基于改进YOLOv3算法的带钢表面缺陷检测

doi:10.3969/j.issn.0372-2112.2020.07.006

电子学报 ›› 2020, Vol. 48 ›› Issue (7): 1284-1292.DOI: 10.3969/j.issn.0372-2112.2020.07.006

所属专题：机器学习之图像处理；优秀论文(2022)

基于改进YOLOv3算法的带钢表面缺陷检测

李维刚^1,2, 叶欣¹, 赵云涛¹, 王文波³

1. 武汉科技大学冶金自动化与检测技术教育部工程研究中心, 湖北武汉 430081;
2. 武汉科技大学高温材料与炉衬技术国家地方联合工程研究中心, 湖北武汉 430081;
3. 武汉科技大学理学院, 湖北武汉 430081

收稿日期:2019-07-29 修回日期:2019-12-05 出版日期:2020-07-25
- 作者简介:
- 李维刚 男,1977年出生于湖北通城.博士,武汉科技大学信息科学与工程学院教授、博导,主要研究方向:冶金过程控制、人工智能和深度学习新方法.E-mail:liweigang.luck@foxmail.com;叶欣男,1997年出生于湖北宜昌.武汉科技大学信息科学与工程学院硕士研究生,主要研究方向:工业过程建模与仿真、深度学习;赵云涛 男,1982年出生于内蒙古赤峰.博士,武汉科技大学信息科学与工程学院副教授,主要研究方向:计算机仿真;王文波 男,1978年出生于湖北襄阳.博士,武汉科技大学信息与计算科学系教授,主要研究方向为多尺度分析与电力系统信号处理、深度学习.
- 基金资助:
- 国家自然科学基金 (No.51774219）

Strip Steel Surface Defect Detection Based on Improved YOLOv3 Algorithm

LI Wei-gang^1,2, YE Xin¹, ZHAO Yun-tao¹, WANG Wen-bo³

1. Engineering Research Center for Metallurgical Automation and Technology of Ministry of Education, Wuhan University of Science and Technology, Wuhan, Hubei 430081, China;
2. National-Provincial Joint Engineering Research Center of High Temperature Materials and Lining Technology, Wuhan University of Science and Technology, Wuhan, Hubei 430081, China;
3. College of Science, Wuhan University of Science and Technology Wuhan, Hubei 430081, China

Received:2019-07-29 Revised:2019-12-05 Online:2020-07-25 Published:2020-07-25

摘要/Abstract

摘要： 针对热轧带钢表面缺陷检测中存在的检测速度慢、检测精度低等问题，提出了一种改进的YOLOv3算法模型.使用加权K-means聚类算法来优化确定先验框参数，提高先验框（priors anchor）与特征图层（feature map）的匹配度；同时，调整YOLOv3算法的网络结构，融合浅层特征与深层特征，形成新的大尺度检测图层，提高网络对带钢表面缺陷的检测精度.实验结果表明，改进后的YOLOv3算法在NEU-DET数据集上平均精度均值达到了80%，较原有的YOLOv3算法提高了11%；同时检测速度保持在50fps，优于目前其它深度学习带钢表面缺陷检测算法.

关键词: 目标检测, 带钢表面缺陷, YOLOv3, 加权K-means

Abstract: To solve the problem of slow speed and low accuracy in the surface defect detection of hot rolled strips,an improved YOLOv3 algorithm is proposed.Firstly,the weighting K-means clustering algorithm is put forward to optimize priors anchor's parameters,which can improve the match between priors anchor and feature map.Secondly,the improved network structure of the YOLOv3 algorithm is proposed to improve the detection accuracy,whose shallow features and deep features are combined to form the new large-scale inspection layer.The experiments are carried out on the NEU-DET dataset,the results show that the average accuracy of the improved YOLOv3 algorithm is 80%,which is 11% higher than that of the original algorithm;the detection speed is 50fps,which is faster than other strip surface defect detection algorithms based on deep learning.

Key words: object detection, strip steel surface defect, YOLOv3, weighting K-means

中图分类号:

TP391.41

李维刚, 叶欣, 赵云涛, 王文波. 基于改进YOLOv3算法的带钢表面缺陷检测[J]. 电子学报, 2020, 48(7): 1284-1292.

LI Wei-gang, YE Xin, ZHAO Yun-tao, WANG Wen-bo. Strip Steel Surface Defect Detection Based on Improved YOLOv3 Algorithm[J]. Acta Electronica Sinica, 2020, 48(7): 1284-1292.

