Skip to main content
SpringerLink
Log in

Stereo-Matching in the Context of Vision-Augmented Vehicles

  • Conference paper
  • First Online:
Advances in Visual Computing (ISVC 2015)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 9475))

Included in the following conference series:

Abstract

Stereo matching accuracy is determined by comparing results with ground truth. However, the kind of detail remains unspecified in regions where a stereo matcher is more accurate. By identifying feature points we are identifying regions where the data cost used can easily represent features. We suggest to use feature matchers for identifying sparse matches of high confidence, and to use those for guiding a belief-propagation mechanism.

Extensive experiments, also including a semi-global stereo matcher, illustrate achieved performance. We also test on data just recently made available for a developing country, which comes with particular challenges not seen before. Since KITTI ground truth is sparse, for most of identified feature points ground truth is actually missing. By using our novel stereo matching method (called FlinBPM) we derive our own ground truth and compare it with results obtained by other matching approaches including our novel stereo matching method (called WlinBPM).

Based on this we were able to identify circumstances in which a census transform fails to define an appropriate data cost measure. There is not a single all-time winner in the set of considered stereo matchers, but there are specific benefits when applying one of the discussed stereo matching strategies. This might point towards a need of adaptive solutions for vision-augmented vehicles.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    On \(28^{th}\) August, 2015 our stereo matcher WlinBPM ranked \(46^{th}\) at [5] compared to linBPM and iSGM which ranked \(57^{th}\) and \(32^{nd}\), respectively.

  2. 2.

    Authors acknowledge the support by Mick Jays, Ian Armstrong and Jeff Echano for allowing overnight access to multiple computers for this sequence.

References

  1. CCSAD dataset. CIMAT, Guanajuato, http://camaron.cimat.mx/Personal/jbhayet/ccsad-dataset (2015)

  2. Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. Int. J. Comput. Vision 70, 41–54 (2006)

    Article  Google Scholar 

  3. Fischler, M.A., Bolles, C.R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. J. Comm. ACM 24, 381–395 (1981)

    Article  MathSciNet  Google Scholar 

  4. Franke, U., Joos, A.: Real-time stereo vision for urban traffic scene understanding. In: Proceedings of IEEE Symposium on Intelligent Vehicles, pp. 273–278 (2000)

    Google Scholar 

  5. Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving?. The KITTI Vision benchmark suite. In: Proceedings of IEEE International Conference on Computer Vision Pattern Recognition (2012)

    Google Scholar 

  6. Hermann, S., Klette, R.: Iterative semi-global matching for robust driver assistance systems. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part III. LNCS, vol. 7726, pp. 465–478. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  7. Hirschmüller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: Proceedings of IEEE International Conference on Computer Vision Pattern Recognition, vol. 2, pp. 807–814 (2005)

    Google Scholar 

  8. Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Proceedings IEEE Conference on Computer Vision Pattern Recognition (2015)

    Google Scholar 

  9. Khan, W., Suaste, V., Caudillo, D., Klette, R.: Belief propagation stereo matching compared to iSGM on binocular or trinocular video data. In: Proceedings of IEEE Symposium on Intelligent Vehicles (2013)

    Google Scholar 

  10. Khan, W., Klette, R.: Stereo accuracy for collision avoidance for varying collision trajectories. In: Proceedings of IEEE Symposium on Intelligent Vehicles (2013)

    Google Scholar 

  11. Klette, R.: Concise Computer Vision. Springer, London (2014)

    Book  MATH  Google Scholar 

  12. Park, S., Jeong, H.: A fast and parallel belief computation structure for stereo matching. In: Proceedings of IASTED European Conference on Internet Multimedia Systems Applications, pp. 284–289 (2007)

    Google Scholar 

  13. Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Computer Vision 47, 7–42 (2002)

    Article  MATH  Google Scholar 

  14. Stein, F.J.: Efficient computation of optical flow using the census transform. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 79–86. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Business and Information Technology, Petone Campus, Wellington Institute of Technology, Wellington, New Zealand

    Waqar Khan

  2. EEE Department, School of Engineering, Auckland University of Technology, Auckland, New Zealand

    Reinhard Klette

Authors
  1. Waqar Khan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Reinhard Klette
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Waqar Khan .

Editor information

Editors and Affiliations

  1. University of Nevada, Reno, Nevada, USA

    George Bebis

  2. NASA Ames Research Center, Moffett Field, California, USA

    Richard Boyle

  3. Lawrence Berkeley National Laboratory, Berkeley, California, USA

    Bahram Parvin

  4. Desert Research Institute, Reno, Nevada, USA

    Darko Koracin

  5. University of Houston, Houston, Texas, USA

    Ioannis Pavlidis

  6. IBM T.J. Watson Research Center, Yorktown Heights, New York, USA

    Rogerio Feris

  7. Purdue University, West Lafayette, Indiana, USA

    Tim McGraw

  8. Side Effects Software, Santa Monica, California, USA

    Mark Elendt

  9. The DiVE, Durham, North Carolina, USA

    Regis Kopper

  10. Texas A&M University, College Station, Texas, USA

    Eric Ragan

  11. Kent State University, Kent, Ohio, USA

    Zhao Ye

  12. Lawrence Berkeley National Laboratory, Berkeley, California, USA

    Gunther Weber

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Khan, W., Klette, R. (2015). Stereo-Matching in the Context of Vision-Augmented Vehicles. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2015. Lecture Notes in Computer Science(), vol 9475. Springer, Cham. https://doi.org/10.1007/978-3-319-27863-6_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-27863-6_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-27862-9

  • Online ISBN: 978-3-319-27863-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation