Weakly supervised crack segmentation using crack attention networks on concrete structures

Anoop Mishra; Gopinath Gangisetti; Yashar Eftekhar Azam; Deepak Khazanchi

doi:10.1177/14759217241228150

journal article Feb 17, 2024

Weakly supervised crack segmentation using crack attention networks on concrete structures

Anoop Mishra

Gopinath Gangisetti Yashar Eftekhar Azam Deepak Khazanchi

Structural Health Monitoring Vol. 23 No. 6 pp. 3748-3777 · SAGE Publications

View at Publisher Save 10.1177/14759217241228150

Abstract

Crack detection or segmentation on concrete structures is a vital process in structural health monitoring (SHM). Though supervised machine learning techniques have gained tremendous success in this domain, data collection and annotation continue to be challenging. Image data collection is challenging, tedious, and laborious, including accessing representative datasets and manually labeling training data in the SHM domain. According to the literature, there are significant issues with the hand-annotation of image data. To address this gap, this paper proposes a two-stage weakly supervised learning framework utilizing a novel “crack attention network (CrANET)” with attention mechanism to detect and segment cracks on images with no human annotations in pixel-level labels. This framework classifies concrete surface images into crack or no-cracks and then uses gradient class activation mapping visualization to generate crack segmentation. Professionals and domain experts subsequently evaluate these segmentation results via a human expert validation study. As the literature suggests that weakly supervised learning is a limited practice in SHM, this research title will motivate researchers in SHM to research and develop a weakly supervised learning approach processing as state of the art.

Topics

No keywords indexed for this article. Browse by subject →

References

54

[1]

US department of transportation: building a better America fact sheet for rural communities, 2022, https://tinyurl.com/66z9w842.

[2]

Gandhi RA Proceedings of the international ISCRAM conference (2018)

[3]

Lee GC (2013)

[4]

10.1080/03081060.2011.602850

[5]

10.1016/j.autcon.2019.04.005

[6]

10.1016/j.advengsoft.2015.02.005

[7]

Reghukumar A (2020) 10.1007/978-981-15-9019-1_19

[8]

Machine Learning Algorithms in Civil Structural Health Monitoring: A Systematic Review

Majdi Flah, Itzel Nunez, Wassim Ben Chaabene et al.

Archives of Computational Methods in Engineering 10.1007/s11831-020-09471-9

[9]

10.1007/s11227-019-03045-8

[10]

10.1080/15732479.2017.1330891

[11]

10.1061/(asce)0887-3801(2003)17:4(255)

[12]

10.1016/j.aej.2017.01.020

[13]

10.1177/1369433220986638

[14]

Tan C (2019)

[15]

Yang Q Comput Concr Int J (2020)

[16]

10.1177/1475921720927488

[17]

10.1016/j.engfracmech.2022.108467

[18]

10.3390/s20071838

[19]

10.3390/app12031374

[20]

Çağlar F Mendeley Data (2019)

[21]

10.1109/access.2021.3133712

[22]

10.3390/buildings12040432

[23]

10.1145/3411764.3445518

[24]

10.1007/978-3-319-46478-7_34

[25]

Unbiased look at dataset bias

Antonio Torralba, Alexei A. Efros

CVPR 2011 10.1109/cvpr.2011.5995347

[26]

Northcutt CG arXiv preprint arXiv:2103.14749 (2021)

[27]

Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring

Billie F. Spencer, Vedhus Hoskere, Yasutaka Narazaki

Engineering 10.1016/j.eng.2018.11.030

[28]

10.1016/j.conbuildmat.2020.120291

[29]

Barnes B Masters Thesis, Department of Civil and Environmental Engineering (2021)

[30]

10.1109/access.2020.2977821

[31]

Zhao W Struct Control Health Monit (2022)

[32]

A review of computer vision–based structural health monitoring at local and global levels

Chuan-Zhi Dong, F Necati Catbas

Structural Health Monitoring 10.1177/1475921720935585

[33]

Alhuda Z Appl Intell (2022)

[34]

10.1016/j.compind.2021.103545

[35]

10.1016/j.measurement.2021.110641

[36]

10.1186/s43251-023-00106-0

[37]

10.1109/cvpr.2019.00550

[38]

10.1007/978-3-030-01234-2_1

[39]

10.1109/cvpr.2011.5995467

[40]

Learning Deep Features for Discriminative Localization

Bolei Zhou, Aditya Khosla, Agata Lapedriza et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.319

[41]

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das et al.

2017 IEEE International Conference on Computer Vis... 10.1109/iccv.2017.74

[42]

Goodfellow I (2016)

[43]

Recent advances in convolutional neural networks

Jiuxiang Gu, Zhenhua Wang, Jason Kuen et al.

Pattern Recognition 10.1016/j.patcog.2017.10.013

[44]

10.3390/s20216299

[45]

Review of Bridge Structural Health Monitoring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection

Limin Sun, Zhiqiang Shang, Ye Xia et al.

Journal of Structural Engineering 10.1061/(asce)st.1943-541x.0002535

[46]

A brief introduction to weakly supervised learning

Zhi-Hua Zhou

National Science Review 10.1093/nsr/nwx106

[47]

Bilen H. WSL tutorial: 1. Introduction to the tutorial on weakly supervised learning.

[48]

Goyal P arXiv preprint arXiv:2103.01988 (2021)

[49]

Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

Amina Adadi, Mohammed Berrada

IEEE Access 10.1109/access.2018.2870052

[50]

Computational modelling of visual attention

Laurent Itti, Christof Koch

Nature Reviews Neuroscience 10.1038/35058500

Showing 50 of 54 references

Cited By

13

CrackCLIP: Adapting Vision-Language Models for Weakly Supervised Crack Segmentation

Fengjiao Liang, Qingyong Li · 2025

Entropy

Triple-stage crack detection in stone masonry using YOLO-ensemble, MobileNetV2U-net, and spectral clustering

Ali Mahmoud Mayya, Nizar Faisal Alkayem · 2025

Automation in Construction

Optical crack detection and assessment using cholesteric liquid crystal elastomers

Tarik Čamo, Rijeesh Kizhakidathazhath · 2024

Structural Health Monitoring

Metrics

13

Citations

54

References

Details

Published: Feb 17, 2024
Vol/Issue: 23(6)
Pages: 3748-3777
License: View

Authors

A

Anoop Mishra

University of Nebraska Omaha, Omaha, NE, USA

G

Gopinath Gangisetti

University of Nebraska Omaha, Omaha, NE, USA

Y

Yashar Eftekhar Azam

University of New Hampshire, Durham, NE, USA

D

Deepak Khazanchi

University of Nebraska Omaha, Omaha, NE, USA

Funding

NSF MIDWEST: Smart Big Data Pipeline for Aging Rural Bridge Transportation Infrastructure Award: 1762034

Cite This Article

Anoop Mishra, Gopinath Gangisetti, Yashar Eftekhar Azam, et al. (2024). Weakly supervised crack segmentation using crack attention networks on concrete structures. Structural Health Monitoring, 23(6), 3748-3777. https://doi.org/10.1177/14759217241228150

Weakly supervised crack segmentation using crack attention networks on concrete structures

You May Also Like