Abstract
Surface defects can affect the quality of steel plate. Many methods based on computer vision are currently applied to surface defect detection of steel plate. However, their real-time performance and object detection of small defect are still unsatisfactory. An improved object detection network based on You Only Look One-level Feature (YOLOF) is proposed to show excellent performance in surface defect detection of steel plate, called DLF-YOLOF. First, the anchor-free detector is used to reduce the network hyperparameters. Secondly, deformable convolution network and local spatial attention module are introduced into the feature extraction network to increase the contextual information in the feature maps. Also, the soft non-maximum suppression is used to improve detection accuracy significantly. Finally, data augmentation is performed for small defect objects during training to improve detection accuracy. Experiments show the average precision and average precision for small objects are 42.7% and 33.5% at a detection speed of 62 frames per second on a single GPU, respectively. This shows that DLF-YOLOF has excellent performance to meet the needs of industrial real-time detection.
Similar content being viewed by others
References
Q. Luo, X. Fang, L. Liu, C. Yang, Y. Sun, IEEE Trans. Instrum. Meas. 69 (2020) 626–644.
N. Neogi, D.K. Mohanta, P.K. Dutta, EURASIP J. Image Video Process. 2014 (2014) 1–19.
X. Sun, J. Gu, S. Tang, J. Li, Appl. Sci. 8 (2018) 2195.
K. Song, Y. Yan, Appl. Surf. Sci. 285 (2013) 858–864.
M.X. Chu, Y. Feng, Y.H. Yang, X. Deng, J. Iron Steel Res. Int. 28 (2021) 303–315.
H. Wang, J. Zhang, Y. Tian, H. Chen, H. Sun, K. Liu, IEEE Trans. Ind. Inform. 15 (2019) 2798–2809.
Q. Sun, J. Cai, Z. Sun, Math. Probl. Eng. 2016 (2016) 5797654.
J. Hou, K. Xia, F. Yang, B. Zu, Math. Probl. Eng. 2018 (2018) 9298017.
M. Tang, Y. Li, W. Yao, L. Hou, Q. Sun, J. Chen, Meas. Sci. Technol. 32 (2021) 115401.
C. Lin, C. Chen, C. Yang, F. Akhyar, C. Hsu, H. Ng, in: Advances in Artificial Intelligence, Software and Systems Engineering, Springer, Berlin, Germany, 2019, pp. 202–212.
J.P. Yun, D. Kim, K. Kim, S.J. Lee, C.H. Park, S.W. Kim, Opt. Eng. 56 (2017) 053108.
G. Song, K. Song, Y. Yan, IEEE Trans. Instrum. Meas. 69 (2020) 9709–9719.
Q. Ren, J. Geng, J. Li, 2018 Chinese Automation Congress (CAC), IEEE, Xi'an, China, 2018, pp. 2173–2178.
W. Li, X. Ye, Y. Zhao, W. Wang, Acta Electronica Sin. 48 (2020) 1284–1292.
X. Tao, D. Zhang, W. Ma, X. Liu, D. Xu, Appl. Sci. 8 (2018) 1575.
M. Sharma, J. Lim, H. Lee, Appl. Sci. 12 (2022) 6004.
Q. Chen, Y. Wang, T. Yang, X. Zhang, J. Cheng, J. Sun, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, IEEE, Piscataway, NJ, USA, 2021, pp. 13039–13048.
T.Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, S. Belongie, in: Proceedings of the IEEE conference on computer vision and pattern recognition, IEEE, Piscataway, NJ, USA, 2017, pp. 2117–2125.
Y. He, K. Song, Q. Meng, Y. Yan, IEEE Trans. Instrum. Meas. 69 (2020) 1493–1504.
T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, C.L. Zitnick, in: European conference on computer vision, Springer, Berlin, Germany, 2014, pp. 740–755.
J. Dai, H. Qi, Y. Xiong, Y. Li, G. Zhang, H. Hu, Y. Wei, in: Proceedings of the IEEE international conference on computer vision, IEEE, Piscataway, NJ, USA, 2017, pp. 764–773.
N. Bodla, B. Singh, R. Chellappa, L.S. Davis, in: Proceedings of the IEEE international conference on computer vision, IEEE, Piscataway, NJ, USA, 2017, pp. 5561–5569.
Z. Tian, C. Shen, H. Chen, T. He, in: Proceedings of the IEEE/CVF international conference on computer vision, IEEE, Piscataway, NJ, USA, 2019, pp. 9627–9636.
A. Neubeck, L. Van Gool, in: 18th International Conference on Pattern Recognition, IEEE, Piscataway, NJ, USA, 2006, pp. 850–855.
K. He, X. Zhang, S. Ren, J. Sun, in: Proceedings of the IEEE conference on computer vision and pattern recognition, IEEE, Piscataway, NJ, USA, 2016, pp. 770–778.
S. Woo, J. Park, J.Y. Lee, I.S. Kweon, in: Proceedings of the European conference on computer vision, Springer, Berlin, Germany, 2018, pp. 3–19.
S. Ren, K. He, R. Girshick, J. Sun, in: Advances in neural information processing systems, MIT Press, Cambridge, USA, 2017, pp. 1137–1149.
Z. Cai, N. Vasconcelos, in: Proceedings of the IEEE conference on computer vision and pattern recognition, IEEE, Piscataway, NJ, USA, 2018, pp. 6154–6162.
T.Y. Lin, P. Goyal, R. Girshick, K. He, P. Dollár, in: Proceedings of the IEEE international conference on computer vision, IEEE, Piscataway, NJ, USA, 2017, pp. 2980–2988.
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.Y. Fu, A.C. Berg, in: European conference on computer vision, Springer, Berlin, Germany, 2016, pp. 21–37.
G. Jocher, A. Chaurasia, A. Stoken, J. Borovec, NanoCode012, Y. Kwon, TaoXie, K. Michael, J. Fang, imyhxy, Lorna, C. Wong, Z. Yifu, A. V, D. Montes, Z. Wang, C. Fati, J. Nadar, Laughing, UnglvKitDe, tkianai, yxNONG, P. Skalski, A. Hogan, M. Strobel, M. Jain, L. Mammana, xylieong, ultralytics/yolov5, Zenodo, ultralytics/yolov5: v6.2-YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai integrations, August 17 2022. https://doi.org/10.5281/zenodo.7002879.
H.G. Ramaswamy, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, IEEE, Piscataway, NJ, USA, 2020, pp. 983–991.
Acknowledgements
This paper is supported by the Natural Science Foundation of Liaoning Province (No. 2022-MS-353) and Basic Scientific Research Project of Education Department of Liaoning Province (Nos. 2020LNZD06 and LJKMZ20220640)
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, Gh., Chu, Mx., Gong, Rf. et al. DLF-YOLOF: an improved YOLOF-based surface defect detection for steel plate. J. Iron Steel Res. Int. 31, 442–451 (2024). https://doi.org/10.1007/s42243-023-01059-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42243-023-01059-4