Crack SAM: enhancing crack detection utilizing foundation models and Detectron2 architecture

被引：0

作者：

Rakshitha, R. ^{[1
]}

Srinath, S. ^{[1
]}

Vinay Kumar, N. ^{[2
]}

Rashmi, S. ^{[1
]}

Poornima, B.V. ^{[1
]}

机构：

[1] JSS Science and Technology University, Mysuru

来源：

Journal of Infrastructure Preservation and Resilience | 2024年 / 5卷 / 01期

关键词：

Crack detection; Crack segmentation; Detectron2; model; SAM;

D O I：

10.1186/s43065-024-00103-1

中图分类号：

学科分类号：

摘要：

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. © The Author(s) 2024.

引用

共 32 条

[1] Koch C., Georgieva K., Kasireddy V., Akinci B., Fieguth P., A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure, Adv Eng Inf, 29, 2, pp. 196-210, (2015)
[2] Weng X., Huang Y., Wang W., Segment-based pavement crack quantification, Autom Constr, 105, (2019)
[3] Munawar H.S., Hammad A.W.A., Haddad A., Soares C.A.P., Waller S.T., Image-based crack detection methods: a review, Infrastructures, 6, 8, (2021)
[4] Shen W., Wang X., Bai X., Zhang Z., DeepContour: a deep convolutional feature learned by positive-sharing loss for contour detection, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit, 07-12-June-2015, October 2016, pp. 3982-3991, (2015)
[5] Ranjbar S., Nejad F.M., Zakeri H., An image-based system for pavement crack evaluation using transfer learning and wavelet transform, Int J Pavement Res Technol, 14, 4, pp. 437-449, (2021)
[6] Elbehiery H., Hefnawy A., Elewa M., Surface defects detection for ceramic tiles using image processing and morphological techniques, Proc - WEC’05 3rd World Enformatika Conf, 5, pp. 158-162, (2005)
[7] Chambon S., Moliard J-M (2011) Automatic Road Pavement Assessment with Image Processing: Review and Comparison, Int J Geophys, 2011, 1, (2011)
[8] Subirats P., Et al., Automation of pavement surface crack detection using the, Image Proc, 1, 1, pp. 3037-3040, (2006)
[9] Chen C., Seo H., Jun C.H., Zhao Y., Pavement crack detection and classification based on fusion feature of LBP and PCA with SVM, Int J Pavement Eng, 23, 9, pp. 3274-3283, (2022)
[10] Hoang N.D., Huynh T.C., Tran X.L., Tran VD (2022) A Novel Approach for Detection of Pavement Crack and Sealed Crack using image Processing and Salp Swarm Algorithm Optimized Machine Learning, Adv Civ Eng, 2022, 1, (2022)

← 1 2 3 4 →