基于多源迁移学习的大坝裂缝检测

计算机科学 ›› 2022, Vol. 49 ›› Issue (6A): 319-324.doi: 10.11896/jsjkx.210500124

• 图像处理&多媒体技术 • 上一篇下一篇

基于多源迁移学习的大坝裂缝检测

王君锋^1,2, 刘凡^1,2, 杨赛³, 吕坦悦^1,2, 陈峙宇^1,2, 许峰²

1 河海大学海岸灾害与防护教育部重点实验室南京 210098
2 河海大学计算机信息学院南京 210098
3 南通大学电气工程学院江苏南通 226019

出版日期:2022-06-10 发布日期:2022-06-08
通讯作者: 刘凡(fanliu@hhu.edu.cn)
作者简介:(2077918179@qq.com)
基金资助:
江苏省自然科学基金(BK20191298);河海大学海岸灾害及保护教育部重点实验室开发基金(20150009);中央高校基本科研业务费(B200202175)

Dam Crack Detection Based on Multi-source Transfer Learning

WANG Jun-feng^1,2, LIU Fan^1,2, YANG Sai³, LYU Tan-yue^1,2, CHEN Zhi-yu^1,2, XU Feng²

1 Key Laboratory of Ministry of Education for Coastal Disaster and Protection,Hohai University,Nanjing 210098,China
2 College of Computer Information,Hohai University,Nanjing 210098,China
3 School of Electrical Engineering,Nantong University,Nantong,Jiangsu 226019,China

Online:2022-06-10 Published:2022-06-08
About author:WANG Jun-feng,born in 1996,postgraduate,is a member of China Computer Federation.His main research interests include object detection and semantic segmentation.
LIU Fan,born in 1988,Ph.D,professor,is a member of China Computer Federation.His main research interests include pattern recognition and computer vision.
Supported by:
Natural Science Foundation of Jiangsu Province(BK20191298),Development Fund of Key Laboratory of Coastal Disaster and Protection of Ministry of Euducation,Hohai University(20150009) and Fundamental Research Funds for the Central Universities(B200202175).

摘要/Abstract

摘要： 针对现有深度学习方法在进行大坝裂缝检测时出现模型过拟合、计算效率低下等问题,文中提出了一种基于多源迁移学习的大坝裂缝检测方法,旨在提高算法准确率的同时,减少模型计算量,加快检测速度。所提方法首先将MobileNet网络和SSD目标检测算法相结合,形成MobileNet-SSD网络,有效减少了模型参数量并减少了计算复杂度;然后利用道路裂缝、墙壁裂缝和桥梁裂缝等多源数据进行训练,并应用迁移学习的思想,将学习到的知识分别迁移到大坝裂缝的检测模型中,以提升模型检测的精确度;最后提出了一种多模型融合方法,将通过迁移学习得到的多个检测结果进行融合,进一步提升了检测结果的重合度。

关键词: 大坝裂缝检测, 模型融合, 迁移学习, 深度学习

Abstract: The existing deep models will encounter overfitting and low computational efficiency when they are directly used for dam crack detection.This paper proposes a new dam crack detection algorithm based on multi-source transfer learning,which aims to improve the accuracy,reduce the model calculation and speed up the detection speed.Firstly,this method combines MobileNet with SSD object detection algorithm to construct a MobileNet-SSD network,which effectively reduces model parameters and computational complexity.Then,the proposed deep network is trained by using multi-source data sets such as road cracks,wall cracks and bridge cracks.Based on the transfer learning idea,the learned knowledge is transferred to the target domain model of dam crack to further improve the detection accuracy.Finally,a multi-model fusion method is proposed to integrate the detection results of different models obtained through transfer learning,which can effectively enhance the location of output boxes.

