基于轻量化YOLO网络的实时X射线焊缝缺陷检测Real-time X-ray Weld Defect Detection Based on Lightweight YOLO Network
龙凌,陈浩,梁昊,赵爽,刘钊,李兆彤
摘要(Abstract)：
X射线无损检测是进行焊缝焊接质量检查的重要方法，为了提高射线评片效率和准确率，本文提出了基于轻量化YOLO网络的实时X射线焊缝缺陷检测方法。首先，在分析焊缝射线检测图像特征的基础上，为提升焊缝图像缺陷检测精度与速度，设计了级联缺陷检测模型，先使用经过轻量化设计的焊缝定位网络定位缺陷集中分布的焊缝区域，再使用滑窗裁剪操作，将切割的小图输入到缺陷检测网络中进行精准的缺陷检测。然后，为了应对缺陷样本过少导致的网络过拟合问题，本文提出了基于负样本正常图像的Copy-Pasting数据增强策略，提升了缺陷检测精度。实验结果表明，本文提出的方法能够有效降低网络模型大小，同时mAP0.5达到99.5%,精确率99.8%,召回率99.6%,检测速度在20 frame/s至33 frame/s,能够满足实时辅助评片的要求。
关键词(KeyWords)： 焊缝缺陷检测;YOLO网络;轻量化模型;数据增强;深度学习
基金项目(Foundation):
作者(Author): 龙凌,陈浩,梁昊,赵爽,刘钊,李兆彤
DOI: 10.20064/j.cnki.2095-347X.2023.02.004
参考文献(References)：
- [1] 全国锅炉压力容器标准化技术委员会(SAC/TC 262).承压设备无损检测射线胶片数字化系统的鉴定方法：GB/T 28266-2012[S].北京：中国标准出版社，2012.
- [2] Li Y P,Gao W X.Research on X-ray welding image defect detection based on convolution neural network[J].Journal of Physics:Conference Series.2019,1237(3).
- [3] Zhang H D,et al.Weld defect detection based on deep learning method [C]//2019 IEEE 15th international conference on automation science and engineering (CASE).IEEE,2019:1574-1579.
- [4] 常海涛，苟军年，李晓梅.Faster R-CNN在工业CT图像缺陷检测中的应用[J].中国图象图形学报，2018,23(7):1061-1071.
- [5] 叶欣.基于深度学习的热轧带钢表面缺陷检测算法研究[D].武汉：武汉科技大学，2021.
- [6] 王浩然，李廷会，曹玉军等.改进YOLOv5s网络在缺陷检测中的应用[J].网络新媒体技术，2022,11(2):58-65.
- [7] Bochkovskiy A,Wang C Y,Liao H Y M.Yolov4:Optimal speed and accuracy of object detection[EB/OL].arXiv preprint arXiv:2004.10934.(2020-04-23).https://arxiv.org/abs/2004.10934.
- [8] 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.
- [9] Liu S,Qi L,Qin H,et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2018:8759-8768.
- [10] 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.2020,34(7):12993-13000.
- [11] 王军，冯孙铖，程勇.深度学习的轻量化神经网络结构研究综述[J].计算机工程，2021,47(8):1-13.
- [12] Howard A G,Zhu M,Chen B,et al.Mobilenets:Efficient convolutional neural networks for mobile vision applications[EB/OL].arXiv preprint arXiv:1704.04861.(2017-04-17).https://arxiv.org/abs/1704.04861.
- [13] Szegedy C,Liu W,Jia Y,et al.Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2015:1-9.
- [14] Han K,Wang Y,Tian Q,et al.Ghostnet:More features from cheap operations[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.2020:1580-1589.
- [15] Zhang X,Zhou X,Lin M,et al.Shufflenet:An extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2018:6848-6856.
- [16] Van Etten A.You only look twice:Rapid multi-scale object detection in satellite imagery[EB/OL].arXiv preprint arXiv:1805.09512.(2018-05-24).https://arxiv.org/abs/1805.09512.
- [17] Lin T Y,Goyal P,Girshick R,et al.Focal loss for dense object detection[C]//Proceedings of the IEEE international conference on computer vision.2017:2980-2988.
- [18] Kisantal M,Wojna Z,Murawski J,et al.Augmentation for small object detection[EB/OL].arXiv preprint arXiv:1902.07296.(2019-02-19).https://arxiv.org/abs/1902.07296.