Accurate and Robust Vanishing Point Detection Method in Unstructured Road Scenes

  • Jiaming Han
  • Zhong Yang
  • Guoxiong Hu
  • Tianyi Zhang
  • Jiarong Song
Article

Abstract

Vanishing point detection is an essential component of vision-based autonomous navigation for unmanned ground vehicles and mobile robots. In this paper, we propose an accurate and robust vanishing point detection method for unstructured road scenes, where the road scenes lack clear road markings and include complex background interference. Since only the road region provides informative clues for vanishing point detection, we first introduce the manifold ranking method to estimate the road region based on background suppression. Then, we develop a series of principles for voter selection, and propose a dynamic adjustment strategy for the candidate selection that reduces the search scope of the vanishing point to perform candidate selection. Finally, we propose an effective voting strategy, in which the candidate that achieves the greatest number of votes in the voting space is considered to be the vanishing point. The experimental results on a large number of unstructured road images show that our proposed method is more accurate and robust than five existing methods.

Keywords

Vanishing point detection Autonomous navigation Unstructured road scene Road region estimation Background interference 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgments

The authors would like to thank the anonymous reviewers for their comments. This research was supported in part by the National Science Foundation of China (Grant No. 61473144), the Aeronautical Science Foundation of China (Key Laboratory) (Grant No. 20162852031) and the Special scientific instrument development of Ministry of science and technology of China (Grant No. 2016YFF0103702).

