Crack SAM: enhancing crack detection utilizing foundation models and Detectron2 architecture
Authors:
Open Access
- 2 October 2024
- journal article
- research article
- Published by Springer Nature in Journal of Infrastructure Preservation and Resilience
- Vol. 5 (1) , 1-19
Abstract
Accurate crack detection is crucial for maintaining pavement integrity, yet manual inspections remain labor-intensive and prone to errors, underscoring the need for automated solutions. This study proposes a novel crack segmentation approach utilizing advanced visual models, specifically Detectron2 and the Segment Anything Model (SAM), applied to the CFD and Crack500 datasets, which exhibit intricate and diverse crack patterns. Detectron2 was tested with four configurations—mask_rcnn_R_50_FPN_3x, mask_rcnn_R_101_FPN_3x, faster_rcnn_R_50_FPN_3x, and faster_rcnn_R_101_FPN_3x—while SAM was compared using Focal Loss, DiceCELoss, and DiceFocalLoss. SAM with DiceFocalLoss outperformed Detectron2, achieving mean IoU scores of 0.69 and 0.59 on the CFD and Crack500 datasets, respectively. The integration of Detectron2 with faster_rcnn_R_101_FPN_3x and SAM using DiceFocalLoss involves generating bounding boxes with Detectron2, which serve as prompts for SAM to produce segmentation masks. This approach achieves mIoU scores of 0.83 for CFD dataset and 0.75 for Crack500 dataset. These results highlight the potential of combining foundation models with Detectron2 for advancing crack detection technologies, offering valuable insights for enhancing highway maintenance systems.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Crack Segmentation Network using Additive Attention Gate—CSN-IIEngineering Applications of Artificial Intelligence, 2022
- Pavement crack detection and classification based on fusion feature of LBP and PCA with SVMInternational Journal of Pavement Engineering, 2021
- Surface crack detection using deep learning with shallow CNN architecture for enhanced computationNeural Computing and Applications, 2021
- Survey on performance of deep learning models for detecting road damages using multiple dashcam image resourcesAdvanced Engineering Informatics, 2020
- An image-based system for pavement crack evaluation using transfer learning and wavelet transformInternational Journal of Pavement Research and Technology, 2020
- Concrete crack detection and quantification using deep learning and structured lightConstruction and Building Materials, 2020
- Crack Detection of Concrete Pavement With Cross-Entropy Loss Function and Improved VGG16 Network ModelIEEE Access, 2020
- Segment-based pavement crack quantificationAutomation in Construction, 2019
- A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructureAdvanced Engineering Informatics, 2015
- Microsoft COCO: Common Objects in Context2014