Turn off MathJax
Article Contents
Qingsheng FENG, Shuai XIAO, Wangyang LIU, et al., “Research on Object Detection and Combination Clustering for Railway Switch Machine Gap Detection,” Chinese Journal of Electronics, vol. 34, no. 1, pp. 1–18, 2025 doi: 10.23919/cje.2023.00.268
Citation: Qingsheng FENG, Shuai XIAO, Wangyang LIU, et al., “Research on Object Detection and Combination Clustering for Railway Switch Machine Gap Detection,” Chinese Journal of Electronics, vol. 34, no. 1, pp. 1–18, 2025 doi: 10.23919/cje.2023.00.268

Research on Object Detection and Combination Clustering for Railway Switch Machine Gap Detection

doi: 10.23919/cje.2023.00.268
More Information
  • Author Bio:

    Qingsheng FENG received the B.S. degree in communication engineering and M.S. degree in traffic information engineering and control from Dalian Jiaotong University, Dalian, China, in 2001 and 2006, respectively, where he is now an Associate Professor. He has overseen and contributed to various projects funded by the Ministry of Education and Provincial Natural Science Foundation. His research interests include intelligent transportation information technology, as well as automation and control within rail transit. (Email: fqs@djtu.edu.cn)

    Shuai XIAO was born in 2001, he is currently pursuing the M.S. degree in traffic information engineering and control at Dalian Jiaotong University, Dalian, China. His current research interests are gap detection and intelligent fault diagnosis of railway switch machines. (Email: xiaos1002@126.com)

    Wangyang LIU received the B.S. degree in rail transit signal and control from Southwest Jiaotong University, Chengdu, China, and he is currently pursuing the M.S. degree at the School of Automation and Electrical Engineering, Dalian Jiaotong University, Dalian, China. His current research direction is automatic control and intelligent driving of train operation. (Email: liuwy20000711@163.com)

    Hong LI received the M.S. degree in traffic information engineering and control from Dalian Jiaotong University, Dalian, China, in 2006. She specializes in applied research within the realms of machine vision and deep learning. Her expertise encompasses network structure optimization and image processing. (Email: signal@djtu.edu.cn)

