A TBD-YOLO-Based Surface Defect Detection Method for Hot Rolled Steel Strips
Source abstract
Abstract
Abstract Hot rolled steel strips play an important role in the fields of construction, automobile manufacturing, energy, shipbuilding and petrochemicals, etc. Their high strength, corrosion resistance and plasticity make them an indispensable material in industrial manufacturing. Surface defect detection is an indispensable process in hot rolling production line, which is of great significance to improve the quality of hot rolled steel strip. The current detection accuracy of small target defects on the surface of hot rolled steel strips is low and cannot meet the real-time detection needs of enterprises. To solve this problem, we propose a steel strip surface defect detection method based on YOLOv8, named TBD-YOLO. First, the downsampling mechanism from YOLOv7 (V7downsample) is referenced to replace the downsampling modules in the backbone and neck networks to enhance detection accuracy. Second, a modified bidirectional feature pyramid network (mod_BiFPN) is designed for the neck to perform weighted fusion of multi-scale feature maps. Finally, a novel task-aligned detection head (TDH) is developed to improve the classification and localization performance of the detection head. Extensive experimental results demonstrate that, compared to the original YOLOv8 model, the detection method proposed in this paper has achieved a 7.8% increase in mean Average Precision at Intersection over Union 0.5 (mAP@0.5) value, effectively enhancing the detection capability for small target defects on hot-rolled steel strips surface. Moreover, the frames per second (FPS) has reached 79.8, meeting the real-time detection requirements of industrial sites.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Surface Roughness and Optical Measurements · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (27)
Show source-provided references
1. Zhang, Y., Zhang, H.F., Huang, Q.Q. et al., DsP-YOLO: An anchor-free network with DsPAN for small object detection of multiscale defects, Expert Syst. Appl., 2024, vol. 241, p. 122669.10.1016/j.eswa.2023.122669 ↗
2. Amin, D.D. and Akhter, S., Deep learning-based defect detection system in steel sheet surfaces, IEEE Region 10 Symp. (TENSYMP) (New Delhi, 2020), pp. 444–448.
3. Su, L.Q., Gao, B., Zhao, X.Y. et al., RHiREM: Intelligent diagnostic framework for pipeline Eddy Current Internal Inspection based on reinforcement learning with hierarchical reward exploration mechanism, NDT & E Int., 2024, vol. 144, p. 103073.10.1016/j.ndteint.2024.103073 ↗
4. Guo, Y., Yoshikawa, R., Yusa, N., and Hashizume, H., Design of a simple side-incident TE11 mode microwave probe for nondestructive pipe inspection, Meas. Sci. Technol., 2023, vol. 34, no. 8, p. 085104.10.1088/1361-6501/accca0 ↗
5. Ramírez, I.S., Chaparro, J.R.P., and Márquez, F.P.G., Unmanned aerial vehicle integrated real time kinematic in infrared inspection of photovoltaic panels, Measurement, 2022, vol. 188, p. 110536.10.1016/j.measurement.2021.110536 ↗
6. Girshick, R., Donahue, J., Darrell, T., and Malik, J., Rich feature hierarchies for accurate object detection and semantic segmentation, 2014 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) (Columbus, 2014), pp. 580–587.10.1109/CVPR.2014.81 ↗
7. Girshick, R., Fast R-CNN, 2015 IEEE International Conference on Computer Vision (ICCV) (Santiago, 2015), pp. 1440–1448.10.1109/ICCV.2015.169 ↗
8. Ren, S.X., He, K., Girshick, R., and Sun, J., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE T. Pattern Anal., 2017, vol. 39, pp. 1137–1149.10.1109/TPAMI.2016.2577031 ↗
9. He, K.M., Gkioxari, G., Dollar, P., and Girshick, R., Mask R-CNN, IEEE T. Pattern Anal., 2020, vol. 42, pp. 386–397.10.1109/TPAMI.2018.2844175 ↗
10. Liu, W., Anguelov, D., Erhan, D. et al., SSD: Single Shot MultiBox Detector, Comput. Vis.—ECCV 2016, Lect. Notes Comput. Sci. (Amsterdam, 2016), pp. 21–37.10.1007/978-3-319-46448-0_2 ↗
11. Redmon, J., Divvala, S.K., Girshick, R., and Farhadi, A., You only look once: Unified, real-time object detection, 2016 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) (Las Vegas, 2016), pp. 779–788.10.1109/CVPR.2016.91 ↗
12. Carion, N., Massa, F., Synnaeve, G. et al., End-to-end object detection with transformers, Comput. Vis.—ECCV 2020. Lect. Notes Comput. Sci. (Glasgow, 2020), pp. 213–229.10.1007/978-3-030-58452-8_13 ↗
13. He, D.Q., Ma, R., Jin, Z.Z. et al., Welding quality detection of metro train body based on ABC Mask R-CNN, Measurement, 2023, vol. 216, p. 112969.10.1016/j.measurement.2023.112969 ↗
14. Qian, B., Al Said, N., and Dong, B., New technologies for UAV navigation with real-time pattern recognition, Ain Shams Eng. J., 2024, vol. 15, no. 3, p. 102480.10.1016/j.asej.2023.102480 ↗
15. Wang, D., Yang, R.H., Zhang, Z.X. et al., P-Swin: Parallel Swin Transformer multi-scale semantic segmentation network for land cover classification, Comput. Geosci.-UK., 2023, vol. 175, p. 105340.
