Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2023, Vol. 63 Issue (7): 1153-1163    DOI: 10.16511/j.cnki.qhdxxb.2023.26.006
  论文 本期目录 | 过刊浏览 | 高级检索 |
基于改进DeepLabV3+网络的坝面裂缝检测方法
周迅1,2,3, 李永龙3, 周颖玥1,2, 王皓冉3, 李佳阳1,2, 赵家琦1,2
1. 西南科技大学 信息工程学院, 绵阳 621000;
2. 西南科技大学 特殊环境机器人技术四川省重点实验室, 绵阳 621000;
3. 清华四川能源互联网研究院, 成都 610213
Dam surface crack detection method based on improved DeepLabV3+ network
ZHOU Xun1,2,3, LI Yonglong3, ZHOU Yingyue1,2, WANG Haoran3, LI Jiayang1,2, ZHAO Jiaqi1,2
1. School of Information Engineering, Southwest University of Science and Technology, Mianyang 621000, China;
2. Sichuan Provincial Key Laboratory Robot Technology Used for Special Environment, Southwest University of Science and Technology, Mianyang 621000, China;
3. Sichuan Energy Internet Research Institute, Tsinghua University, Chengdu 610213, China
全文: PDF(11765 KB)   HTML
输出: BibTeX | EndNote (RIS)      
摘要 基于图像分析的水电站坝面缺陷判别是一种高效、精准的方法,然而大坝裂缝图像存在背景复杂以及裂缝和背景像素比例不均衡等问题,导致传统算法的检测效果差。该文提出一种基于改进的DeepLabV3+网络模型的坝面裂缝检测方法。该方法利用三线注意力模块(three line attention module,TLAM)提高模型对裂缝像素的提取能力;采用空洞空间金字塔池化(atrous spatial pyramid pooling,ASPP)模块进行级联优化,实现更密集的像素采样,获取更丰富的裂缝特征;将MobileNetV2作为特征提取主干网络,可实现网络轻量化并减少模型参数;将焦点损失(focal loss,FL)和Dice损失(Dice loss,DL)作为模型的损失函数,可克服数据不平衡的困难。对西南某水电站的坝面裂缝数据集进行模型有效性和对比实验,结果表明:该方法中用来评价模型精度的F1,score、平均交并比(mean intersection over union,MIoU)和平均像素精度(mean pixel accuracy,MPA)的值分别达到73.98%、66.73%和73.81%,比改进前的DeepLabV3+网络检测效果分别提高了3.33%、2.89%和1.12%,该方法可为坝面维护以及未来风险评估提供技术支撑。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
周迅
李永龙
周颖玥
王皓冉
李佳阳
赵家琦
关键词 坝面裂缝注意力机制损失函数DeepLabV3+网络    
Abstract:Image analysis is an efficient and accurate method for identifying hydropower dam surface defects. However, due to the complex background of dam crack images and the uneven proportion of cracks and background pixels, the detection effect of traditional algorithms is poor. Moreover, traditional artificial crack inspection is not only inefficient but also costly in the present day. Efficient and accurate dam surface crack detection techniques are crucial for dam maintenance and operation. In order to achieve accurate and efficient dam surface crack detection, a dam surface crack detection method based on an improved DeepLabV3+ model is proposed. Model training is carried out for the self-made dam surface crack image dataset of a hydropower station in Southwest China, and the model is evaluated by F1,score, ZMIoU, ZMPA, parameter quantity and other indicators. The following improvements are made to the traditional DeepLabV3+ network model: (1) A three line attention module is added to improve the model's ability to extract crack pixels and reduce proportion imbalance between background pixels and crack pixels. (2) The original pyramid pooling module is cascaded for model optimization so that the model can achieve more intensive pixel sampling, and subsequently obtain more abundant crack features. (3) In order to solve the problem of the significant/too large number of traditional DeepLabV3+ network parameters, MobileNetV2 network is used as the backbone of the model to extract the network, to reduce the network to a lightweight module, and to reduce model parameters. (4) Focal loss and Dice loss are used as the loss functions of the model to overcome the data imbalance and to improve the accuracy of network classification. The improved DeepLabV3+ network model in this paper could better realize the extraction of crack pixels, reduce the problems caused by the imbalance of pixel proportion, and better ensure the efficient and accurate detection of dam surface cracks. The experiment on the self-made dam surface crack image dataset of a hydropower station in Southwest China showed the following: (1) Compared with the original model, the improved DeepLabV3+ model increased F1, score by 3.33%, ZMIOU by 2.89%, ZMPA by 1.12%, and the parameters were reduced to 3 014 714. This finding showed that the improved model proposed in this paper had stronger performance than the original model, better ability to extract crack pixels, and could better complete the task of crack identification. (2) Compared with other attention mechanisms, the three line attention module proposed in this paper had certain advantages, which could increase the attention of the model to the crack pixels and enable the model to extract the crack features needed. Through an analysis of the experimental results, the model improved in this paper has stronger segmentation ability, less missing data and false detection, and can effectively complete the dam surface crack segmentation task. The improved method increases the efficiency and accuracy of dam surface crack detection and reduces the model parameters. It can provide powerful data support for crack detection and the safe operation of hydropower projects.
Key wordsdam surface crack    attention mechanism    loss function    DeepLabV3+ network
收稿日期: 2022-10-11      出版日期: 2023-06-27
基金资助:国家自然科学基金项目(U21A20157,52009064);四川省科技计划资助项目(2022YFSY0011,2022YFQ0080,2023YFS0410)
通讯作者: 李永龙,高级工程师,E-mail:liyonglong@hotmail.com;周颖玥,副研究员,E-mail:zhouyingyue@swust.edu.cn     E-mail: liyonglong@hotmail.com;zhouyingyue@swust.edu.cn
作者简介: 周迅(1997—),男,硕士研究生。
引用本文:   
周迅, 李永龙, 周颖玥, 王皓冉, 李佳阳, 赵家琦. 基于改进DeepLabV3+网络的坝面裂缝检测方法[J]. 清华大学学报(自然科学版), 2023, 63(7): 1153-1163.
ZHOU Xun, LI Yonglong, ZHOU Yingyue, WANG Haoran, LI Jiayang, ZHAO Jiaqi. Dam surface crack detection method based on improved DeepLabV3+ network. Journal of Tsinghua University(Science and Technology), 2023, 63(7): 1153-1163.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2023.26.006  或          http://jst.tsinghuajournals.com/CN/Y2023/V63/I7/1153
  