  • Corresponding author: Email: fqs@djtu.edu.cn
  • Received Date: 2023-07-31
  • Accepted Date: 2023-12-04
  • Available Online: 2024-03-01
  • Turnouts and switch machines play a crucial role in facilitating train line operations and establishing routes, making them vital for ensuring the safety and efficiency of railway transportation. Through the gap detection system of switch machines, the real-time working status of turnouts and switch machines on railway sites can be quickly known. However, due to the challenging working environment and demanding conversion tasks of switch machines, the current gap detection system has often experienced the issues of fault detection. To address this, this study proposes an automatic gap detection method for railway switch machines based on object detection and combination clustering. Firstly, a lightweight object detection network, specifically the MobileNetV3-YOLOv5s model, is used to accurately locate and extract the focal area. Subsequently, the extracted image undergoes preprocessing and is then fed into a combination clustering algorithm to achieve precise segmentation of the gap area and background, the algorithm consists of simple linear iterative clustering (SLIC), Canopy and kernel fuzzy c-means clustering (KFCM). Finally, the Fisher optimal segmentation criterion is utilized to divide the data sequence of pixel values, determine the classification nodes and calculate the gap size. The experimental results obtained from switch machine gap images captured in various scenes demonstrate that the proposed method is capable of accurately locating focal areas, efficiently completing gap image segmentation with a segmentation accuracy of 93.55%, and swiftly calculating the gap size with a correct rate of 98.57%. Notably, the method achieves precise detection of gap sizes even after slight deflection of the acquisition camera, aligning it more closely with the actual conditions encountered on railway sites.
  • loading
  • [1]
    X. X. Hu, Y. Cao, T. Tang, et al., “Data-driven technology of fault diagnosis in railway point machines: Review and challenges,” Transportation Safety and Environment, vol. 4, no. 4, article no. tdac036, 2022. doi: 10.1093/tse/tdac036
    [2]
    X. Liu, A. Lovett, T. Dick, et al., “Optimization of ultrasonic rail-defect inspection for improving railway transportation safety and efficiency,” Journal of Transportation Engineering, vol. 140, no. 10, article no. 04014048, 2014. doi: 10.1061/(ASCE)TE.1943-5436.0000697
    [3]
    Y. Cao, Y. K. Sun, G. Xie, et al., “A sound-based fault diagnosis method for railway point machines based on two-stage feature selection strategy and ensemble classifier,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 8, pp. 12074–12083, 2022. doi: 10.1109/TITS.2021.3109632
    [4]
    Y. K. Sun, Y. Cao, P. Li, et al., “Vibration-based fault diagnosis for railway point machines using VMD and multiscale fluctuation-based dispersion entropy,” Chinese Journal of Electronics, vol. 33, no. 3, pp. 803–813, 2024. doi: 10.23919/cje.2022.00.075
    [5]
    M. Hamadache, S. Dutta, O. Olaby, et al., “On the fault detection and diagnosis of railway switch and crossing systems: An overview,” Applied Sciences, vol. vo.9, no. 23, article no. 5129, 2019. doi: 10.3390/app9235129
    [6]
    S. Z. Huang, F. Zhang, R. J. Yu, et al., “Turnout fault diagnosis through dynamic time warping and signal normalization,” Journal of Advanced Transportation, vol. 2017 article no. 3192967, 2017. doi: 10.1155/2017/3192967
    [7]
    Z. Shi, Z. C. Liu, and J. Lee, “An auto-associative residual based approach for railway point system fault detection and diagnosis,” Measurement, vol. 119 pp. 246–258, 2018. doi: 10.1016/j.measurement.2018.01.062
    [8]
    S. Z. Huang, X. L. Yang, L. Wang, et al., “Two-stage turnout fault diagnosis based on similarity function and fuzzy c-means,” Advances in Mechanical Engineering, vol. 10, no. 12, pp. 1–12, 2018. doi: 10.1177/1687814018811402
    [9]
    Y. K. Sun, Y. Cao, G. Xie, et al., “Condition monitoring for railway point machines based on sound analysis and support vector machine,” Chinese Journal of Electronics, vol. 29, no. 4, pp. 786–792, 2020. doi: 10.1049/cje.2020.06.007
    [10]
    Y. K. Sun, Y. Cao, G. Xie, et al., “Sound based fault diagnosis for RPMs based on multi-scale fractional permutation entropy and two-scale algorithm,” IEEE Transactions on Vehicular Technology, vol. 70, no. 11, pp. 11184–11192, 2021. doi: 10.1109/TVT.2021.3090419
    [11]
    X. Lu, “Design and implementation of turnout safety detection system based on machine vision, ” Master Thesis, Beijing Jiaotong University, Beijing, China, 2007. (in Chinese).
    [12]
    S. C. Lou, “Study on switch machines gap detection system based on video image recognition technology, ” Master Thesis, Lanzhou Jiaotong University, Lanzhou, China, 2013. (in Chinese).
    [13]
    H. B. Zhou, Y. G. Zhang, L. N. Wang, et al., “Research of switch gap detection method based on machine vision,” Automation & Instrumentation, no. 6, pp. 26–29, 2014. doi: 10.3969/j.issn.1001-9227.2014.06.0026
    [14]