16. Liu, X.Y. and He, Y.G., A multi-stream multi-scale lightweight SwinMLP network with an adaptive channel-spatial soft threshold for online fault diagnosis of power transformers, Meas. Sci. Technol., 2023, vol. 34, no. 7, p. 075014.10.1088/1361-6501/acc2db ↗
17. Wan, D.H., Lu, R.S., Hu, B.T. et al., YOLO-MIF: Improved YOLOv8 with multi-information fusion for object detection in gray-scale images, Adv. Eng. Inf., 2024, vol. 62, p. 102709.10.1016/j.aei.2024.102709 ↗
18. Lu, M., Sheng, W.Q., Zou, Y. et al., WSS-YOLO: An improved industrial defect detection network for steel surface defects, Measurement, 2024, vol. 236, p. 115060.10.1016/j.measurement.2024.115060 ↗
19. Tan, M.X., Pang, R.M., and Le, Q.V., EfficientDet: Scalable and efficient object detection, 2020 IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) (2020), pp. 10778–10787.10.1109/CVPR42600.2020.01079 ↗
20. Feng, C.J., Zhong, Y.J., and Gao, Y., TOOD: Task-aligned one-stage object detection, 2021 IEEE/CVF Int. Conf. Comput. Vis. (ICCV) (2021), pp. 3490–3499.10.1109/ICCV48922.2021.00349 ↗
21. Dai, X., Chen, Y., and Xiao, B., Dynamic head: Unifying object detection heads with attentions, 2021 IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) (Nashville, 2021), pp. 7369–7378.10.1109/CVPR46437.2021.00729 ↗
22. Tian, Z., Shen, C., and Chen, H., FCOS: Fully convolutional one-stage object detection, 2019 IEEE/CVF Int. Conf. Comput. Vis. (ICCV) (Seoul, 2019), pp. 9626–9635.10.1109/ICCV.2019.00972 ↗
23. He, Y., Song, K.C., Meng, Q.G., and Yan, Y.H., An end-to-end steel surface defect detection approach via fusing multiple hierarchical features, IEEE T. Instrum. Meas., 2020, vol. 69, no. 4, pp. 1493–1504.10.1109/TIM.2019.2915404 ↗
24. Karras, T., Aittala, M., Laine, S. et al., Alias-free generative adversarial networks, Neural Inf. Process. Syst., 2021, pp. 1–31.
25. Under review as a conference paper at ICLR 2022, Context augmentation and feature refinement network for tiny object detection, pp. 1–11.
26. Peng, Y.P., Sonka, M., and Chen, D.Z., U-Net v2: Rethinking the skip connections of U-Net for medical image segmentation, Preprint, 2023. arXiv:2311.17791v2.
27. Stefenon, S.F., Seman, L.O., Klaar, A.C.R. et al., Hypertuned-YOLO for interpretable distribution power grid fault location based on EigenCAM, Ain Shams Eng. J., 2024, vol. 15, no. 6, p. 102722.10.1016/j.asej.2024.102722 ↗