参考文献

[1] 屈尔庆,崔月姣,徐森,等.改进的Gabor滤波器带钢表面缺陷显著性检测[J].华中科技大学学报(自然科学版),2017,45(10):12-17. QU Er-qing,CUI Yue-jiao,XU Sen.Saliency defect detection in strip steel by improved Gabor filter[J].Hua zhong Univ of Sci & Tech (Natural Science Edition),2017,45(10):12-17.(in Chinese)
[2] 任海鹏,马展峰.基于复杂网络特性的带钢表面缺陷识别[J].自动化学报,2011,37(11):1407-1412. REN Hai-Peng,MA Zhan-Feng.Strip steel surface defect recognition based on complex network characteristics[J].Acta Automatica Sinica,2011,37(11):1407-1412.(in Chinese)
[3] ZHU S G,DU J P,REN N.A novel simple visual tracking algorithm based on hashing and deep learning[J].Chinese Journal of Electronics,2017,26(05):1073-1078.
[4] XU K,XU Y,ZHOU P,et al.Application of RNAMlet to surface defect identification of steels[J].Optics and Lasers in Engineering,2018,105(06):110-117.
[5] SONG K C,YAN Y H.A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects[J].Applied Surface Science,2013,285(part_PB):858-864.
[6] HE D,XU K,ZHOU P.Defect detection of hot rolled steels with a new object detection framework called classification priority network[J].Computers & Industrial Engineering,2019,128(03):290-297.
[7] FU G Z,SUN P Z,ZHU W B,et al.A deep-learning-based approach for fast and robust steel surface defects classification[J].Optics and Lasers in Engineering,2019,121(10):397-405.
[8] HE Y,SONG K C,MENG Q G,et al.Semi-supervised defect classification of steel surface based on multi-training and generative adversarial network[J].Optics and Lasers in Engineering,2019,122(11):294-302.
[9] HE D,XU K,ZHOU P,et al.Surface defect classification of steels with a new semi-supervised learning method[J].Optics and Lasers in Engineering,2019,117(06):40-48.
[10] HE Y,SONG K C,MENG Q G,et al.An end-to-end steel surface defect detection approach via fusing multiple hierarchical features[J].IEEE Transactions on Instrumentation and Measurement,2019,PP(99):1-1.
[11] 姜维,张重生,殷绪成.基于深度学习的场景文字检测综述[J].电子学报,2019,47(5):1152-1161. JIANG Wei,ZHANG Chong-sheng,YIN Xu-cheng.Deep learning based scene text detection:A survey[J].Acta Electronica Sinica,2019,47(5):1152-1161.(in Chinese)
[12] 张慧,王坤峰,王飞跃.深度学习在目标视觉检测中的应用进展与展望.自动化学报,2017,43(08):1289-1305. ZHANG Hui,WANG Kun-Feng,WANG Fei-Yue.Advances and perspectives on applications of deep learning in visual object detection[J].Acta Automatica Sinica,2017,43(08):1289-1305.(in Chinese)
[13] 罗会兰,童康,孔繁胜.基于深度学习的视频中人体动作识别进展综述[J].电子学报,2019,47(5):1162-1173. LUO Hui-lan,TONG Kang,KONG Fan-sheng.The progress of human action recognition in videos based on deep learning:A review[J].Acta Electronica Sinica,2019,47(5):1162-1173.(in Chinese)
[14] REN S Q,HE K M,GIRSHICK R B,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.
[15] HE K M,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[A].Proceedings of the IEEE International Conference on Computer Vision[C].Venice:IEEE Press,2017.2961-2969.
[16] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[A].Computer Vision and Pattern Recognition[C].USA:IEEE,2016.779-788.
[17] REDMON J,FARHADI A.YOLO9000:better,faster,stronger[A].Computer Vision and Pattern Recognition[C].USA:IEEE,2017.6517-6525.
[18] REDMON J,FARHADI A.YOLOv3:An incremental improvement[A].Computer Vision and Pattern Recognition[C].arXiv Preprint,2018,arXiv:1804.02767.
[19] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multibox detector[A].Proceedings of the IEEE European Conference on Computer Vision[C].Amsterdam,The Netherlands:IEEE,2016.21-37.
[20] 石杰,周亚丽,张奇志.基于改进Mask RCNN和Kinect的服务机器人物品识别系统[J].仪器仪表学报,2019,40(04):216-228. SHI Jie,ZHOU Ya-li,ZHANG Qi-zhi.Service robot item recognition system based on improved mask RCNN and kinect[J].Chinese Journal of Scientific Instrument,2019,40(04):216-228.(in Chinese)
[21] 裴伟,许晏铭,朱永英,等.改进的SSD航拍目标检测方法[J].软件学报,2019,30(03):738-758. PEI Wei,XU Yan-Ming,ZHU Yong-Ying,et al.The target detection method of aerial photography images with improved SSD[J].Journal of Software,2019,30(03):738-758.(in Chinese)
[22] 黄继鹏,史颖欢,高阳.面向小目标的多尺度Faster-RCNN检测算法[J].计算机研究与发展,2019,56(02):319-327. HUANG Ji-peng,SHI Ying-huan,GAO Yang.Multi-scale faster-RCNN algorithm for small object detection[J].Journal of Computer Research and Development,2019,56(02):319-327.(in Chinese)
[23] 王俊强,李建胜,周学文,等.改进的SSD算法及其对遥感影像小目标检测性能的分析[J].光学学报,2019,39(06):373-382. Wang Jun-qiang,Li Jian-sheng,Zhou Xuewen,et al.Improved SSD algorithm and its performance analysis of small target detection in remote sensing images[J].Acta Optica Sinica,2019,39(06):373-382.(in Chinese)
[24] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[A].Computer Vision and Pattern Recognition[C].USA:IEEE,2016.770-778.

