Scholarlink

<p>Bridges continuously face traffic pressure and environmental influences, leading to surface defects that need accurate detection for optimized maintenance and sustainability. The appearance and shape of bridge surface defects vary greatly, and multiple overlapping defects can occur in small areas. Current automatic detection methods also struggle with detection accuracy due to these complexities. Most studies focus on specific defect types and cannot fully assess a bridge’s condition. To address these limitations, we propose YOLO-Defect, a novel multi-scale YOLO-based deep neural network that introduces two innovative modules: the Global Depthwise Spatial Pyramid Pooling Fusion (GDSPPF) module for multi-scale feature integration, and the Feature Enhancement (FE) module for improved defect-background discrimination. YOLO-Defect is evaluated on the ZJU SYG crack and CODEBRIM datasets, outperforming benchmarks like Faster R-CNN, SSD, RetinaNet, and YOLOv5. On the ZJU SYG crack dataset, it achieves 78.2% mAP@0.5 and 56.9% mAP@0.5:0.95, while on the CODEBRIM dataset, it achieves 39.5% mAP@0.5 and 17.8% mAP@0.5:0.95.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

YOLO-Defect: multi-scale feature enhancement for robust bridge surface defect detection

  • 期刊论文

  • 发表日期：

    2026年7月22日

查看全文
  • Haihao Tang,
  • Xiaobo Zhang,
  • Yutao Liu,
  • Donghai Zhai,
  • Yongle Li

摘要

Bridges continuously face traffic pressure and environmental influences, leading to surface defects that need accurate detection for optimized maintenance and sustainability. The appearance and shape of bridge surface defects vary greatly, and multiple overlapping defects can occur in small areas. Current automatic detection methods also struggle with detection accuracy due to these complexities. Most studies focus on specific defect types and cannot fully assess a bridge’s condition. To address these limitations, we propose YOLO-Defect, a novel multi-scale YOLO-based deep neural network that introduces two innovative modules: the Global Depthwise Spatial Pyramid Pooling Fusion (GDSPPF) module for multi-scale feature integration, and the Feature Enhancement (FE) module for improved defect-background discrimination. YOLO-Defect is evaluated on the ZJU SYG crack and CODEBRIM datasets, outperforming benchmarks like Faster R-CNN, SSD, RetinaNet, and YOLOv5. On the ZJU SYG crack dataset, it achieves 78.2% mAP@0.5 and 56.9% mAP@0.5:0.95, while on the CODEBRIM dataset, it achieves 39.5% mAP@0.5 and 17.8% mAP@0.5:0.95.