  
  
  
  
  
  
  
  
  
  
  
  
[1] 孙金华.我国水库大坝安全管理成就及面临的挑战[J].中国水利, 2018(20):1-6. SUN J H. Achievements and challenges of reservoir dam safety management in China[J]. China Water Resources, 2018(20):1-6.(in Chinese).
[2] 中华人民共和国水利部,中华人民共和国国家统计局.第一次全国水利普查公报[N].中国水利报, 2013-03-26(2). Ministry of Water Resources of the People's Republic of China, National Bureau of Statistics of the People's Republic of China. Bulletin of first national census for water[N]. China Water Resources News, 2013-03-26(2).(in Chinese).
[3] BUFFI G, MANCIOLA P, GRASSI S, et al. Survey of the Ridracoli Dam:UAV-based photogrammetry and traditional topographic techniques in the inspection of vertical structures[J]. Geomatics, Natural Hazards and Risk, 2017, 8(2):1562-1579.
[4] 朱道雄.水电站建筑物病害分析及处理措施研究:以宝珠寺电站、紫兰坝电站为例[D].宜昌:三峡大学, 2020. ZHU D X. Disease analysis and treatment measures of hydropower station buildings:Taking Baozhusi Hydropower Station and Zilanba Hydropower Station as examples[D]. Yichang:China Three Gorges University, 2020.(in Chinese).
[5] FUJITA Y, HAMAMOTO Y. A robust automatic crack detection method from noisy concrete surfaces[J]. Machine Vision and Applications, 2011, 22(2):245-254.
[6] LIU Y Q, YEOH J K W. Automated crack pattern recognition from images for condition assessment of concrete structures[J]. Automation in Construction, 2021, 128(5):103765.
[7] LEE B Y, KIM Y Y, YI S T, et al. Automated image processing technique for detecting and analysing concrete surface cracks[J]. Structure and Infrastructure Engineering, 2013, 9(6):567-577.
[8] NOH Y, KOO D, KANG Y M, et al. Automatic crack detection on concrete images using segmentation via fuzzy C-means clustering[C]//2017 International Conference on Applied System Innovation (ICASI). Sapporo, Japan:IEEE, 2017:877-880.
[9] YAMAGUCHI T, HASHIMOTO S. Fast crack detection method for large-size concrete surface images using percolation-based image processing[J]. Machine Vision and Applications, 2010, 21(5):797-809.
[10] QU Z, CHEN Y X, LIU L, et al. The algorithm of concrete surface crack detection based on the genetic programming and percolation model[J]. IEEE Access, 2019, 7(1):57592-57603.
[11] PRASANNA P, DANA K J, GUCUNSKI N, et al. Automated crack detection on concrete bridges[J]. IEEE Transactions on Automation Science and Engineering, 2016, 13(2):591-599.
[12] YANG Y S, YANG C M, HUANG C W. Thin crack observation in a reinforced concrete bridge pier test using image processing and analysis[J]. Advances in Engineering Software, 2015, 83(1):99-108.
[13] 王一兵,包腾飞,高治鑫.基于LabVIEW+VDM的混凝土坝裂缝检测方法[J].水利水电科技进展, 2021, 41(5):76-82. WANG Y B, BAO T F, GAO Z X. Crack detection method of concrete dams based on LabVIEW+VDM[J]. Advances in Science and Technology of Water Resources, 2021, 41(5):76-82.(in Chinese)
[14] KUMAR P, SHARMA A, KOTA S R. Automatic multiclass instance segmentation of concrete damage using deep learning model[J]. IEEE Access, 2021, 9:90330-90345.
[15] LIU Z Q, CAO Y W, WANG Y Z, et al. Computer vision-based concrete crack detection using U-Net fully convolutional networks[J]. Automation in Construction, 2019, 104(1):129-139.
[16] CHA Y J, CHOI W, BVYVKÖZTVRK O. Deep learning-based crack damage detection using convolutional neural networks[J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(5):361-378.
