Abstract
It is crucial to grasp the status of all the catenary support components along the high-speed railway in real time, and thus conduct efficient fault detection to ensure the safety and stability of the catenary equipment. Therefore, in order to study the positioning and bad state detection of the support suspension device of the high-speed rail catenary, so as to improve the efficiency and automation level of components fault detection, a Yolov5 detection network combining the attention mechanism is proposed, called CA-Yolov5. The attention module is continuously added to the last three convolutional networks of different scales of Yolov5. The mechanism of embedding location information into channel attention can effectively improve the convolutional feature expression ability of the network, and guide the model to learn different channel weights without ignoring the importance of location information. Experiments show that the localization accuracy of 12 categories CSCs (Catenary support components) most performs better when compared with some recent representative networks, thus demonstrating the effectiveness of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wu, C., Liu, Z., Jiang, H.: Catenary image enhancement using wavelet-based contourlet transform with cycle translation. Optik-Int. J. Light Electron Opt. 125(15), 3922–3925 (2014)
Aydin, I., Karaköse, M., Akin, E.: A robust anomaly detection in pantograph-catenary system based on mean-shift tracking and foreground detection. In: 2013 IEEE International Conference on Systems, Man, and Cybernetics, Manchester, pp. 4444–4449. IEEE Press, Piscataway (2013)
Felzenszwalb, P.F., Girshick, R.B., Mcallester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)
Han, Y., Liu, Z., Geng, X., Zhong, J.P.: Fracture detection of ear pieces in catenary support devices of high-speed railway based on HOG features and two-dimensional Gabor transform. J. China Railway Soc. 39(2), 52–57 (2017)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Conference on Computer Vision and Pattern Recognition, San Diego, pp. 886–893, 20–25 (2005)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Wang, X., Han, T.X., Yan, S.: An hog-lbp human detector with partial occlusion handling. In: IEEE International Conference on Computer Vision, Tyoto, 29 September–02 October 2009, pp. 32–39 (2009)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2015)
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region based fully convolutional networks. ar**v:1605.06409 (2016)
Girshick, R.B.: Fast R-CNN. In: IEEE Conference on Computer Vision and Pattern Recognition, Santiago, pp. 1440–1448 (2015)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 1. IEEE (2001)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788 (2016)
Liu, W., et al.: SSD: single shot multibox detector. ar**v:1512.02325 (2015)
Jocher, G., et al.: ultralytics/yolov5: v4.0 (2021). https://doi.org/10.5281/zenodo.4418161
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. CoRR, vol. abs/1903.06586, pp. 1–12 (2019). http://arxiv.org/abs/1903.06586
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
He, K.M., Zhang, X.Y., Ren, S.Q., et al.: Deep residual learning for image recognition. In: IEEE International Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 770–778 (2016)
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759–8768 (2018)
Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: CVPR (2021)
Liu, W., et al.: Multi-objective performance evaluation of the detection of catenary support components using DCNNs. In: Proceedings of 15th IFAC Symposium Control Transportation Systems (CTS), pp. 98–105, January 2018
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhao, R., Han, Z., Liu, Z. (2022). Detection Approach Based on an Improved Yolov5 for Catenary Support Components. In: Jia, L., Qin, Y., Liang, J., Liu, Z., Diao, L., An, M. (eds) Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021. EITRT 2021. Lecture Notes in Electrical Engineering, vol 864. Springer, Singapore. https://doi.org/10.1007/978-981-16-9905-4_64
Download citation
DOI: https://doi.org/10.1007/978-981-16-9905-4_64
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-9904-7
Online ISBN: 978-981-16-9905-4
eBook Packages: EngineeringEngineering (R0)