Automatic Crack Detection Using Weakly Supervised Semantic Segmentation Network and Mixed-Label Training Strategy
| Autor: | Zhang Shuyuan, Xu Hongli, Zhu Xiaoran, Xie Lipeng |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2024 |
| Předmět: | |
| Zdroj: | Foundations of Computing and Decision Sciences, Vol 49, Iss 1, Pp 95-118 (2024) |
| Druh dokumentu: | article |
| ISSN: | 2300-3405 2024-0007 |
| DOI: | 10.2478/fcds-2024-0007 |
| Popis: | Automatic crack detection in construction facilities is a challenging yet crucial task. However, existing deep learning (DL)-based semantic segmentation methods for this field are based on fully supervised learning models and pixel-level manual annotation, which are time-consuming and labor-intensive. To solve this problem, this paper proposes a novel crack semantic segmentation network using weakly supervised approach and mixed-label training strategy. Firstly, an image patch-level classifier of crack is trained to generate a coarse localization map for automatic pseudo-labeling of cracks combined with a thresholding-based method. Then, we integrated the pseudo-annotated with manual-annotated samples with a ratio of 4:1 to train the crack segmentation network with a mixed-label training strategy, in which the manual labels were assigned with a higher weight value. The experimental data on two public datasets demonstrate that our proposed method achieves a comparable accuracy with the fully supervised methods, reducing over 65% of the manual annotation workload. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|