[17] ZHENG M J, LEI Z J, ZHANG K. Intelligent detection of building cracks based on deep learning[J]. Image and Vision Computing, 2020, 103(1):103987.
[18] WU X Y, MA J F, SUN Y, et al. Multi-scale deep pixel distribution learning for concrete crack detection[C]//202025th International Conference on Pattern Recognition (ICPR). Milan, Italy:IEEE, 2021:6577-6583.
[19] ALI R, CHUAH J H, TALIP M S A, et al. Structural crack detection using deep convolutional neural networks[J]. Automation in Construction, 2022, 133(1):103989.
[20] PARK S E, EEM S H, JEON H. Concrete crack detection and quantification using deep learning and structured light[J]. Construction and Building Materials, 2020, 252(1):119096.
[21] BHOWMICK S, NAGARAJAIAH S, VEERARAGHAVAN A. Vision and deep learning-based algorithms to detect and quantify cracks on concrete surfaces from UAV videos[J]. Sensors, 2020, 20(21):6299.
[22] 王君锋,刘凡,杨赛,等.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. WANG J F, LIU F, YANG S, et al. Dam crack detection based on multi-source transfer learning[J]. Computer Science, 2022, 49(6A):319-324.(in Chinese)
[23] CHEN L C, ZHU Y K, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the 15th European Conference on Computer Vision. Munich, Germany:Springer, 2018:833-851.
[24] SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2:Inverted residuals and linear bottlenecks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA:IEEE, 2018:4510-4520.
[25] RONNEBERGER O, FISCHER P, BROX T. U-Net:Convolutional networks for biomedical image segmentation[C]//18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich, Germany:Springer, 2015:234-241.
[26] BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet:A deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12):2481-2495.
[27] ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA:IEEE, 2017:2881-2890.
[28] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[C/OL].(2014-12-22)[2022-09-21]. https://arxiv.org/abs/1412.7062.
[29] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab:Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(4):834-848.
[30] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, USA:ACM, 2017:6000-6010.
[31] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8):2011-2023.
[32] WOO S, PARK J, LEE J Y, et al. CBAM:Convolutional block attention module[C]//Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich, Germany:Springer, 2018:3-19.
[33] WANG Q L, WU B G, ZHU P F, et al. ECA-Net:Efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA:IEEE, 2020:11531-11539.
[34] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA:IEEE, 2015:3431-3440.
[1] 张洋, 江铭虎. 基于句法树节点嵌入的作者识别方法[J]. 清华大学学报(自然科学版), 2023, 63(9): 1390-1398.
[2] 黄贲, 康飞, 唐玉. 基于目标检测的混凝土坝裂缝实时检测方法[J]. 清华大学学报(自然科学版), 2023, 63(7): 1078-1086.
[3] 逯波, 段晓东, 袁野. 面向跨模态检索的自监督深度语义保持Hash[J]. 清华大学学报(自然科学版), 2022, 62(9): 1442-1449.
[4] 杨宏宇, 张梓锌, 张良. 基于并行特征提取和改进BiGRU的网络安全态势评估[J]. 清华大学学报(自然科学版), 2022, 62(5): 842-848.
[5] 李明扬, 孔芳. 融入自注意力机制的社交媒体命名实体识别[J]. 清华大学学报(自然科学版), 2019, 59(6): 461-467.
[6] 张宇, 张鹏远, 颜永红. 基于注意力LSTM和多任务学习的远场语音识别[J]. 清华大学学报(自然科学版), 2018, 58(3): 249-253.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn