Skip to main content

Advertisement

Springer Nature Link
Log in

Efficient railway tracks detection and turnouts recognition method using HOG features

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Railway tracks detection and turnouts recognition are the basic tasks in driver assistance systems, which can determine the interesting regions for detecting obstacles and signals. In this paper, a novel railway tracks detection and turnouts recognition method using HOG (Histogram of Oriented Gradients) features was presented. At first, the approach computes HOG features and establishes integral images, and then extracts railway tracks by region-growing algorithm. Then based on recognizing the open direction of the turnout, we find the path where the train will travel through. Experiments demonstrated that our method was able to correctly extract tracks and recognize turnouts even in very bad illumination conditions and run fast enough for practical use. In addition, our approach only needs a computer and a cheap camera installed in the railroad vehicle, not specialized hardwares and equipment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Notes

  1. If only finding one railway track, the other can be obtained by mirror-method. We may delete extra tracks by mirror-method and information of image sequences if more than two railway tracks are detected.

  2. If the change of the distance between two railway tracks is monotonic, only the half of one railway track is detected and connected with tapering rail (In practice, this case is almost impossible to happen, we may deal with it as no existing turnout).

  3. s 1 is the maximum lateral deviation s 1 of the center X t of the currently traveled track from the center of the vehicle.

References

  1. Rico Garcia C, Lehner A, Strang T, Rockl M (2007) Comparison of Collision avoidance systems and applicability to rail transport. In: Proceedings of 7th international conference on intelligent transport systems telecommunications, ISBN 1-4244-1177-7, pp 521–526

  2. SRA (2004) European rail traffic management system. Website http://www.sra.gov.uk

  3. Singh M, Singh S, Jaiswal J, Hempshall J (2006) Autonomous rail track inspection using vision based system. In: IEEE international conference on computational intelligence for Homeland security and personal safety, vol 16, pp 56–59

  4. McCall JC, Trivedi MM (2006) Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation. IEEE Trans Intell Transport Syst 7(2):20–37

    Article  Google Scholar 

  5. Danescu R, Nedevschi S (2009) Probabilistic lane tracking in difficult road scenarios using stereovision. Trans Intell Transport Syst 10(2):272–282

    Article  Google Scholar 

  6. Lipski C, Scholz B, Berger K, Linz C, Stich T, Magnor M (2008) A fast and robust approach to lane marking detection and lane tracking. In: IEEE southwest symposium on image analysis and interpretation, pp 57−60

  7. Zhou Y, Xu R, Hu X, Ye Q (2006) A robust lane detection and tracking method based on computer vision. Meas Sci Technol 17(4):736–746

    Article  Google Scholar 

  8. Kim Z, Cohn TE (2004) Pseudoreal-time activity detection for railroad grade-crossing safety. IEEE Trans Intell Transport Syst 5(4):319–324

    Article  Google Scholar 

  9. Mohler N, Ruder M, Ahmed F (2003) An obstacle detection system for automated trains. In: Intelligent vehicles symposium, pp 180–185

  10. Mockel S, Scherer F, Schuster PF (2003) Multi-sensor obstacle detection on railway tracks. In: Intelligent vehicles symposium, pp 42–46

  11. Kaleli F, Akgul YS (2009) Vision-based railroad track extraction using dynamic programing. In: The 12th international IEEE conference on intelligent transportation systems

  12. Maire F (2007) Vision based anti-collision system for rail track maintenance vehicles. In: IEEE conference on advanced video and signal based surveillance (AVSS), pp 170–175

  13. Gschwandtner M, Pree W, Uhl A (2010) Track detection for autonomous trains. Lect Notes Comput Sci 6455:19–28

    Google Scholar 

  14. Nassu BT, Ukai M (2011) Rail extraction for driver support in railways. In: Intelligent vehicles symposium (IV), IEEE, pp 83–88

  15. Wohlfeil J, Institute of Robot (2011) Vision based rail track and switch recognition for self-localization of trains in a rail network. In: Intelligent vehicles symposium (IV), IEEE, pp 1025–1030

  16. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. CVPR 1:886–893

    Google Scholar 

  17. Laptev I (2006) Improvements of object detection using boosted histograms. BMVC

  18. Qi Z, Wang L, Xu Y (2008) Robust object detection based on decision trees and a new cascade architecture. In: Proceedings of cimca, pp 1129–1134

  19. Qi Z, Xu Y, Wang L (2011) Online multiple instance boosting for object detection. Neurocomputing 74(10):1769–1775

    Article  Google Scholar 

  20. Kadota R, Sugano H, Hiromoto M, Ochi H, Miyamoto R, Nakamura Y (2009) Hardware architecture for HOG feature extraction. In: IIH-MSP, September

  21. Ma H, Zeng C (2011) Robust head-shoulder detection by pca-based multilevel hog-lbp detector for people counting. In: ICPR

  22. Kuo C-H, Huang C, Nevatia R (2010) Multi-target tracking by on-line learned discriminative appearance models. In: CVPR, pp 685–692

  23. Porkili F (2005) Integral histogram: afast way to extract histograms in cartesian spaces. In: Proceedings of the IEEE conference on computer vision and pattern recognition, CVPR

  24. Adams R, Bischof L (1994) Seeded region growing. IEEE Trans Pattern Anal Mach Intell 16(6):64–647

    Article  Google Scholar 

  25. Swain MJ, Ballard DH (1991) Color indexing. IJCV 7(1):11–32

    Article  Google Scholar 

Download references

Acknowledgments

This work has been partially supported by grants from National Natural Science Foundation of China (No.709- 21061, No.10601064, No.61153003), the CAS/SAFEA International Partnership Program for Creative Research Teams and Major International (Ragional) Joint Research Project (No.71110107026), the President Fund of GUCAS, and the National Technology Support Program 2009BAH42B02.

Author information

Authors and Affiliations

  1. Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing, 100190, China

    Zhiquan Qi, Yingjie Tian & Yong Shi

  2. College of Information Science and Technology, University of Nebraska at Omaha, Omaha, NE, 68182, USA

    Yong Shi

Authors
  1. Zhiquan Qi
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yingjie Tian
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yong Shi
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence to Yingjie Tian or Yong Shi.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Qi, Z., Tian, Y. & Shi, Y. Efficient railway tracks detection and turnouts recognition method using HOG features. Neural Comput & Applic 23, 245–254 (2013). https://doi.org/10.1007/s00521-012-0846-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-012-0846-0

Keywords

Profiles

  1. Yingjie Tian View author profile