13th Asia Pacific Transportation Development Conference
A New Method of Achieving Quantitative Measurement for Horizontal Position Displacement of Track Fastener
Publication: Resilience and Sustainable Transportation Systems
ABSTRACT
To solve the problem that the horizontal position displacement of the track fast clip fastener is difficult to achieve quantitative measurement, this paper adopts an image segmentation technology based on machine vision combined with deep learning algorithm to realize the quantitative calculation and analysis of the relative position of the fastener and the rail. The method uses the convolutional neural network PSPNet to construct the automatic recognition and segmentation model of the fastener edge and the rail edge features, and then calculates the fastener horizontal position deviation by the relation between the fastener image pixel and the actual size. The model was verified by actual 893 images acquired on site from Shijiazhuang railway section. The results showed that the average correct rate of the automatic recognition and segmentation model of the fastener and the rail edge features was high to 98.35%, the average loss was 0.0109, and the accuracy of the horizontal displacement of the fastener reached less than 0.25 mm.
Get full access to this article
View all available purchase options and get full access to this chapter.
ACKNOWLEDGEMENT
This project is supported by SUES Research Start-up Fund No. 0240-E3-0507-19-05081, NSFC (Grant No. 51975347), NSFC (Grant No. 51907117) and Key Technology R&D Project of Shanghai Committee of Science and Technology (Grant No. 18030501300).
REFERENCES
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481-2495.
Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). “ DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834-848.
He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). “Mask R-CNN”. 2017 IEEE International Conference on Computer Vision (ICCV), 2980-2988.
Li, J., He, S., Wong, H. C., & Lo, S. L. (2019). “Proposal-Driven Segmentation for Videos”. IEEE Signal Processing Letters, 26(8), 1098-1102.
Long, J., Shelhamer, E., & Darrell, T. (2015). “Fully Convolutional Networks for Semantic Segmentation”. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431-3440.
Wang, W. Q., Yang, J., & You, X. (2018). “Combining ElasticFusion with PSPNet for RGB-D based Indoor Semantic Mapping”. 2018 Chinese Automation Congress (CAC), 2996-3001.
Xu, G., Cheng, C., Yang, W., Xie, W., Kong, L., Hang, R., … & Yang, J. (2019). “Oceanic Eddy Identification Using an AI Scheme”. Remote Sensing, 11(11).
Yokoi, S., Hara, T., Katafuchi, T., Matsusako, M., Zhou, X., & Fujita, H. (2019). “Quantitative analysis of dopamine transporter imaging using generating MR image from low dose CT image and segmentation by Deep Learning”. International Forum on Medical Imaging in Asia 2019, 11050.
Zeiler, M. D., Taylor, G. W., & Fergus, R. (2011). “Adaptive Deconvolutional Networks for Mid and High Level Feature Learning”. 2011 IEEE International Conference on Computer Vision (ICCV), 2018-2025.
Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). “Pyramid Scene Parsing Network”. 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), 6230-6239.
Information & Authors
Information
Published In
Resilience and Sustainable Transportation Systems
Pages: 385 - 393
Editors: Fengxiang Qiao, Ph.D., Texas Southern University, Yong Bai, Ph.D., Marquette University, Pei-Sung Lin, Ph.D., University of South Florida, Steven I Jy Chien, Ph.D., New Jersey Institute of Technology, Yongping Zhang, Ph.D., California State Polytechnic University, and Lin Zhu, Ph.D., Shanghai University of Engineering Science
ISBN (Online): 978-0-7844-8290-2
Copyright
© 2020 American Society of Civil Engineers.
History
Published online: Jun 29, 2020
Published in print: Jun 29, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.