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//IEEE International Conference on Computer Vision, 2017: 2961-2969.
[6] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Computer Vision & Pattern Recognition, 2016.
[7] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
[8] REDMON J, FARHADI A. Yolov3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[9] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[10] LI C, LI L, JIANG H, et al. YOLOv6: a single-stage object detection framework for industrial applications[J]. arXiv:2209.02976, 2022.
[11] 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[J]. arXiv:2207.02696, 2022.
[12] GE Z, LIU S, WANG F, et al. Yolox: exceeding yolo series in 2021[J]. arXiv:2107.08430, 2021.
[13] WANG C Y, YEH I H, LIAO H Y M. You only learn one representation: unified network for multiple tasks[J]. arXiv:2105.04206, 2021.
[14] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision (ECCV 2016), Msterdam, The Netherlands, October 11-14, 2016. [S.l.]: Springer International Publishing, 2016: 21-37.
[15] 程婧怡, 段先华, 朱伟. 改进YOLOv3的金属表面缺陷检测研究[J]. 计算机工程与应用, 2021, 57(19): 252-258.
CHEN J Y, DUAN X H, ZHU W. Research on metal surface defect detection by improved YOLOv3[J]. Computer Engineering and Applications, 2021, 57(19): 252-258.
[16] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318-327.
[17] SHEN D, LIU X, SHANG Y, et al. Deep learning-based automatic defect detection method for sewer pipelines[J]. Sustainability, 2023, 15(12): 9164.
[18] ZHAO H Q, ZHANG T S. Fabric surface defect detection using SE-SSDNet[J]. Symmetry,2022,14(11):2373.
[19] SHARMA M, LIM J, LEE H. The amalgamation of the object detection and semantic segmentation for steel surface defect detection[J]. Applied Sciences, 2022, 12(12): 6004.
[20] GUO Z X, WANG C S, YANG G, et al. MSFT-YOLO: improved YOLOv5 based on transformer for detecting defects of steel surface[J]. Sensors, 2022, 22(9): 3467.
[21] WU Y, CHEN Y, YUAN L, et al. Rethinking classification and localization for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 10186-10195.
[22] SONG G, LIU Y, WANG X. Revisiting the sibling head in object detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 11563-11572.
[23] ZHUANG J, QIN Z, YU H, et al. Task-specific context decoupling for object detection[J]. arXiv:2303.01047, 2023.
[24] ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//AAAI Conference on Artificial Intelligence, 2020: 12993-13000.