Multi-temporal crack segmentation in concrete structures using deep learning approaches
Cracks are among the earliest indicators of deterioration in concrete structures. Early automatic detection of these cracks can significantly extend the lifespan of critical infrastructures, such as bridges, buildings, and tunnels, while simultaneously reducing maintenance costs and facilitating eff...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-07-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-annals.copernicus.org/articles/X-G-2025/341/2025/isprs-annals-X-G-2025-341-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849702602641506304 |
|---|---|
| author | S. Harb P. Achanccaray Diaz M. Maboudi M. Gerke |
| author_facet | S. Harb P. Achanccaray Diaz M. Maboudi M. Gerke |
| author_sort | S. Harb |
| collection | DOAJ |
| description | Cracks are among the earliest indicators of deterioration in concrete structures. Early automatic detection of these cracks can significantly extend the lifespan of critical infrastructures, such as bridges, buildings, and tunnels, while simultaneously reducing maintenance costs and facilitating efficient structural health monitoring. This study investigates whether leveraging multi-temporal data for crack segmentation can enhance segmentation quality. Therefore, we compare a Swin UNETR trained on multi-temporal data with a U-Net trained on mono-temporal data to assess the effect of temporal information compared with conventional single-epoch approaches. To this end, a multi-temporal dataset comprising 1356 images, each with 32 sequential crack propagation images, was created. After training the models, experiments were conducted to analyze their generalization ability, temporal consistency, and segmentation quality. The multi-temporal approach consistently outperformed its mono-temporal counterpart, achieving an IoU of 82.72% and a F1-score of 90.54%, representing a significant improvement over the mono-temporal model’s IoU of 76.69% and F1-score of 86.18%, despite requiring only half of the trainable parameters. The multi-temporal model also displayed a more consistent segmentation quality, with reduced noise and fewer errors. These results suggest that temporal information significantly improves the performance of segmentation models, offering a promising solution for improved crack identification and long-term monitoring of concrete structures, even with limited sequential data. |
| format | Article |
| id | doaj-art-b6db1a2602d74bbb8688d5561d1b49e5 |
| institution | DOAJ |
| issn | 2194-9042 2194-9050 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj-art-b6db1a2602d74bbb8688d5561d1b49e52025-08-20T03:17:35ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502025-07-01X-G-202534134810.5194/isprs-annals-X-G-2025-341-2025Multi-temporal crack segmentation in concrete structures using deep learning approachesS. Harb0P. Achanccaray Diaz1M. Maboudi2M. Gerke3Institute of Geodesy and Photogrammetry, Technische Universität Braunschweig, GermanyInstitute of Geodesy and Photogrammetry, Technische Universität Braunschweig, GermanyInstitute of Geodesy and Photogrammetry, Technische Universität Braunschweig, GermanyInstitute of Geodesy and Photogrammetry, Technische Universität Braunschweig, GermanyCracks are among the earliest indicators of deterioration in concrete structures. Early automatic detection of these cracks can significantly extend the lifespan of critical infrastructures, such as bridges, buildings, and tunnels, while simultaneously reducing maintenance costs and facilitating efficient structural health monitoring. This study investigates whether leveraging multi-temporal data for crack segmentation can enhance segmentation quality. Therefore, we compare a Swin UNETR trained on multi-temporal data with a U-Net trained on mono-temporal data to assess the effect of temporal information compared with conventional single-epoch approaches. To this end, a multi-temporal dataset comprising 1356 images, each with 32 sequential crack propagation images, was created. After training the models, experiments were conducted to analyze their generalization ability, temporal consistency, and segmentation quality. The multi-temporal approach consistently outperformed its mono-temporal counterpart, achieving an IoU of 82.72% and a F1-score of 90.54%, representing a significant improvement over the mono-temporal model’s IoU of 76.69% and F1-score of 86.18%, despite requiring only half of the trainable parameters. The multi-temporal model also displayed a more consistent segmentation quality, with reduced noise and fewer errors. These results suggest that temporal information significantly improves the performance of segmentation models, offering a promising solution for improved crack identification and long-term monitoring of concrete structures, even with limited sequential data.https://isprs-annals.copernicus.org/articles/X-G-2025/341/2025/isprs-annals-X-G-2025-341-2025.pdf |
| spellingShingle | S. Harb P. Achanccaray Diaz M. Maboudi M. Gerke Multi-temporal crack segmentation in concrete structures using deep learning approaches ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | Multi-temporal crack segmentation in concrete structures using deep learning approaches |
| title_full | Multi-temporal crack segmentation in concrete structures using deep learning approaches |
| title_fullStr | Multi-temporal crack segmentation in concrete structures using deep learning approaches |
| title_full_unstemmed | Multi-temporal crack segmentation in concrete structures using deep learning approaches |
| title_short | Multi-temporal crack segmentation in concrete structures using deep learning approaches |
| title_sort | multi temporal crack segmentation in concrete structures using deep learning approaches |
| url | https://isprs-annals.copernicus.org/articles/X-G-2025/341/2025/isprs-annals-X-G-2025-341-2025.pdf |
| work_keys_str_mv | AT sharb multitemporalcracksegmentationinconcretestructuresusingdeeplearningapproaches AT pachanccaraydiaz multitemporalcracksegmentationinconcretestructuresusingdeeplearningapproaches AT mmaboudi multitemporalcracksegmentationinconcretestructuresusingdeeplearningapproaches AT mgerke multitemporalcracksegmentationinconcretestructuresusingdeeplearningapproaches |