DyReCS-YOLO: A Dynamic Re-Parameterized Channel-Shuffle Network for Accurate X-Ray Tire Defect Detection

Bai, Xinlong; Dong, Quancheng; Han, Jinshuo; Zhou, Youjie; Qi, Xu; Tian, Longteng

doi:10.3390/electronics14234570

Open AccessArticle

DyReCS-YOLO: A Dynamic Re-Parameterized Channel-Shuffle Network for Accurate X-Ray Tire Defect Detection

by

Xinlong Bai

,

Quancheng Dong

^*

,

Jinshuo Han

,

Youjie Zhou

,

Xu Qi

and

Longteng Tian

School of Mechanical Engineering, University of Jinan, Jinan 250022, China

^*

Author to whom correspondence should be addressed.

Electronics 2025, 14(23), 4570; https://doi.org/10.3390/electronics14234570

Submission received: 22 October 2025 / Revised: 18 November 2025 / Accepted: 20 November 2025 / Published: 22 November 2025

(This article belongs to the Special Issue 2D/3D Industrial Visual Inspection and Intelligent Image Processing)

Download

Browse Figures

Versions Notes

Abstract

Reliable detection of X-ray tire defects is essential for safety and quality assurance in manufacturing. However, low contrast and high noise make traditional methods unreliable. This paper presents DyReCS-YOLO, a dynamic re-parameterized channel-shuffle network based on YOLOv8. The model introduces a C2f_DyRepFusion module combining dynamic convolution and a shuffle-and-routing mechanism, enabling adaptive kernel adjustment and efficient cross-channel interaction. Experiments on an industrial X-ray tire dataset containing 8326 images across 58 defect categories demonstrate that DyReCS-YOLO achieves an mAP@0.5 of 0.741 and mAP@0.5:0.95 of 0.505, representing improvements of 4.5 and 2.8 percentage points over YOLOv8-s, and 9.2 and 7.7 percentage points over YOLOv11-s, respectively. The precision increases from 0.698 (YOLOv8-s) and 0.668 (YOLOv11-s) to 0.739, while maintaining real-time inference at 189.5 FPS, meeting industrial online detection requirements. Ablation results confirm that the combination of dynamic convolution and channel shuffle improves small-defect perception and robustness. Moreover, DyReCS-YOLO achieves an mAP@0.5 of 0.975 on the public MT defect dataset, verifying its strong cross-domain generalization.

Keywords: tire defect detection; X-ray imaging; dynamic convolution; YOLOv8; channel shuffle; feature fusion

Share and Cite

MDPI and ACS Style

Bai, X.; Dong, Q.; Han, J.; Zhou, Y.; Qi, X.; Tian, L. DyReCS-YOLO: A Dynamic Re-Parameterized Channel-Shuffle Network for Accurate X-Ray Tire Defect Detection. Electronics 2025, 14, 4570. https://doi.org/10.3390/electronics14234570

AMA Style

Bai X, Dong Q, Han J, Zhou Y, Qi X, Tian L. DyReCS-YOLO: A Dynamic Re-Parameterized Channel-Shuffle Network for Accurate X-Ray Tire Defect Detection. Electronics. 2025; 14(23):4570. https://doi.org/10.3390/electronics14234570

Chicago/Turabian Style

Bai, Xinlong, Quancheng Dong, Jinshuo Han, Youjie Zhou, Xu Qi, and Longteng Tian. 2025. "DyReCS-YOLO: A Dynamic Re-Parameterized Channel-Shuffle Network for Accurate X-Ray Tire Defect Detection" Electronics 14, no. 23: 4570. https://doi.org/10.3390/electronics14234570

APA Style

Bai, X., Dong, Q., Han, J., Zhou, Y., Qi, X., & Tian, L. (2025). DyReCS-YOLO: A Dynamic Re-Parameterized Channel-Shuffle Network for Accurate X-Ray Tire Defect Detection. Electronics, 14(23), 4570. https://doi.org/10.3390/electronics14234570

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

DyReCS-YOLO: A Dynamic Re-Parameterized Channel-Shuffle Network for Accurate X-Ray Tire Defect Detection

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI