Generalized Preemptive RANSAC - Making Preemptive RANSAC Feasible even in Low Resources Devices

Severino Gomes-Neto, Bruno M. Carvalho

Abstract

This paper examines a generalized version of Preemptive RANSAC for visual motion estimation. The approach described employs the BRUMA function for dealing with varying block sizes and the percentages of hypotheses to be removed during the hypotheses rejection phase. The generation of a flexible number of hypotheses is also performed in order to balance the preemption scheme. Experiments were performed for both forward and side-wise motions in synthetic environment by using simulation and the ground-truth used to compare the Standard Preemptive RANSAC and its generalized version. Simulations confirmed that the quality of the results produced by the Standard Preemptive RANSAC degrade as the hardware resources used are decreased, as opposed to the results produced by the Generalized Preemptive RANSAC, with the results of the Standard Preemptive RANSAC having errors up to eleven times larger than the Generalized Preemptive RANSAC.

References

  1. Chum, O. and Matas, J. (2005). Matching with PROSAC - Progressive Sample Consensus. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01, CVPR 7805, pages 220-226, Washington, DC, USA. IEEE Computer Society.
  2. Chum, O. and Matas, J. (2008). Optimal Randomized RANSAC. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(8):1472-1482.
  3. Fischler, M. A. and Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM, 24(6):381-395.
  4. Gomes-Neto, S. and Carvalho, B. M. d. (2010). BRUMA: Generalizing All Preemption Functions. In Proc. IWSSIP, pages 380-383.
  5. Konouchine, A., Gaganov, V., and Veznevets, V. (2005). AMLESAC: A New Maximum Likelihood Robust Estimator. In In Proc. Graphicon05, pages 93-100.
  6. Li, H. and Hartley, R. (2006). Five-Point Motion Estimation Made Easy. In Proceedings of the 18th International Conference on Pattern Recognition - Volume 01, ICPR 7806, pages 630-633, Washington, DC, USA. IEEE Computer Society.
  7. Michaelsen, E., von Hansen, W., Meidow, J., Kirchhof, M., and Stilla, U. (2006). Estimating The Essential Matrix: GOODSAC versus RANSAC. In Symposium of ISPRS Commission III: Photogrammetric Computer Vision, pages 161-166.
  8. Nistér, D. (2003). Preemptive RANSAC for Live Structure and Motion Estimation. In Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2, ICCV 7803, pages 199-, Washington, DC, USA. IEEE Computer Society.
  9. Nistér, D. (2004). An Efficient Solution to the Five-Point Relative Pose Problem. IEEE Trans. Pattern Anal. Mach. Intell., 26(6):756-777.
  10. Raguram, R., Frahm, J.-M., and Pollefeys, M. (2008). A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus. In Forsyth, D., Torr, P., and Zisserman, A., editors, Computer Vision ECCV 2008, volume 5303 of Lecture Notes in Computer Science, pages 500-513. Springer Berlin Heidelberg.
  11. Rodehorst, V. and Hellwich, O. (2006). Genetic Algorithm SAmple Consensus (gasac) - A Parallel Strategy for Robust Parameter Estimation. In Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop, CVPRW 7806, pages 103-, Washington, DC, USA. IEEE Computer Society.
  12. Torr, P. H. S. and Zisserman, A. (2000). MLESAC: A New Robust Estimator with Application to Estimating Image Geometry. Computer Vision and Image Understanding, 78:2000.
  13. Vedaldi, A., Jin, H., Favaro, P., and Soatto, S. (2005). KALMANSAC: Robust Filtering by Consensus. In ICCV, pages 633-640. IEEE Computer Society.
  14. S?egvic, S., Schweighofer, G., and Pinz, A. (2007a). Influence of numerical conditioning on the accuracy of relative orientation. In CVPR. IEEE Computer Society.
  15. S?egvic, S., Schweighofer, G., and Pinz, A. (2007b). Performance evaluation of the five-point relative pose with emphasis on planar scenes. In Performance Evaluation for Computer Vision, pages 33-40, Austria. Workshop of the Austrian Association for Pattern Recognition.
Download


Paper Citation


in Harvard Style

Gomes-Neto S. and M. Carvalho B. (2014). Generalized Preemptive RANSAC - Making Preemptive RANSAC Feasible even in Low Resources Devices . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 406-415. DOI: 10.5220/0004737004060415


in Bibtex Style

@conference{visapp14,
author={Severino Gomes-Neto and Bruno M. Carvalho},
title={Generalized Preemptive RANSAC - Making Preemptive RANSAC Feasible even in Low Resources Devices},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={406-415},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004737004060415},
isbn={978-989-758-009-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - Generalized Preemptive RANSAC - Making Preemptive RANSAC Feasible even in Low Resources Devices
SN - 978-989-758-009-3
AU - Gomes-Neto S.
AU - M. Carvalho B.
PY - 2014
SP - 406
EP - 415
DO - 10.5220/0004737004060415