Identification of Fine Cracks in Concrete Bridges Based on the SFP-YOLOv11 Model

DOI

10.2991/978-94-6463-856-1_37How to use a DOI?

Keywords

Concrete bridge; Fine crack; YOLOv11; Object detection

Abstract

To address the issue of insufficient accuracy in identifying fine cracks in concrete bridges under complex backgrounds, a new crack detection model based on SPF-YOLOv11 is proposed. The model integrates Space-to-Depth Convolution (SPD-Conv), Feature Pyramid Shared Convolution (FPS-Conv), and the small object detection layers. To validate the model’s effectiveness, four sets of ablation experiments were designed to assess the impact of each module on the performance of the model. Results indicate that SPF-YOLOv11 enhances the retention of detail features, improving the detection accuracy of fine cracks. Compared to the original YOLOv11 model, the precision increased by 17%, recall improved by 8%, the F1 score rose by 12%, and mAP@0.5 increased by 11%.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ru Zhang
AU  - Chaodong Guan
AU  - Nahai Ding
AU  - Rui Miao
AU  - Xiaodong Sui
PY  - 2025
DA  - 2025/09/22
TI  - Identification of Fine Cracks in Concrete Bridges Based on the SFP-YOLOv11 Model
BT  - Proceedings of the 2025 International Conference on Resilient City and Safety Engineering (ICRCSE 2025)
PB  - Atlantis Press
SP  - 395
EP  - 403
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-856-1_37
DO  - 10.2991/978-94-6463-856-1_37
ID  - Zhang2025
ER  -