Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Automated visual inspection of target parts for train safety based on deep learning

  • Author(s): Fuqiang Zhou 1 ; Ya Song 1 ; Liu Liu 2 ; Dongtian Zheng 1
    • View affiliations
  • Source: Volume 12, Issue 6, August 2018, p. 550 – 555
    DOI:  10.1049/iet-its.2016.0338 , Print ISSN 1751-956X, Online ISSN 1751-9578
© The Institution of Engineering and Technology
Received 12/12/2016, Accepted 15/01/2018, Revised 16/11/2017, Published 13/02/2018

Visual inspection of target parts is a common approach to ensuring train safety. However, some key parts, such as fastening bolts, do not possess sufficient feature information, because they are usually small, polluted, or obscured. These factors affect inspection accuracy and can lead to serious accidents. Therefore, traditional visual inspection relying on feature extraction cannot always meet the requirements of high-accuracy inspection. Deep learning has considerable advantages in image recognition for autonomous information mining, but it requires a considerable amount of computation. To resolve the issues mentioned above, this study proposes a method that combines traditional visual inspection with deep learning. Traditional feature extraction is used to locate the targets approximately, which makes the deep learning purposeful and efficient. A composite neural network, stacked auto-encoder convolutional neural network (SAE-CNN), is provided to further improve the training efficiency. A SAE is added to a CNN so that the network can obtain optimum results faster and more accurately. Taking the inspection of centre plate bolts in a moving freight car as an example, the overall system and specific processes are described. The study results showed satisfactory accuracy. A related analysis and comparative experiment were also conducted.

Inspec keywords: feature extraction; learning (artificial intelligence); inspection; railway safety; neural nets; traffic engineering computing; data mining

Other keywords: image recognition; inspection accuracy; centre plate bolts; stacked auto-encoder convolutional neural network; SAE-CNN; target parts; deep learning; autonomous information mining; feature extraction; automated visual inspection; training efficiency; moving freight car; composite neural network; train safety

Subjects: Traffic engineering computing; Computer vision and image processing techniques; Knowledge engineering techniques; Data handling techniques; Image recognition; Neural computing techniques

References

    1. 1)
      • 21. Bouvrie, J.: ‘Notes on Convolutional Neural Networks’, Neural Nets, 2006.
    2. 2)
      • 1. Ngigi, R.W., Pislaru, C., Ball, A., et al: ‘Modern techniques for condition monitoring of railway vehicle dynamics’. Journal of Physics: Conf. Series, Huddersfield, UK, June 2012, pp. 12016–12027.
    3. 3)
      • 18. Anthimopoulos, M., Christodoulidis, S., Ebner, L., et al: ‘Lung pattern classification for interstitial lung diseases using a deep convolutional neural network’, IEEE Trans. Med. Imaging, 2016, 35, (5), pp. 1207–1216.
    4. 4)
      • 10. Zhao, J., Gong, M., Liu, J., et al: ‘Deep learning to classify difference image for image change detection’. Int. Joint Conf. on Neural Networks, IEEE, Beijing, China, July 2014.
    5. 5)
      • 19. Pim, M., Max, A., Viergever, A.M., et al: ‘Automatic segmentation of MR brain images with a convolutional neural network’, IEEE Trans. Med. Imaging, 2016, 35, (5), p. 1252.
    6. 6)
      • 17. Nogueira, R., Lotufo, R., Campos, M.R.: ‘Fingerprint liveness detection using convolutional neural networks’, IEEE Trans. Inf. Forensics Sec., 2017, 11, (6), pp. 1206–1213.
    7. 7)
      • 4. Resendiz, E., Hart, J.M., Ahuja, N.: ‘Automated visual inspection of railroad tracks’, IEEE Trans. Intell. Transp. Syst., 2013, 14, (2), pp. 751–760.
    8. 8)
      • 8. Lu, S., Liu, Z., Nan, G., et al: ‘Automated visual inspection of brake shoe wear’. Applied Optics and Photonics China (AOPC2015), Beijing, China, May 2015).
    9. 9)
      • 20. Berkin, B., Itthi, C., Audrey, P., et al: ‘Fast image reconstruction with L2-regularization’, J. Magn. Reson. Imag., 2014, 40, (1), pp. 181–191.
    10. 10)
      • 13. Wu, F., Wang, Z., Zhang, Z., et al: ‘Weakly semi-supervised deep learning for multi-label image annotation’, IEEE Trans. Big Data, 2017, 1, (3), pp. 109–122.
    11. 11)
      • 9. Nan, G., Yao, J.E.: ‘A real-time visual inspection method of fastening bolts in freight car operation’. Society of Photo-Optical Instrumentation Engineers (SPIE) Conf. Series, Beijing, China, May 2015, vol. 9675.
    12. 12)
      • 12. Lu, X., Lin, Z., Jin, H., et al: ‘Rating image aesthetics using deep learning’, IEEE Trans. Multimed., 2015, 17, (11), pp. 2021–2034.
    13. 13)
      • 5. Feng, H., Jiang, Z., Xie, F., et al: ‘Automatic fastener classification and defect detection in vision-based railway inspection systems’, IEEE Trans. Instrum. Meas., 2014, 63, (4), pp. 877–888.
    14. 14)
      • 22. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. IEEE Conf. on Computer Vision & Pattern Recognition, San Diego, CA, USA, June 2005, pp. 886–893.
    15. 15)
      • 2. Rathod, V.R., Anand, R.S., Ashok, A.: ‘Comparative analysis of NDE techniques with image processing’, Nondestruct. Test. Eval., 2012, 27, (4), pp. 305–326.
    16. 16)
      • 7. Liu, L., Zhou, F., He, Y.: ‘Vision-based fault inspection of small mechanical components for train safety’, IET Intell. Transp. Syst., 2015, 10, (2), pp. 130–139.
    17. 17)
      • 15. Su, H., Liu, F., Xie, Y., et al: ‘Region segmentation in histopathological breast cancer images using deep convolutional neural network’. IEEE Int. Symp. on Biomedical Imaging, New York, USA, April 2015.
    18. 18)
      • 11. Gao, S., Zhang, Y., Jia, K., et al: ‘Single sample face recognition via learning deep supervised autoencoders’, IEEE Trans. Inf. Forensics Sec., 2015, 10, (10), pp. 2108–2118.
    19. 19)
      • 6. Liu, L., Zhou, F., He, Y.: ‘Automated visual inspection system for bogie block key under complex freight train environment’, IEEE Trans. Instrum. Meas., 2015, 65, (1), pp. 1–13.
    20. 20)
      • 3. Zhou, F., Zou, R., Qiu, Y., et al: ‘Automated visual inspection of angle cocks during train operation’, Proc. Inst. Mech. Eng. F J. Rail Rapid Transit, 2013, 228, (7), pp. 794–806.
    21. 21)
      • 14. Wu, D., Pigou, L., Kindermans, P.J., et al: ‘Deep dynamic neural networks for multimodal gesture segmentation and recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2016, 38, (8), pp. 1583–1597.
    22. 22)
      • 16. Kim, Y., Moon, T.: ‘Human detection and activity classification based on micro Doppler signatures using deep convolutional neural networks’, IEEE Geosci. Remote Sens. Lett., 2016, 13, (1), pp. 8–12.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2016.0338
Loading

Related content

content/journals/10.1049/iet-its.2016.0338
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address