基于改进YOLOv3算法的带钢表面缺陷检测

Strip Steel Surface Defect Detection Based on Improved YOLOv3 Algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	琚长瑞, 秦晓燕, 袁广林, 李豪, 朱虹. 尺度敏感损失与特征融合的快速小目标检测方法[J]. 电子学报, 2022, 50(9): 2119-2126.
[2]	李超, 黄新宇, 王凯. 基于特征融合和自学习锚框的高分辨率图像小目标检测算法[J]. 电子学报, 2022, 50(7): 1684-1695.
[3]	包中华, 卢建斌, 田永华, 田树森. 密集杂波背景下雷达微弱海面目标的修正Hough变换TBD检测新方法[J]. 电子学报, 2022, 50(7): 1735-1743.
[4]	肖进胜, 张舒豪, 陈云华, 王元方, 杨力衡. 双向特征融合与特征选择的遥感影像目标检测[J]. 电子学报, 2022, 50(2): 267-272.
[5]	李斌, 齐延荣, 周清雷. 基于Winograd算法的目标检测加速器设计与优化[J]. 电子学报, 2022, 50(10): 2387-2397.
[6]	罗会兰, 袁璞, 童康. 基于深度学习的显著性目标检测方法综述[J]. 电子学报, 2021, 49(7): 1417-1427.
[7]	程旭, 宋晨, 史金钢, 周琳, 张毅锋, 郑钰辉. 基于深度学习的通用目标检测研究综述[J]. 电子学报, 2021, 49(7): 1428-1438.
[8]	周勇, 陈思霖, 赵佳琦, 张迪, 王瀚正. 基于弱语义注意力的遥感图像可解释目标检测[J]. 电子学报, 2021, 49(4): 679-689.
[9]	王洪雁, 张海坤, 罗宇华, 汪祖民. 复杂动态背景下基于群稀疏的运动目标检测方法[J]. 电子学报, 2021, 49(12): 2330-2338.
[10]	罗大鹏, 杜国庆, 曾志鹏, 魏龙生, 高常鑫, 陈应, 肖菲, 罗琛. 基于少量样本学习的多目标检测跟踪方法[J]. 电子学报, 2021, 49(1): 183-191.
[11]	罗会兰, 陈鸿坤. 基于深度学习的目标检测研究综述[J]. 电子学报, 2020, 48(6): 1230-1239.
[12]	刘颖, 刘红燕, 范九伦, 公衍超, 李莹华, 王富平, 卢津. 基于深度学习的小目标检测研究与应用综述[J]. 电子学报, 2020, 48(3): 590-601.
[13]	孟祥伟. 量化秩非参数CFAR检测器在杂波边缘中的性能分析[J]. 电子学报, 2020, 48(2): 384-389.
[14]	权宇, 李志欣, 张灿龙, 马慧芳. 融合深度扩张网络和轻量化网络的目标检测模型[J]. 电子学报, 2020, 48(2): 390-397.
[15]	侯庆山, 邢进生. 基于Grad-CAM与KL损失的SSD目标检测算法[J]. 电子学报, 2020, 48(12): 2409-2416.