Deep Learning-Based Metrics for Measuring Sustainability of County-Owned Bridges in the US
Publication: ASCE Inspire 2023
ABSTRACT
While bridges on the National Highway System are inspected and actively maintained by state departments of transportation in the US, the maintenance of county-owned bridges is the responsibility of local governments. They need simplified and improved metrics to better assess the service life and sustainability of their bridges. It is not a sustainable practice to seek state or federal funds when their bridges are posted or closed. Thus, actionable metrics are required to better maintain locally owned bridges, particularly those that are more vulnerable and/or located in rural areas. Local governments aim to make a budgetary plan and conduct timely repairs, but they need decision aids because communicating priorities on multiple bridge items can be challenging. By using deep learning-based computer vision techniques to automatically detect distress in the five benchmark maintenance categories, local governments can better understand maintenance urgency and work toward enhancing the sustainability of their bridges.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Bianchi, E., and Hebdon, M. (2021). Trained Model for the Semantic Segmentation of Concrete Cracks (Conglomerate). University Libraries, Virginia Tech. Software. https://doi.org/10.7294/16628596.v1.
He, K., Chen, X., Xie, S., Li, Y., Dollár, P., and Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000–16009).
Kaggle. (2018). Structural Defects Network (SDNET). https://www.kaggle.com/datasets/aniruddhsharma/structural-defects-network-concrete-crack-images Accessed on March 5, 2023.
Kirillov, A., et al. (2023). Segment anything. arXiv preprint arXiv:2304.02643.
Mei, Q., and Gül, M. (2019). A cost effective solution for road crack inspection using cameras and deep neural networks. arXiv preprint arXiv:1907.06014.
Pal, M., Palevičius, P., Landauskas, M., Orinaitė, U., Timofejeva, I., and Ragulskis, M. (2021). An overview of challenges associated with automatic detection of concrete cracks in the presence of shadows. Applied Sciences, 11(23), 11396.
Shamsabadi, E. A., Xu, C., Rao, A. S., Nguyen, T., Ngo, T., and Dias-da-Costa, D. (2022). Vision transformer-based autonomous crack detection on asphalt and concrete surfaces. Automation in Construction, 140, 104316.
Tang, W., Wu, R. T., and Jahanshahi, M. R. (2022). Crack segmentation in high-resolution images using cascaded deep convolutional neural networks and Bayesian data fusion. Smart Structures and Systems, 29(1), 221–235.
Ultralytics. (2023). You Only Look Once (YOLO)v8.
Information & Authors
Information
Published In
ASCE Inspire 2023
Pages: 529 - 536
History
Published online: Nov 14, 2023
ASCE Technical Topics:
- Architectural engineering
- Bridge engineering
- Bridge management
- Bridges
- Bridges (by type)
- Building management
- Business management
- Engineering fundamentals
- Government
- Highway bridges
- Highway transportation
- Infrastructure
- Infrastructure resilience
- Local government
- Maintenance and operation
- Measurement (by type)
- Metric systems
- Organizations
- Practice and Profession
- Structural engineering
- Sustainable development
- Transportation engineering
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.