Abstract
Railway transportation plays an important role in the national economy of China. As a basic component of railway infrastructure, railway fasteners play a crucial role in connecting various components. However, traditional manual inspection methods cannot guarantee the accuracy and efficiency of fastener detection, which poses potential threats to railway safety. In recent years, the widespread application of deep learning technology has brought new opportunities for fastener detection. YOLOv8 algorithm is currently one of the popular object detection algorithms with excellent detection accuracy and speed. ShuffleNetV2 network structure is a lightweight convolutional neural network that can significantly reduce model parameters and computational complexity without sacrificing detection accuracy. Therefore, the purpose of this study is to improve the detection speed and accuracy of YOLOv8 algorithm by combining its lightweight feature with ShuffleNetV2, and to propose a lightweight fastener detection method based on ShuffleNetV2 and YOLOv8, and introduce SE attention mechanism to enhance feature extraction. The method was trained and tested using 2km data images collected from a certain section of Nan**g subway, and its effectiveness was verified through experiments. The results showed that the proposed method was 2.8% higher than the official YOLOv8 source code, and increased by 5.5% and 3.4% compared with YOLOv7 and YOLOv5, respectively. In addition, the proposed method has a smaller model and is more suitable for lightweight fastener detection on embedded devices. This research has important significance for improving the automation of fastener detection, reducing computational parameters, and improving detection speed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wu, Y., et al.: Automatic detection of arbitrarily oriented fastener defect in high-speed railway. Autom. Constr. 131, 103913 (2021)
Zhan, Z., et al.: Wireless rail fastener looseness detection based on MEMS accelerometer and vibration entropy. IEEE Sens. J. 20(6), 3226–3234 (2019)
Huang, J., et al.: A comprehensive review of loosening detection methods for threaded fasteners. Mech. Syst. Signal Process. 168, 108652 (2022)
Nassar, S.A., **anjie, Y.: A mathematical model for vibration-induced loosening of preloaded threaded fasteners. J. Vib. Acoust. 131(2) (2009)
Zhang, P., et al.: Vibration modes and wave propagation of the rail under fastening constraint. Mech. Syst. Signal Process. 160, 107933 (2021)
Fan, H., et al.: High-speed railway fastener detection based on a line local binary pattern. IEEE Signal Process. Lett. 25(6), 788–792 (2018)
Feng, H., et al.: Automatic fastener classification and defect detection in vision-based railway inspection systems. IEEE Trans. Instrum. Meas. 63(4), 877–888(2013)
Liu, J., et al.: Defect detection for bird-preventing and fasteners on the catenary support device using improved faster R-CNN. In: Proceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT) 2019: Rail Transportation Information Processing and Operational Management Technologies. Springer, Singapore (2020)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)
Qi, H., Xu, T., Wang, G., et al.: MYOLOv3-Tiny: a new convolutional neural network architecture for real-time detection of track fasteners. Comput. Ind. 123, 103303 (2020)
Wei, X., et al.: Railway track fastener defect detection based on image processing and deep learning techniques: a comparative study. Eng. Appl. Artif. Intell. 80, 66–81 (2019)
Bai, T., et al.: An optimized railway fastener detection method based on modified Faster R-CNN. Measurement 182, 109742 (2021)
Hu, J., et al.: High speed railway fastener defect detection by using improved YOLOX-Nano model. Sensors 22(21), 8399 (2022)
Terven, J., Cordova-Esparza. D.: A comprehensive review of YOLO: from YOLOv1 to YOLOv8 and beyond (2023). ar**v:2304.00501
Ma, N., et al.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Ju, R.Y., Cai, W.: Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm (2023). ar**v:2304.05071
Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017
Zhang, Z., Lyons, M., Schuster, M., et al.: Comparison between geometry-based and gabor-wavelets-based facial expression recognition using multi-layer perceptron. In: Proceedings Third IEEE International Conference on Automatic face and gesture recognition. IEEE, pp. 454–459 (1998)
Tolstikhin, I.O., et al.: Mlp-mixer: An all-mlp architecture for vision. Adv. Neural. Info. Proc. Syst. 34, 24261–24272 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 Bei**g Paike Culture Commu. Co., Ltd.
About this paper
Cite this paper
Duan, J., Bai, T., Lv, B., Zong, H., Fu, H. (2024). Lightweight Detection of Fasteners with YOLOv8 Combined with ShuffleNetV2. In: Yang, J., Yao, D., Jia, L., Qin, Y., Liu, Z., Diao, L. (eds) Proceedings of the 6th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2023. EITRT 2023. Lecture Notes in Electrical Engineering, vol 1136. Springer, Singapore. https://doi.org/10.1007/978-981-99-9315-4_46
Download citation
DOI: https://doi.org/10.1007/978-981-99-9315-4_46
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-9314-7
Online ISBN: 978-981-99-9315-4
eBook Packages: EngineeringEngineering (R0)