Advertisement

Improving Robustness of Vision Based Localization Under Dynamic Illumination

  • Jared Le Cras
  • Jonathan Paxman
  • Brad Saracik
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 480)

Abstract

A dynamic light source poses significant challenges to vision based localization algorithms. There are a number of real world scenarios where dynamic illumination may be a factor, yet robustness to dynamic lighting is not demonstrated for most existing algorithms. Localization in dynamically illuminated environments is complicated by static objects casting dynamic shadows. Features may be extracted on both the static objects and their shadows, exacerbating localization error. This work investigates the application of a colour model which separates brightness from chromaticity to eliminate features and matches that may be caused by dynamic illumination. The colour model is applied in two novel ways. Firstly, the chromaticity distortion of a single feature is used to determine if the feature is the result of illumination alone. These features are removed before the feature matching process. Secondly, the chromaticity distortion of features matched between images is examined to determine if the monochrome based algorithm has matched them correctly. The evaluation of the techniques in a Simultaneous Localization and Mapping (SLAM) task show substantial improvements in accuracy and robustness.

Keywords

Scale Invariant Feature Transform Colour Model Feature Match Pixel Colour Localization Path 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    J. Civera, O. Grasa, A. Davison, J. Montiel, 1-Point RANSAC for EKF filtering: application to real-time structure from motion and visual odometry. J. Field Robot. 27(5), 609–631 (2010)CrossRefGoogle Scholar
  2. 2.
    E. Mouragnon, M. Lhuillier, M. Dhome, F. Dekeyser, P. Sayd, Generic and real-time structure from motion using local bundle adjustment. Image Vis. Comput. 27(8), 1178–1193 (2009)CrossRefGoogle Scholar
  3. 3.
    S. Se, D. Lowe, J. Little, in Vision-Based Mobile Robot Localization and Mapping Using Scale-Invariant Features. Proceedings IEEE international conference on robotics and automation, vol. 2 (2001), pp. 2051–2058Google Scholar
  4. 4.
    J. Tardif, Y. Pavlidis, K. Daniilidis, in Monocular Visual Odometry in Urban Environments Using an Omnidirectional Camera. international conference on intelligent robots and systems (2008), pp. 2531–2538Google Scholar
  5. 5.
    J. Wolf, W. Burgard, H. Burkhardt, Robust vision-based localization by combining an image-retrieval system with Monte Carlo localization. IEEE Trans. Rob. 21(2), 208–216 (2005)CrossRefGoogle Scholar
  6. 6.
    D. Lowe, Distinctive Image Features from Scale-Invariant Keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  7. 7.
    E. Rosten, T. Drummond, Machine learning for high-speed corner detection. Lect. Notes Comput. Sci. 3951, 430–443 (2006)CrossRefGoogle Scholar
  8. 8.
    A. Jarosz, in Development of inspection system for evaluation of ore-passes at Grasberg mine, PT freeport, Indonesia. Proceedings of the 21st world mining congress & expo (2008)Google Scholar
  9. 9.
    J. Le Cras, J. Paxman, B. Saracik, A. Jarosz, in An inspection and surveying system for vertical shafts. Proceedings Australasian conference on robotics and automation 2009 (2009)Google Scholar
  10. 10.
    K. Mikolajczyk, C. Schmid, A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)CrossRefGoogle Scholar
  11. 11.
    D. Chekhlov, M. Pupilli, W. Mayol, A. Calway, in Robust Real-Time Visual Slam Using Scale Prediction and Exemplar Based Feature Description. Proceedings of the international conference on computer vision and pattern recognition (2007)Google Scholar
  12. 12.
    M. Swain, D. Ballard, Color indexing. Int. J. Comput. Vision 7(1), 11–31 (1991)CrossRefGoogle Scholar
  13. 13.
    G. Finlayson, S. Chatterjee, B. Funt, in Color Angular Indexing. Proceedings of the 4th European conference on computer vision, vol. 2 (1996), pp. 16–27 Google Scholar
  14. 14.
    J. Geusebroek, R. van den Boomgaard, A. Smeulders, H. Geerts, Color invariance. IEEE Trans. Pattern Anal. Mach. Intell. 23(12), 1338–1350 (2001)CrossRefGoogle Scholar
  15. 15.
    T. Horprasert, D. Harwood, L. Davis, in A Robust Background Subtraction and Shadow Detection. Proceedings of the Asian conference on computer vision (2000)Google Scholar
  16. 16.
    A. Abdel-Hakim, A. Farag, in CSIFT—A SIFT Descriptor with Color Invariant Characteristics. Proceedings of IEEE conference on computer vision and pattern recognition, vol. 2 (2006), pp. 1978–1983Google Scholar
  17. 17.
    G. Burghouts, J. Geusebroek, Performance evaluation of local colour invariants. Comput. Vis. Image Underst. 113, 48–62 (2009)CrossRefGoogle Scholar
  18. 18.
    G. Silveira, E. Malis, in Real Time Visual Tracking Under Arbitrary Illumination Changes. Proceedings of the 2007 IEEE conference on computer vision and pattern recognition (2007) pp. 1–6Google Scholar
  19. 19.
    G. Silveira, E. Malis, P. Rives, An efficient direct approach to visual slam. IEEE Trans. Rob. 24(5), 969–979 (2008)CrossRefGoogle Scholar
  20. 20.
    H. Bischof, H. Wildenauer, A. Leonardis, Illumination insensitive recognition using eigenspaces. Comput. Vis. Image Underst. 95, 86–104 (2004)CrossRefGoogle Scholar
  21. 21.
    G. Steinbauer, H. Bischof, Illumination insensitive robot self-localization using panoramic eigenspaces. Lect. Notes Comput. Sci. 3276, 84–96 (2005)CrossRefGoogle Scholar
  22. 22.
    A. Sunghwan, C. Jinwoo, C. Minyong, C. Wan Kyun, in Metric Slam in Home Environment with Visual Objects and Sonar Features. Proceedings of the 2006 IEEE international conference on intelligent robots and systems (2006), pp. 4048–4053Google Scholar
  23. 23.
    A. SungHwan, C. Jinwoo, D. Nakju Lett, C. Wan Kyun, A practical approach for EKF-SLAM in an indoor environment: fusing ultrasonic sensors and stereo camera. Auton. Robots 24(3), 315–335 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Curtin UniversityBentleyAustralia

Personalised recommendations