Steel Surface Defect Detection Based on Improved RT-DETR

Qiubo HUANG , Yakui ZHANG , Mei WANG

Journal of Donghua University(English Edition) ›› 2026, Vol. 43 ›› Issue (5) : 80 -89.

PDF (5531KB)
Journal of Donghua University(English Edition) ›› 2026, Vol. 43 ›› Issue (5) :80 -89. DOI: 10.19884/j.1672-5220.202502011
Information Technology and Artificial Intelligence
research-article
Steel Surface Defect Detection Based on Improved RT-DETR
Author information +
History +
PDF (5531KB)

Abstract

To address the challenges of low accuracy in small target detection and high model complexity in steel surface defect detection, a novel defect detection algorithm named FCS-DETR is proposed based on the real-time detection transformer (RT-DETR) framework. The methodology involves three key technical improvements. First, a newly designed DC-RepC3 module replaces the original RepC3 module to expand the model’s receptive field for enhanced contextual information capture, which effectively suppresses complex background noise while improving detection accuracy. Second, for selective feature extraction, partial convolution is integrated into the backbone network to significantly reduce the parameter count and computational load, while wavelet pooling is further incorporated to strengthen model robustness. Finally, a Wise-ShapeIoU-NWD joint loss function is proposed, which incorporates both the shape and distribution characteristics of the target, reducing the geometric discrepancies between the predicted and ground truth bounding boxes and thus improving bounding box regression accuracy. Experimental results on the NEU-DET dataset demonstrate that FCS-DETR achieves a mean average precision at an intersection-over-union threshold of 0.50 (mAP50) of 76.6%, representing an improvement of 3.4 percentage points over RT-DETR-R18, while reducing the parameter count and computational complexity of the model by 31.8% and 28.8%, respectively. These advancements establish FCS-DETR as an effective solution for accurate and efficient steel surface defect detection, showing substantial potential for industrial applications.

Keywords

steel surface defect detection / RT-DETR / partial convolution / dilated convolution / wavelet pooling / Wise-IoU

Cite this article

Download citation ▾
Qiubo HUANG, Yakui ZHANG, Mei WANG. Steel Surface Defect Detection Based on Improved RT-DETR. Journal of Donghua University(English Edition), 2026, 43 (5) : 80-89 DOI:10.19884/j.1672-5220.202502011

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

Wu G H, Xiong H J. Radiography testing in China[J]. Chinese Journal of Scientific Instrument, 2016, 37(8): 1683-1695. (in Chinese)

[2]

Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2016: 779-788.

[3]

Farhadi A, Redmon J. YOLOv3: an incremental improvement[C]// Computer Vision and Pattern Recognition. Heidelberg: Springer, 2018, 1804: 1-6.

[4]

Li C Y, Li L L, Jiang H L, et al. YOLOv6: a single-stage object detection framework for industrial applications[PP/OL]. arXiv (2022-09-07)[2025-01-25]. https://arxiv.org/abs/2209.02976. arXiv: 2209.02976.

[5]

Zhang S Q, Shi W Y, Zhang S W, et al. Steel surface defect detection based on improved YOLOv5 algorithm[J]. Science Technology and Engineering, 2023, 23(35): 15148-15157. (in Chinese)

[6]

Li W, Yao X M, Zhang P C, et al. Study on improved YOLO-V7 algorithm of steel surface defect detection[J]. Mechanical Science and Technology for Aerospace Engineering. 2025, 44(12): 2191-2200. (in Chinese)

[7]

Zhen G Y, Zhao L R, Li W Y, et al. Research on lightweight of steel surface defect detection network based on improved YOLOv5[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2024(3): 58-63. (in Chinese)

[8]

Zhao Y A, Lü W Y, Xu S L, et al. DETRs beat YOLOs on real-time object detection[C]// 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2024: 16965-16974.

[9]

Williams T, Li R. Wavelet pooling for convolutional neural networks[C]// International Conference on Learning Representations.[S.l.]:[s.n.], 2018.

[10]

Wang C Y, Liao H Y, Wu Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway: IEEE, 2020: 1571-1580.

[11]

Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module[M]// Computer Vision-ECCV 2018. Cham: Springer International Publishing, 2018: 3-19.

[12]

Chen J R, Kao S H, He H, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2023: 12021-12031.

[13]

Tong Z J, Chen Y H, Xu Z W, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[PP/OL]. arXiv (2023-04-08)[2025-01-25]. https://arxiv.org/abs/2301.10051. arXiv: 2301.10051.

[14]

Zhang H, Zhang S J. Shape-IoU: more accurate metric considering bounding box shape and scale[PP/OL]. arXiv (2024-01-12)[ 2024-12-15]. https://arxiv.org/abs/2312.17663. arXiv: 2312.17663.

[15]

Wang J W, Xu C, Yang W, et al. A normalized Gaussian Wasserstein distance for tiny object detection[PP/OL]. arXiv (2022-07-14)[2024-12-15]. https://arxiv.org/abs/2110.13389. arXiv: 2110.13389.

[16]

He Y, Song K C, Meng Q G, et al. An end-to-end steel surface defect detection approach via fusing multiple hierarchical features[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(4): 1493-1504.

[17]

Fu R G, Hu Q Y, Dong X H, et al. Axiom-based grad-CAM: towards accurate visualization and explanation of CNNs[PP/OL]. arXiv (2020-08-19)[2024-12-15]. https://arxiv.org/abs/2008.02312. arXiv: 2008.02312.

[18]

Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141.

[19]

Huang H, Chen Z, Zou Y, et al. Channel prior convolutional attention for medical image segmentation[J]. Computers in Biology and Medicine, 2024, 178: 108784.

PDF (5531KB)

0

Accesses

0

Citation

Detail

Sections
Recommended

/

〈 〉