Key words: Dam crack detection, Deep learning, Model fusion, Transfer learning

中图分类号:

TP391

王君锋, 刘凡, 杨赛, 吕坦悦, 陈峙宇, 许峰. 基于多源迁移学习的大坝裂缝检测[J]. 计算机科学, 2022, 49(6A): 319-324. https://doi.org/10.11896/jsjkx.210500124

WANG Jun-feng, LIU Fan, YANG Sai, LYU Tan-yue, CHEN Zhi-yu, XU Feng. Dam Crack Detection Based on Multi-source Transfer Learning[J]. Computer Science, 2022, 49(6A): 319-324. https://doi.org/10.11896/jsjkx.210500124

参考文献

[1] DONG L B.Analysis and study on the influencing factors of dam safety [D].Nanjing:Hohai University,2008.
[2] YU J Y,DING P C,WANG C.Overview:Application of Convolution Neural Network in Object Detection[J].Computer Science,2018,45(S2):17-26.
[3] LIENHART R,MAYDT J.An extended set of Haar-like fea-tures for rapid object detection[C]//International Conference on Image Processing.New York:IEEE Press,2002:900-903.
[4] VIOLA P,JONES M.Rapid Object Detection using Cascade of Simple Features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR).New York:IEEE Press,2003:511-518.
[5] FELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,32(9):1627-1645.
[6] LI Z W,LIU F,YANG W J,et al.A Survey of ConvolutionalNeural Networks:Analysis,Applications,and Prospects[J].IEEE Transactions on Neural Networks and Learning Systems,2021,2021(99):1-21.
[7] GIRSHICK R,DONAHUE J,DARRELI T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE Press,2014:580-587.
[8] KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNetClassification with Deep Convolutional Neural Networks[J].Communications of the ACM,2017,60(6):84-90.
[9] GIRSHICK R.Fast R-CNN[C]//IEEE International Confe-rence on Computer Vision(ICCV).New York:IEEE Press,2015:1440-1448.
[10] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence.New York:IEEE Press,2017,39(6):1137-1149.
[11] REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]//IEEE Confe-rence on Computer Vision and Pattern Recognition(CVPR).New York:IEEE Press,2016:779-788.
[12] LIU W,ANUUELOV D,ERHAN D,et al.SSD:Single ShotMultiBox Detector[C]//Computer Vision-14th European Conference(ECCV 2016).New York:IEEE Press,2016,9905:21-37.
[13] CHEN W,FAN X N,LI M,et al.Dam Crack Detection of Artificial Colony Algorithm Based on Gabor Operator[J].Microprocessors,2015,36(4):32-38.
[14] ZHANG D W,XU M Z,MA L,et al.Research on image segmentation method of underwater dam cracks[J].Software Guide,2016,15(9):170-172.
[15] XU H,HE J J,FANG L.Dam Crack Detection Based on Image Saliency[J].Industrial Control Computer,2018,31(9):19-20,23.
[16] VALENCA J,JULIO E.MCrack-Dam:the scale-up of a method to assess cracks on concrete dams by image processing.The case study of Itaipu Dam,at the Brazil-Paraguay border[J].Journal of Civil Structural Health Monitoring,2018,2018(8):857-866.
[17] FAN X N,WU J J,SHI P F,et al.A Novel Underwater Dam Crack Extraction Algorithm Based on Lorentz Information Measure[J].Computer and Modernization,2018(3):73-77.
[18] JIANG X Y,ZAHNG S,HE S Y.Dam crack detection based on lattice Boltzmann model[J].Science & Technology View,2018,233(11):98-99.
[19] MAO Y C,QI H,CHEN H,et al.A comprehensive evaluation method for dam safety based on deep learning:China,201710598587[P].2017-4.
[20] MAO Y G,WANG J,CHEN X L,et al.Dam Defect Recognition and Classification Based on Feature Combination and CNN[J].Computer Science,2019,46(3):273-280.
[21] WANG S,ZHANG H,WANG H,et al.Combination of Point-Cloud Model and FCN for Dam Crack Detection and Scale Calculation[C]//2019 Chinese Automation Congress(CAC).New York:IEEE Press,2019:5859-5862.
[22] TANG J,MAO Y,WANG J,et al.Multi-task Enhanced Dam Crack Image Detection Based on Faster R-CNN[C]//IEEE 4th International Conference on Image,Vision and Computing(ICIVC).New York:IEEE Press,2019:336-340.
