SCA-Net: Structure–Context Aggregation with Multi-Scale Feature Fusion for Underwater Optical Defect Detection
Underwater optical images are often degraded by scattering, uneven illumination, and background clutter, making structural defects difficult to distinguish and localize. This study presents SCA-Net, an RT-DETR-r18-based detector for cracks, spalling, and holes in underwater structures. The network incorporates three modifications to the baseline. A dilated reparameterized residual block (DRRB) replaces the second residual convolution in the backbone. An efficient context transformer (ECT) applies single-head additive attention to the deepest feature map, while a detail–context enhancement fusion (DCEF) module combines parallel atrous convolutions with a projected detail pathway in the bidirectional neck. Channel gates are used in the associated resampling modules. On the image-level split of the underwater defect dataset (UDD), SCA-Net achieved a precision of 0.943, a recall of 0.927, an [email protected] of 0.942, and an [email protected]:0.95 of 0.638. Compared with RT-DETR-r18, recall, [email protected], and [email protected]:0.95 increased by 11.3, 2.5, and 2.1 percentage points, respectively. Among the tested configurations, the full model achieved the highest recall and both mAP metrics. The evaluation was limited to the image-level UDD split. Because the original videos and acquisition-batch records were not retained, independence across acquisition groups and generalization to other inspection conditions could not be verified.
Authors
- Zhe Chen (ORCID: https://orcid.org/0000-0002-2250-5371)
- You Zhang (ORCID: https://orcid.org/0000-0002-9599-2676)
- Chunyan Ma (ORCID: https://orcid.org/0000-0002-2772-1575)
- Yin Huang
- Wei Wei
- Jian Sun
Institutions
- Hohai University (CN)
- Shanghai Jiao Tong University (CN)
Publication Details
- Journal
- Technologies
- Published
- 2026-11-19
- DOI
- https://doi.org/10.3390/technologies14110769
- Primary Topic
- Infrastructure Maintenance and Monitoring
- Type
- article
- Field-Weighted Citation Impact
- 0.00