Advertisement

Clustering Algorithm Exploring Road Geometry in a Video-Based Driver Assistant System

  • Norbert BogyaEmail author
  • Róbert Fazekas
  • Judit Nagy-György
  • Zsolt Vizi
Conference paper
Part of the Mathematics in Industry book series (MATHINDUSTRY, volume 30)

Abstract

In this paper we present two algorithms for an advanced driver assistance system to investigate road geometry. The proposed solutions can handle both simple and complex scenarios, e.g. construction zones. Our input data consists of segments and polygonal paths, whose clustering gives a proper input for a lane model. The presented methods use thresholding and spectral clustering approaches.

Notes

Acknowledgements

This research was supported by the project EFOP-3.6.2-16-2017-00015.

References

  1. 1.
    Chung, F.R.: Spectral graph theory. CBMS Regional Conference Series in Mathematics, vol. 92 (1997)Google Scholar
  2. 2.
    Hall, K.M.: An r-dimensional quadratic placement algorithm. Manag. Sci. Theory Ser. 17(3), 219–229 (1970)CrossRefGoogle Scholar
  3. 3.
    Kelly, A.R., Hancock, E.R.: Grouping-line segments using eigenclustering. In: Proceedings of the British Machine Vision Conference 2000, pp. 1–10 (2000)Google Scholar
  4. 4.
    Koren, Y.: On spectral graph drawing. In: Proceedings of the 9th Annual International Conference on Computing and Combinatorics, COCOON’03, pp. 496–508 (2003)Google Scholar
  5. 5.
    Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: analysis and an algorithm. In: Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic, NIPS’01, pp. 849–856 (2002)Google Scholar
  6. 6.
    Perona, P., Freeman, W.: A factorization approach to grouping. In: Computer Vision ECCV’98. Lecture Notes in Computer Science, vol. 1406 (1998)CrossRefGoogle Scholar
  7. 7.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intel. 22(8), 888–905 (2000)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Norbert Bogya
    • 1
    Email author
  • Róbert Fazekas
    • 2
  • Judit Nagy-György
    • 1
  • Zsolt Vizi
    • 2
  1. 1.University of SzegedBolyai InstituteSzegedHungary
  2. 2.Robert Bosch Kft.BudapestHungary

Personalised recommendations