References

  1. 1.
    Yang, W., Fang, B., Tang, Y.Y.: Fast and accurate vanishing point detection and its application in inverse perspective mapping of structured road[j]. IEEE Trans. Syst. Man Cybern.: Systems PP(99), 1–12 (2017)Google Scholar
  2. 2.
    Phung, S.L., Le, M.C., Bouzerdoum, A.: Pedestrian lane detection in unstructured scenes for assistive navigation[J]. Comput. Vis. Image Underst. 149, 186–196 (2016)CrossRefGoogle Scholar
  3. 3.
    Pandey, A., Pandey, S., Parhi, D.R.: Mobile robot navigation and obstacle avoidance techniques: a review[j]. Int. Rob. Auto. J. 2(3), 00022 (2017)Google Scholar
  4. 4.
    Mur-Artal, R., Tardós, J.D.: Orb-slam2: an open-source slam system for monocular, stereo, and rgb-d cameras[J]. IEEE Trans. Robot. 33(5), 1255–1262 (2017)CrossRefGoogle Scholar
  5. 5.
    Moghadam, P., Starzyk, J.A., Wijesoma, W.S.: Fast vanishing-point detection in unstructured environments[J]. IEEE Trans. Image Process. 21(1), 425–430 (2012)MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    Weili, D., Yong, L., Wenfeng, W., et al.: Depth estimation of urban road image based on contour understanding[j]. Acta Opt. Sin. 34(7), 0715001 (2014)CrossRefGoogle Scholar
  7. 7.
    Kroeger, T., Dai, D., Van Gool, L.: Joint vanishing point extraction and tracking[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2449–2457 (2015)Google Scholar
  8. 8.
    Annich, A., El Abderrahmani, A., Satori, K.: Fast and easy 3D reconstruction with the help of geometric constraints and genetic algorithms[J]. 3D Res. 8(3), 30 (2017)CrossRefGoogle Scholar
  9. 9.
    Lee, J.K., Yoon, K.J.: Real-time joint estimation of camera orientation and vanishing points[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1866–1874 (2015)Google Scholar
  10. 10.
    Kortli, Y., Marzougui, M., Bouallegue, B., et al.: A novel illumination-invariant lane detection system[C]. In: 2017 2nd International Conference on Anti-Cyber Crimes (ICACC), pp. 166–171. IEEE (2017)Google Scholar
  11. 11.
    Ding, W., Li, Y., Liu, H.: Efficient vanishing point detection method in unstructured road environments based on dark channel prior[J]. IET Comput. Vis. 10(8), 852–860 (2016)CrossRefGoogle Scholar
  12. 12.
    Wu, Z., Fu, W., Xue, R., et al.: A novel line space voting method for vanishing-point detection of general road images[J]. Sensors 16(7), 948 (2016)CrossRefGoogle Scholar
  13. 13.
    Li, Y., Ding, W., Zhang, X.G., et al.: Road detection algorithm for autonomous navigation systems based on dark channel prior and vanishing point in complex road scenes[J]. Robot. Auton. Syst. 85, 1–11 (2016)CrossRefGoogle Scholar
  14. 14.
    Yoo, J.H., Lee, S.W., Park, S.K., et al.: A robust lane detection method based on vanishing point estimation using the relevance of line segments[J]. IEEE Trans. Intell. Transp. Syst. 18(12), 3254–3266 (2017)CrossRefGoogle Scholar
  15. 15.
    She, Q., Lu, Z., Liao, Q.: Vanishing point estimation for challenging road images[C]. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 996–1000. IEEE (2014)Google Scholar
  16. 16.
    Kong, H., Sarma, S.E., Tang, F.: Generalizing Laplacian of Gaussian filters for vanishing-point detection[J]. IEEE Trans. Intell. Transp. Syst. 14(1), 408–418 (2013)CrossRefGoogle Scholar
  17. 17.
    Fan, X., Chen, Y., Piao, J., et al.: Advanced road vanishing point detection by using weber adaptive local filter[C]. In: International Conference on Internet of Vehicles, pp. 3–13. Springer, Cham (2016)Google Scholar
  18. 18.
    Kong, H., Audibert, J.Y., Ponce, J.: Vanishing point detection for road detection[C]. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 96–103. IEEE (2009)Google Scholar
  19. 19.
    Nguyen, L., Phung, S.L., Bouzerdoum, A.: Efficient vanishing point estimation for unstructured road scenes[C]. In: 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1–6. IEEE (2016)Google Scholar
  20. 20.
    Nguyen, L., Phung, S.L., Bouzerdoum, A.: Enhanced pixel-wise voting for image vanishing point detection in road scenes[C]. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1852–1856. IEEE (2017)Google Scholar
  21. 21.
    Yang, W., Luo, X., Fang, B., et al.: Fast and accurate vanishing point detection in complex scenes[C]. In: 2014 IEEE 17th International Conference on Intelligent Transportation Systems (ITSC), pp. 93–98. IEEE (2014)Google Scholar
  22. 22.
    Miksik, O.: Rapid vanishing point estimation for general road detection[C]. In: 2012 IEEE International Conference on Robotics and Automation (ICRA), pp. 4844–4849. IEEE (2012)Google Scholar
  23. 23.
    Shi, J., Wang, J., Fu, F.: Fast and robust vanishing point detection for unstructured road following[J]. IEEE Trans. Intell. Transp. Syst. 17(4), 970–979 (2016)CrossRefGoogle Scholar
  24. 24.
    Zhou, D., Weston, J., Gretton, A., et al.: Ranking on data manifolds[C]. In: Advances in Neural Information Processing Systems, pp. 169–176 (2004)Google Scholar
  25. 25.
    Wang, Q., Lin, J., Yuan, Y.: Salient band selection for hyperspectral image classification via manifold ranking[J]. IEEE Transactions on Neural Networks and Learning Systems 27(6), 1279–1289 (2016)CrossRefGoogle Scholar
  26. 26.
    Neubert, P., Protzel, P.: Compact watershed and preemptive slic: On improving trade-offs of superpixel segmentation algorithms[C]. In: 2014 22nd International Conference on Pattern Recognition (ICPR), pp. 996-1001. IEEE (2014) Google Scholar
  27. 27.
    Alvarez, J.M.Á., Lopez, A.M.: Road detection based on illuminant invariance[J]. IEEE Trans. Intell. Transp. Syst. 12(1), 184–193 (2011)CrossRefGoogle Scholar
  28. 28.
    Xiang, Y., Wang, F., Wan, L., et al.: An advanced multiscale edge detector based on gabor filters for SAR Imagery[J]. IEEE Geosci. Remote Sens. Lett. 14(9), 1522–1526 (2017)CrossRefGoogle Scholar
  29. 29.
    Lee, T.S.: Image representation using 2D Gabor wavelets[J]. IEEE Trans. Pattern Anal. Mach. Intell. 18(10), 959–971 (1996)CrossRefGoogle Scholar
  30. 30.
    Xiao, J., Hays, J., Ehinger, K.A., et al.: Sun database: large-scale scene recognition from abbey to zoo[C]. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3485–3492. IEEE (2010)Google Scholar
  31. 31.
    Fan, X., Riaz, I., Rehman, Y., et al.: Vanishing point detection using random forest and patch-wise weighted soft voting[J]. IET Image Process. 10(11), 900–907 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V., part of Springer Nature 2018

Authors and Affiliations

  1. 1.College of Automation EngineeringNanjing University of Aeronautics and AstronauticsNanjingPeople’s Republic of China
  2. 2.College of SoftwareJiangxi Normal UniversityNanchangPeople’s Republic of China

Personalised recommendations