    T. H. Xu, G. Wang, H. F. Wang, et al., “Gap measurement of point machine using adaptive wavelet threshold and mathematical morphology,” Sensors, vol. 16, no. 12, article no. 2006, 2016. doi: 10.3390/s16122006
    [15]
    Z. W. Zhong and J. Y. Chen, “CMOS plane based location and detection of switch gaps,” Journal of the China Railway Society, vol. 38, no. 12, pp. 70–75, 2016. doi: 10.3969/j.issn.1001-8360.2016.12.011
    [16]
    Z. F. Li, D. Y. Lin, X. F. Peng, et al., “Detection algorithm of switch machine gap based on template matching,” Journal of the China Railway Society, vol. 43, no. 8, pp. 88–96, 2021. doi: 10.3969/j.issn.1001-8360.2021.08.011
    [17]
    C. Li, L. H. Zhao, and W. N. Liu, “Automatic detection algorithm of switch machine gap based on canny operator,” Journal of the China Railway Society, vol. 40, no. 10, pp. 81–87, 2018. doi: 10.3969/j.issn.1001-8360.2018.10.012
    [18]
    Y. T. Liu and G. W. Chen, “Automatic detection of switch machine gap based on SFFCM image segmentation,” Journal of Beijing Jiaotong University, vol. 46, no. 2, pp. 29–36, 2022. doi: 10.11860/j.issn.1673-0291.20210137
    [19]
    T. Tao, D. C. Dong, S. Z. Huang, et al., “Gap detection of switch machines in complex environment based on object detection and image processing,” Journal of Transportation Engineering, Part A: Systems, vol. 146, no. 8, article no. 04020083, 2020. doi: 10.1061/JTEPBS.0000406
    [20]
    H. G. Pan, Y. H. Shi, X. Y. Lei, et al., “Fast identification model for coal and gangue based on the improved tiny YOLO v3,” Journal of Real-Time Image Processing, vol. 19, no. 3, pp. 687–701, 2022. doi: 10.1007/s11554-022-01215-1
    [21]
    P. C. Yan, Q. S. Sun, N. N. Yin, et al., “Detection of coal and gangue based on improved YOLOv5.1 which embedded scSE module,” Measurement, vol. 188, article no. 110530, 2022. doi: 10.1016/j.measurement.2021.110530
    [22]
    F. J. Gui, S. Yu, H. L. Zhang, et al., “Coal gangue recognition algorithm based on improved YOLOv5,” in Proceedings of 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, Chongqing, China, pp. 1136–1140, 2021.
    [23]
    M. Sandler, A. Howard, M. L. Zhu, et al., “MobileNetV2: Inverted residuals and linear bottlenecks,” in Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 4510–4520, 2018.
    [24]
    Y. Hu, X. F. Zhang, D. Li, et al., “Anisotropic diffusion filters for flow-dependent variational data assimilation of sea surface temperature,” Ocean Modelling, vol. 184 article no. 102233, 2023. doi: 10.1016/j.ocemod.2023.102233
    [25]
    Z. Mbarki, C. Ben Jabeur Seddik, and H. Seddik, “Building a modified block matching kernel based on Wave Atom transform for efficient image denoising,” The Egyptian Journal of Remote Sensing and Space Science, vol. 24, no. 3, pp. 857–878, 2021. doi: 10.1016/j.ejrs.2021.08.009
    [26]
    G. G. Bhutada, R. S. Anand, and S. Saxena, “Edge preserved image enhancement using adaptive fusion of images denoised by wavelet and curvelet transform,” Digital Signal Processing, vol. 21, no. 1, pp. 118–130, 2011. doi: 10.1016/j.dsp.2010.09.002
    [27]
    L. A. de Oliveira Junior, H. R. Medeiros, D. Macêdo, et al., “SegNetRes-CRF: A deep convolutional encoder-decoder architecture for semantic image segmentation,” in Proceedings of the 2018 International Joint Conference on Neural Networks, Rio de Janeiro, Brazil, pp. 1–6, 2018.
    [28]
    A. Valada, R. Mohan, and W. Burgard, “Self-supervised model adaptation for multimodal semantic segmentation,” International Journal of Computer Vision, vol. 128, no. 5, pp. 1239–1285, 2020. doi: 10.1007/s11263-019-01188-y
    [29]
    H. J. Yu, M. F. Jiang, H. R. Chen, et al., “Super-pixel algorithm and group sparsity regularization method for compressed sensing MR image reconstruction,” Optik, vol. 140 pp. 392–404, 2017. doi: 10.1016/j.ijleo.2017.04.069
    [30]
    H. B. Wu, J. J. Zhang, C. Luo, et al., “Equivalent modeling of photovoltaic power station based on canopy-FCM clustering algorithm,” IEEE Access, vol. 7 pp. 102911–102920, 2019. doi: 10.1109/ACCESS.2019.2931444
    [31]
    J. Z. Ma, S. Li, H. Qin, et al., “Unsupervised multi-class co-segmentation via joint-cut over L1-manifold hyper-graph of discriminative image regions,” IEEE Transactions on Image Processing, vol. 26, no. 3, pp. 1216–1230, 2017. doi: 10.1109/TIP.2016.2631883
    [32]
    T. Lei, X. H. Jia, Y. N. Zhang, et al., “Significantly fast and robust fuzzy c-means clustering algorithm based on morphological reconstruction and membership filtering,” IEEE Transactions on Fuzzy Systems, vol. 26, no. 5, pp. 3027–3041, 2018. doi: 10.1109/TFUZZ.2018.2796074
    [33]
    J. F. Jing, S. J. Liu, G. Wang, et al., “Recent advances on image edge detection: A comprehensive review,” Neurocomputing, vol. 503, pp. 259–271, 2022. doi: 10.1016/j.neucom.2022.06.083
    [34]
    M. M. Rahman, M. K. Pk, and M. S. Uddin, “Optimum threshold parameter estimation of bidimensional empirical mode decomposition using fisher discriminant analysis for speckle noise reduction,” International Arab Journal of Information Technology, vol. 12, no. 5, pp. 456–464, 2015.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(14)  / Tables(8)

    Article Metrics

    Article views (300) PDF downloads(31) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return