Scene classification-assisted deep learning for crack detection in asphalt pavements
Regular inspection of concrete structures is essential for maintaining their serviceability and safety. Traditional visual inspection methods face challenges due to subjective judgment, shortage of qualified engineers, and budget constraints. This research proposes an automated crack detection syste...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Case Studies in Construction Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214509525008629 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839623238111461376 |
|---|---|
| author | Hiromu Tanaka Kazuma Shibano Tetsuya Suzuki |
| author_facet | Hiromu Tanaka Kazuma Shibano Tetsuya Suzuki |
| author_sort | Hiromu Tanaka |
| collection | DOAJ |
| description | Regular inspection of concrete structures is essential for maintaining their serviceability and safety. Traditional visual inspection methods face challenges due to subjective judgment, shortage of qualified engineers, and budget constraints. This research proposes an automated crack detection system using deep learning with UAV-captured visible images, addressing the challenge of varying lighting conditions on bridge pavements. A two-stage approach is implemented: first, a LeNet-based scene classification model classifies images into noisy areas, sunlit pavement areas, and shaded pavement areas; second, U-Net-based crack detection models are trained specifically for each lighting condition. To improve dataset quality and quantity, image processing techniques using L*a*b* color space are applied. Piecewise linear interpolation is used for L* values to switch contrast characteristics, while level shift is applied to a* and b* values. The scene classification achieves 94.4 % accuracy, with high precision in distinguishing between sunlit and shaded pavements. For crack detection, data augmentation through image processing significantly improves the shaded pavement model's performance, with recall increasing from 0.162 to 0.732. The highest F-measure of 0.784 is obtained when both training and test data are unified through image processing. The composite model combining scene classification and crack detection effectively reduces false detections in noisy areas and enables accurate detection across different lighting conditions. These results demonstrate that limiting training conditions to specific lighting environments and unifying dataset appearance through image processing contribute to improved crack detection accuracy in real-world bridge inspection scenarios. |
| format | Article |
| id | doaj-art-1f48d23c5e664d56b574a07d43e68181 |
| institution | Matheson Library |
| issn | 2214-5095 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Construction Materials |
| spelling | doaj-art-1f48d23c5e664d56b574a07d43e681812025-07-21T04:09:52ZengElsevierCase Studies in Construction Materials2214-50952025-12-0123e05064Scene classification-assisted deep learning for crack detection in asphalt pavementsHiromu Tanaka0Kazuma Shibano1Tetsuya Suzuki2Graduate School of Science and Technology, Niigata University, Niigata 950-2181, Japan; Corresponding author.Graduate School of Science and Technology, Niigata University, Niigata 950-2181, JapanInstitute of Agriculture, Niigata University, Niigata 950-2181, JapanRegular inspection of concrete structures is essential for maintaining their serviceability and safety. Traditional visual inspection methods face challenges due to subjective judgment, shortage of qualified engineers, and budget constraints. This research proposes an automated crack detection system using deep learning with UAV-captured visible images, addressing the challenge of varying lighting conditions on bridge pavements. A two-stage approach is implemented: first, a LeNet-based scene classification model classifies images into noisy areas, sunlit pavement areas, and shaded pavement areas; second, U-Net-based crack detection models are trained specifically for each lighting condition. To improve dataset quality and quantity, image processing techniques using L*a*b* color space are applied. Piecewise linear interpolation is used for L* values to switch contrast characteristics, while level shift is applied to a* and b* values. The scene classification achieves 94.4 % accuracy, with high precision in distinguishing between sunlit and shaded pavements. For crack detection, data augmentation through image processing significantly improves the shaded pavement model's performance, with recall increasing from 0.162 to 0.732. The highest F-measure of 0.784 is obtained when both training and test data are unified through image processing. The composite model combining scene classification and crack detection effectively reduces false detections in noisy areas and enables accurate detection across different lighting conditions. These results demonstrate that limiting training conditions to specific lighting environments and unifying dataset appearance through image processing contribute to improved crack detection accuracy in real-world bridge inspection scenarios.http://www.sciencedirect.com/science/article/pii/S2214509525008629Deep learningUAV imageryImage processingLighting conditionLeNetU-Net |
| spellingShingle | Hiromu Tanaka Kazuma Shibano Tetsuya Suzuki Scene classification-assisted deep learning for crack detection in asphalt pavements Case Studies in Construction Materials Deep learning UAV imagery Image processing Lighting condition LeNet U-Net |
| title | Scene classification-assisted deep learning for crack detection in asphalt pavements |
| title_full | Scene classification-assisted deep learning for crack detection in asphalt pavements |
| title_fullStr | Scene classification-assisted deep learning for crack detection in asphalt pavements |
| title_full_unstemmed | Scene classification-assisted deep learning for crack detection in asphalt pavements |
| title_short | Scene classification-assisted deep learning for crack detection in asphalt pavements |
| title_sort | scene classification assisted deep learning for crack detection in asphalt pavements |
| topic | Deep learning UAV imagery Image processing Lighting condition LeNet U-Net |
| url | http://www.sciencedirect.com/science/article/pii/S2214509525008629 |
| work_keys_str_mv | AT hiromutanaka sceneclassificationassisteddeeplearningforcrackdetectioninasphaltpavements AT kazumashibano sceneclassificationassisteddeeplearningforcrackdetectioninasphaltpavements AT tetsuyasuzuki sceneclassificationassisteddeeplearningforcrackdetectioninasphaltpavements |