YOLODF: A Concrete Bridge Surface Damage Detection Model Based on Multiscale Feature Fusion in Complex Environments

Li, L; Rashidi, M; Yu, Y; Bozorg, B; Kalhori, H

YOLODF: A Concrete Bridge Surface Damage Detection Model Based on Multiscale Feature Fusion in Complex Environments

Li, L Rashidi, M Yu, Y Bozorg, B Kalhori, H

Permalink

Publisher:: WILEY
Publication Type:: Journal Article
Citation:: Structural Control and Health Monitoring, 2025, 2025, (1)
Issue Date:: 2025-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (4.33 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Li, L
dc.contributor.author	Rashidi, M
dc.contributor.author	Yu, Y
dc.contributor.author	Bozorg, B
dc.contributor.author	Kalhori, H https://orcid.org/0000-0002-1908-4895
dc.contributor.editor	Cha, Y-J
dc.date.accessioned	2026-04-13T05:02:37Z
dc.date.available	2026-04-13T05:02:37Z
dc.date.issued	2025-01-01
dc.identifier.citation	Structural Control and Health Monitoring, 2025, 2025, (1)
dc.identifier.issn	1545-2255
dc.identifier.issn	1545-2263
dc.identifier.uri	http://hdl.handle.net/10453/194679
dc.description.abstract	Timely and efficient real-time surface damage detection is essential for maintaining the healthy operation of concrete bridges and has become a critical research focus. However, existing deep learning–based damage detection methods still face challenges such as low detection accuracy, poor adaptability, and limited applicability to diverse scenarios. To address these issues and enhance surface damage detection performance in complex environments, this study proposes an improved YOLODF model based on You Only Look Once, Version 5 (YOLOv5). The improvements include replacing the C3 module with the C2f structure with depthwise separable convolutions and inverted bottlenecks (DSIBC2f) module to build a new backbone network, DSIBCSPDarknet, which strengthens feature extraction capabilities. The SPPFCSPC structure is introduced to replace the spatial pyramid pooling fast (SPPF) module, enabling more effective multiscale feature fusion. Furthermore, the Enhanced Multidimensional Collaborative Attention (EMCA) is combined with the DSIBC2f module to construct a fused neck, FNeck, further optimizing feature fusion. Experimental results show that YOLODF significantly outperforms YOLOv5 in terms of precision, recall, F1 score, and mAP<inf>0.5</inf> and also surpasses the latest YOLOv12. Additionally, it demonstrates excellent damage detection capabilities in challenging scenarios, such as adverse weather, noise interference, and color variations. Despite a slight increase in computational load, YOLODF achieves a detection speed of 118 frames per second, demonstrating its high practicality for surface damage detection on bridges in complex environments.
dc.language	English
dc.publisher	WILEY
dc.relation	http://purl.org/au-research/grants/arc/IH210100048
dc.relation.ispartof	Structural Control and Health Monitoring
dc.relation.isbasedon	10.1155/stc/9952459
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0905 Civil Engineering
dc.subject.classification	Civil Engineering
dc.subject.classification	4005 Civil engineering
dc.title	YOLODF: A Concrete Bridge Surface Damage Detection Model Based on Multiscale Feature Fusion in Complex Environments
dc.type	Journal Article
utslib.citation.volume	2025
utslib.for	0905 Civil Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2026-04-13T05:02:35Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	2025
utslib.citation.issue	1

Abstract:

Timely and efficient real-time surface damage detection is essential for maintaining the healthy operation of concrete bridges and has become a critical research focus. However, existing deep learning–based damage detection methods still face challenges such as low detection accuracy, poor adaptability, and limited applicability to diverse scenarios. To address these issues and enhance surface damage detection performance in complex environments, this study proposes an improved YOLODF model based on You Only Look Once, Version 5 (YOLOv5). The improvements include replacing the C3 module with the C2f structure with depthwise separable convolutions and inverted bottlenecks (DSIBC2f) module to build a new backbone network, DSIBCSPDarknet, which strengthens feature extraction capabilities. The SPPFCSPC structure is introduced to replace the spatial pyramid pooling fast (SPPF) module, enabling more effective multiscale feature fusion. Furthermore, the Enhanced Multidimensional Collaborative Attention (EMCA) is combined with the DSIBC2f module to construct a fused neck, FNeck, further optimizing feature fusion. Experimental results show that YOLODF significantly outperforms YOLOv5 in terms of precision, recall, F1 score, and mAP0.5 and also surpasses the latest YOLOv12. Additionally, it demonstrates excellent damage detection capabilities in challenging scenarios, such as adverse weather, noise interference, and color variations. Despite a slight increase in computational load, YOLODF achieves a detection speed of 118 frames per second, demonstrating its high practicality for surface damage detection on bridges in complex environments.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/194679