Abstract
Aiming at problems of long-distance and steep-slope FAST (Five-hundred-meter Aperture Spherical radio Telescope) cable detection, a set of vision system and its processing method based YOLOX are proposed. This system overcomes many difficulties such as collecting high-altitude samples and complex background environment in FAST cable detection tasks, and It achieves the accurate positioning and classification of defects. Good detection effects have been achieved for multi-morphology, multi-scale, especially small defects. The defect detection system was validated on three defect data sets which could affect the normal use of the cable, and the accuracy is 91.7%. Thus the system and method can meet the efficiency and accuracy requirements of FAST cable detection, and it can also be practically applied to other various cables.
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
References
Qiao, X., Wang, H., Qi, C., et al.: Design and algorithm research of cable surface defect detection system based on machine vision. Mach. Tool Hydraul. 48(5), 49–53 (2020)
He, L.: Research on rapid cable surface defect detection algorithm based on machine vision. Electron. Technol. Softw. Eng. (11), 2 (2021)
Chen, L., Yang, X., Liu, H.: Research on cable surface defect detection based on improved deeplabv3+ network. High Technol. Commun. 031(009), 986–992 (2021)
Cha, Y.J., Choi, W., Suh, G., et al.: Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput. Aided Civ. Infrastruct. Eng. 33(9), 731 (2018)
Chen, J., Liu, Z., Wang, H., et al.: Automatic defect detection of fasteners on the catenary support device using deep convolutional neural network. IEEE Trans. Instrum. Meas. 67(2), 257 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25(2) (2012)
Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 2999–3007 (2017)
Ge, Z., Liu, S., Wang, et al.: YOLOX: exceeding YOLO series in 2021 (2021)
Ge, Z., Liu, S., Li, Z., et al.: OTA: optimal transport assignment for object detection (2021)
Acknowledgment
This work was supported by national key R&D programs (No. 2019YFB1312701) and the self-managed Project of State Key Laboratory of Robotic Technology and System in Harbin Institute of Technology (No. SKLRS202208B).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tong, X., Zhang, X., Liu, G., Li, C., Zhao, J. (2023). Vision Based Surface Defect Detection of Long-Distance and Steep-Slope FAST Cable. In: Qian, Z., Jabbar, M., Cheung, S.K.S., Li, X. (eds) Proceeding of 2022 International Conference on Wireless Communications, Networking and Applications (WCNA 2022). WCNA 2022. Lecture Notes in Electrical Engineering, vol 1059. Springer, Singapore. https://doi.org/10.1007/978-981-99-3951-0_60
Download citation
DOI: https://doi.org/10.1007/978-981-99-3951-0_60
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-3950-3
Online ISBN: 978-981-99-3951-0
eBook Packages: EngineeringEngineering (R0)