Block pavement and distress segmentation using deep learning models
- Authors
- Denu, Eskndir Getachew; Cho, Yoon-Ho
- Issue Date
- Jul-2024
- Publisher
- SPRINGER INT PUBL AG
- Keywords
- TransUNet; Block pavement; Distress detection; Convolutional neural networks; Transformers; Transfer learning
- Citation
- INNOVATIVE INFRASTRUCTURE SOLUTIONS, v.9, no.7
- Journal Title
- INNOVATIVE INFRASTRUCTURE SOLUTIONS
- Volume
- 9
- Number
- 7
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/74709
- DOI
- 10.1007/s41062-024-01533-2
- ISSN
- 2364-4176
2364-4184
- Abstract
- Block pavements require efficient distress detection and segmentation methods for quality control and pavement management systems. This research proposes TransUNet, a hybrid model for block and distress segmentation, combining convolutional neural networks (CNNs) and Vision transformers. The model adopts transfer learning to achieve accurate block segmentation, pre-training the model on a large wall image dataset and then fine-tuning it on a smaller set of block pavement images. This approach yields promising results with 77% intersection over union (IoU), 96.8% precision, 99.5% recall, and 98.1% F1-score, surpassing conventional CNN-based models, UNet and UNet + + . The use of transfer learning not only enhances accuracy but also significantly reduces training time and computational resources, as it eliminates the need for a large dataset. For the block distress segmentation model, the proposed hybrid TransUNet model obtained a mIoU of 71.3% outperforming CNN-based models. The CNN models often struggle to handle the diverse distress types commonly found in block pavements, resulting in sub-optimal distress segmentation outcomes. By automating block and distress segmentation, the proposed models contribute to efficient maintenance planning and the development of sustainable infrastructure.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/74709)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.