What question did this study set out to answer?

This research aims to improve rail surface defect detection in complex backgrounds using a lightweight YOLOv8n-based method.

July 2, 2026Scientific ReportsOpen Access

A lightweight YOLOv8n-based method for rail surface defect detection in complex railway environments

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved defect detection in complex railway environments, suggesting an effective lightweight solution.

This research aims to improve rail surface defect detection in complex backgrounds using a lightweight YOLOv8n-based method.
Developed a K-means + + defect scale prior optimization strategy for better small target representation.
Incorporated CloAtt, a local-global collaborative attention module, into the C2f structure.
Designed the Attention-Guided Bidirectional Feature Pyramid Network (ABiFPN) for improved feature fusion.
Achieved a mean Average Precision (mAP) of 85.7% at 0.5 IoU with 2.13M parameters and 7.5 GFLOPs.
Demonstrated improved detection accuracy compared to the baseline YOLOv8n.
Proposed model shows effective performance with reduced complexity for rail defect detection.

Zhu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark