Flexi-YOLO: A lightweight method for road crack detection in complex environments
PLOS One · 16.06.2025 · 20 (6) · e0325993
DOI: 10.1371/journal.pone.0325993 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 16.06.2025. Verfasst von Jiexiang Yang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Group Building Scientific Innovation Project for Universities in Chongqing, Joint Training Base Construction Project for Graduate Students in Chongqing.
Abstract (Originalsprache)
Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model’s loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. The DCNv-C2f module is constructed for the transformation and fusion of feature information, allowing the convolutional kernels to adapt to the complex shape characteristics of cracks dynamically. A Global Attention Module (GAM) is integrated to improve the model’s perception of global information. The AKConv convolution operation is employed to adaptively adjust the size of convolutions, further enhancing local feature capturing. Additionally, a lightweight network design is implemented, establishing G-Head (Ghost-Head) as the detection head to optimize the issue of feature redundancy. Experimental results show that Flexi-YOLO achieves an accuracy increase of 2.7% over YOLOv8n, a recall rate rise of 4.7%, a mAP improvement of 5.3%, a mAP@0.5–0.95 increase of 3.9%, a decrease of 0.5 in GFLOPS, and an F1 score improvement from 0.80 to 0.84. Flexi-YOLO offers higher detection accuracy and robustness and meets the industrial demands for lightweight real-time detection and lower application costs, providing an efficient and precise solution for the automated detection of road cracks.
Autor:innen und Institutionen
- School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing, China.
- Institute of Computer Vision and Traffic Image Understanding, School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing, China.
- School of Mathematics and Statistics, Chongqing Jiaotong University, Chongqing, China.
ORCID-Profile: Jiexiang Yang
Förderung
- National Natural Science Foundation of China
- Group Building Scientific Innovation Project for Universities in Chongqing
- Joint Training Base Construction Project for Graduate Students in Chongqing
- Science and Technology Research Program of Chongqing Municipal Education Commission
Zitieren
APA
Yang, J., Tian, R., Zhou, Z., Tan, X., & He, P. (2025). Flexi-YOLO: A lightweight method for road crack detection in complex environments. PLOS One, 20(6), e0325993. https://doi.org/10.1371/journal.pone.0325993
Vancouver
Yang J, Tian R, Zhou Z, Tan X, He P. Flexi-YOLO: A lightweight method for road crack detection in complex environments. PLOS One. 2025;20(6):e0325993. doi:10.1371/journal.pone.0325993
BibTeX
@article{Yang2025,
author = {Yang, Jiexiang and Tian, Renjie and Zhou, Zexing and Tan, Xingyue and He, Pingyang},
title = {Flexi-YOLO: A lightweight method for road crack detection in complex environments},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {6},
pages = {e0325993},
doi = {10.1371/journal.pone.0325993}
}
EUVIMED