Skip to main content
SpringerLink
Log in

Obstacle detection in single images with deep neural networks

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Obstacle detection in single images is a challenging problem in autonomous navigation on low-cost condition. In this paper, we introduce an approach for obstacle detection in single images with deep neural networks. We propose the followings: (1) a deep model combined with other deep neural network for obstacle detection; (2) a method to segment obstacles and infer their depths. Among others, both local and global information are generated in our method for better classification and portability. Experiments are performed on the open datasets and images captured by our autonomous vehicle. The results show that our method is effective in both obstacle detection and depth inference.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

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

Similar content being viewed by others

References

  1. Defense Advanced Research Projects Agency. DARPA urban challenge (2007). http://archive.darpa.mil/grandchallenge/. Nov 2007

  2. Enkelmann, W.: Obstacle detection by evaluation of optical flow fields from image sequences. Image Vis. Comput. 9(3), 160–168 (1991)

    Article  Google Scholar 

  3. Braillon, C., Pradalier, C., Crowley, J.L., et al.: Real-time moving obstacle detection using optical flow models. Intelligent Vehicles Symposium IEEE. (2006)

  4. Shi, J., Tomasi, C.: Good features to track. In: Proceedings of the CVPR, 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 593–600. (1994)

  5. Bouguet, J.Y.: Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm, Intel Corporation (2001)

  6. Jung, B., Sukhatme, G.S.: Real-time motion tracking from a mobile robot. Int. J. Soc. Robot. 2(1), 63–78 (2010)

    Article  Google Scholar 

  7. Jia, B., Liu, R., Zhu, M.: Real-time obstacle detection with motion features using monocular vision. Vis. Comput. (2014). doi:10.1007/s00371-014-0918-5

  8. Turk, M.A., Marra, M.: Color Road Segmentation and Video Obstacle Detection. In: SPIE Proceedings of Mobile Robots, vol. 727, pp.136–142. Cambridge, MA (1987)

  9. Ulrich, I., Nourbakhsh, I.: “Appearance-based obstacle detection with monocular color vision”, AAAI/IAAI, pp. 866–871. (2000)

  10. Wu, H., Liu, N., Luo, X., et al.: Real-time background subtraction-based video surveillance of people by integrating local texture patterns. Signal Image Video Process. 8(4), 665–676 (2014)

  11. Christian, C., Noll, D., Werner, M.: Artificial neural networks in real-time car detection and tracking applications. Pattern Recognit. Lett. 17(4), 335–343 (1996)

    Article  Google Scholar 

  12. Ubbens, T.W., Schuurman, C.: Vision-based obstacle detection using a support vector machine. Electr. Comput. Eng. Can. Conf. IEEE 2009, 459–462 (2009)

    Google Scholar 

  13. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradientbased learning applied to document recognition. Proc. IEEE 86–11, 2278–2324 (1998)

    Article  Google Scholar 

  14. Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems 19. MIT Press. 1(2), 153–160 (2007)

  15. Ranzato, M., Poultney, C., Chopra, S., LeCun, Y.: Efficient learning of sparse representations with an energy-based model. In: NIPS07. MIT Press. 1, 2 (2007)

  16. Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  17. Scharwchter, T., Enzweiler, M., Roth, S., Franke, U.: Efficient multi-cue scene segmentation. In: Proceedings of the German Conference on Pattern Recognition (GCPR), pp. 435–445. (2013)

  18. Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving?, The KITTI vision benchmark suite. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3354–3361. (2012)

  19. Geiger, A., Lenz, P., Stiller, C., et al.: Vision meets robotics: The KITTI Dataset. Int. J. Robot. Res. (2013). doi:10.1177/0278364913491297

Download references

Acknowledgments

This research was supported by the “Strategic Priority Research Program - Network Video Communication and Control” of the Chinese Academy of Sciences (Grant No.XDA06030900), and by the Applications and Demonstrations of New Complex Forms of TV Business (Grant No.2012BAH73F02).

Author information

Authors and Affiliations

  1. University of Science and Technology of China, Hefei, 230026, Anhui, People’s Republic of China

    Baozhi Jia, Weiguo Feng & Ming Zhu

Authors
  1. Baozhi Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Weiguo Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ming Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Baozhi Jia.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jia, B., Feng, W. & Zhu, M. Obstacle detection in single images with deep neural networks. SIViP 10, 1033–1040 (2016). https://doi.org/10.1007/s11760-015-0855-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-015-0855-4

Keywords

Search

Navigation