[23] LI L J,ZHANG H,PANG J,et al.Dam surface crack detection based on deep learning[C]//2019 International Conference on Robotics,Intelligent Control and Artificial Intelligence(RICAI).New York:ACM,2019:738-743.
[24] FAN X,WU J,SHI P,et al.A novel automatic dam crack detection algorithm based on local-global clustering[J].Multimedia Tools & Applications,2018(2018):26581-26599.
[25] SOUSA M J,MOUTINHO A,ALMEIDA M.Wildfire detection using transfer learning on augmented datasets[J].Expert Systems with Applications,2020,142(2020):1-14.
[26] LI X D,HU Y,LI M T,et al.Fault diagnostics between diffe-rent type of components:A transfer learning approach[J].Applied Soft Computing,2020,86(2020):1-11.
[27] ZHENG Z,QI H,ZHUANG L,et al.Automated Rail SurfaceCrack Analytics Using Deep Data-driven Models and Transfer Learning[J].Sustainable Cities and Society,2021,70(2021):1-11.
[28] HOWARD A G,ZHU M,CHEN B,et al.MobileNets:Efficient Convolutional Neural Networks for Mobile Vision Applications[J].arXiv:1704.04861,2017.
[29] AKCAY S,KUNDEGORSKI M E,WILLCOCKS C G,et al.Using Deep Convolutional Neural Network Architectures for Object Classification and Detection within X-ray Baggage Secu-rity Imagery[J].IEEE Transactions on Information Forensics & Security,2018,13(9):2203-2215.
[30] SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Net-works for Large-Scale Image Recognition[C]//ICLR 2015.New York:IEEE Press,2014:1-14.
[31] KE Y,LU Y L.Pet dog recognition method based on VGG16[J].Practical Electronics,2020,407(21):44-47.
[32] REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[J].arXiv,2018:1-6.
[33] NIE M,WANG C.Pavement Crack Detection based on yolo v3[C]//2019 2nd International Conference on Safety Produce Informatization(IICSPI).New York:IEEE Press,2019:327-330.
[34] DARSH P,RATHI P,KUMAR M.YOLO v3-Tiny:Object Detection and Recognition using one stage improved model[C]//2020 6th International Conference on Advanced Computing and Communication Systems(ICACCS).New York:IEEE Press,2020:687-694.
[35] TANG J,MAO Y,WANG J,et al.Multi-task Enhanced Dam Crack Image Detection Based on Faster R-CNN[C]//2019 IEEE 4th International Conference on Image,Vision and Computing(ICIVC).New York:IEEE Press,2019:336-340.

相关文章 15

[1]	徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[2]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[3]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[4]	方义秋, 张震坤, 葛君伟. 基于自注意力机制和迁移学习的跨领域推荐算法 Cross-domain Recommendation Algorithm Based on Self-attention Mechanism and Transfer Learning 计算机科学, 2022, 49(8): 70-77. https://doi.org/10.11896/jsjkx.210600011
[5]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[6]	王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[7]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[8]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[9]	胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[10]	程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[11]	侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[12]	周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[13]	苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[14]	祝文韬, 兰先超, 罗唤霖, 岳彬, 汪洋. 改进Faster R-CNN的光学遥感飞机目标检测 Remote Sensing Aircraft Target Detection Based on Improved Faster R-CNN 计算机科学, 2022, 49(6A): 378-383. https://doi.org/10.11896/jsjkx.210300121
[15]	王建明, 陈响育, 杨自忠, 史晨阳, 张宇航, 钱正坤. 不同数据增强方法对模型识别精度的影响 Influence of Different Data Augmentation Methods on Model Recognition Accuracy 计算机科学, 2022, 49(6A): 418-423. https://doi.org/10.11896/jsjkx.210700210

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed