Skip to main content
Log in

FestGPU: a framework for fast robust estimation on GPU

  • Original Research Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

Robust estimation is used in a wide range of applications. One of the most popular algorithms for robust estimation is the random sample consensus (ransac) that achieves a high degree of accuracy even with a significant amount of outliers. A major drawback of ransac is the fast increasing number of iterations caused by higher outlier ratios, resulting in increasing computational costs. In this paper FestGPU, a framework for Fast robust ESTimation on GPU, is presented which reaches a speedup of up to 135\(\times\) compared to a singlecore CPU. Together with a C++ and a Matlab interface the framework is made publicly available on the authors’ website for the research community.

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

Access this article

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
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Babenko, P., Shah, M.: MinGPU: a minimum GPU library for computer vision. J. Real-Time Image Process. 3(4), 255–268 (2008)

    Article  Google Scholar 

  2. Barreto, J., Daniilidis, K.: Fundamental matrix for cameras with radial distortion. In: Proceedings of IEEE Int. Conf. on Computer Vision, vol. 1, pp. 625–632 (2005)

  3. Brito, J., Angst, R., Köser, K., Zach, C., Branco, P., Ferreira, M., Pollefeys, M.: Unknown radial distortion centers in multiple view geometry problems. Computer Vision—ACCV. LNCS, vol. 7727, pp. 136–149. Springer, Berlin, Heidelberg (2012)

  4. Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011)

    Article  Google Scholar 

  5. Choi, S., Kim, T., Yu, W.: Performance evaluation of RANSAC family. In: Proceedings of the British Machine Vision Conf., pp. 1–12 (2009)

  6. Chum, O., Matas, J.: Matching with PROSAC—progressive sample consensus. In: Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 220–226 (2005)

  7. Cornelis, N., Van Gool, L.: Fast scale invariant feature detection and matching on programmable graphics hardware. In: Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition (Workshops), pp. 1–8 (2008)

  8. Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)

    Article  MathSciNet  Google Scholar 

  9. Frahm, J.M., Pollefeys, M.: RANSAC for (quasi-)degenerate data (QDEGSAC). In: Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition 1, 453–460 (2006)

  10. Fung, J., Mann, S.: OpenVIDIA: Parallel GPU computer vision. In: Proceedings of the 13th Annual ACM Int. Conf. on Multimedia, pp. 849–852 (2005)

  11. Hartley, R.I.: In defense of the eight-point algorithm. IEEE Trans. Pattern Anal. Mach. Intell. 19(6), 580–593 (1997)

    Article  Google Scholar 

  12. Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)

  13. Havel, J., Dubská, M., Herout, A., Jošth, R.: Real-time detection of lines using parallel coordinates and CUDA. J. Real- Time Image Process. 9(1), 205–216 (2014)

    Article  Google Scholar 

  14. Ko, Y., Yi, Y., Ha, S.: An efficient parallelization technique for x264 encoder on heterogeneous platforms consisting of CPUs and GPUs. J. Real- Time Image Process. 9(1), 5–18 (2014)

    Article  Google Scholar 

  15. Marsaglia, G., Zaman, A.: A new class of random number generators. Ann. Appl. Prob. 1(3), 462–480 (1991)

    Article  MATH  MathSciNet  Google Scholar 

  16. Michaelsen, E., Hansen, W.V., Meidow, J., Kirchhof, M., Stilla, U.: Estimating the essential matrix: GOODSAC versus RANSAC. In: Symposium on Photogrammetric Computer Vision (2006)

  17. Montañés Laborda, M., Torres Moreno, E., Martínez del Rincón, J., Herrero Jaraba, J.: Real-time GPU color-based segmentation of football players. J. Real-Time Image Process. 7(4), 267–279 (2012)

    Article  Google Scholar 

  18. NVIDIA: CUDA C Programming Guide (Version 5.5) (2013)

  19. Pharr, M., Fernando, R. (eds.): GPU Gems 2: Programming Techniques for High-Performance Graphics and General-Purpose Computation. Addison-Wesley, London (2005)

  20. Roters, J., Jiang, X.: FestGPU: a framework for Fast robust ESTimation on GPU. http://cvpr.uni-muenster.de/research/gpu-estimation

  21. Roters, J., Jiang, X.: Incremental dense reconstruction from sparse 3D points with an integrated level-of-detail concept. In: Jiang, X., Bellon, O.R.P., Goldgof, D., Oishi, T. (eds.) Advances in Depth Image Analysis and Applications, LNCS, vol. 7854, pp. 116–125. Springer, Berlin Heidelberg (2013)

    Chapter  Google Scholar 

  22. Roters, J., Steinicke, F., Hinrichs, K.H.: Quasi-real-time 3D reconstruction from low-altitude aerial images. In: Zlatanova, S.,Ledoux, H., Fendel, E., Rumor, M. (eds.) Proceedings of the 28th Urban Data Management Symposium, pp. 231–241 (2011)

  23. Rousseeuw, P.J.: Least median of squares regression. J. Am. Stat. Assoc. 79(388), 871–880 (1984)

    Article  MATH  MathSciNet  Google Scholar 

  24. Stewart, C.V.: Robust parameter estimation in computer vision. SIAM Rev. 41, 513–537 (1999)

    Article  MATH  MathSciNet  Google Scholar 

  25. Terriberry, T., French, L., Helmsen, J.: GPU accelerating speeded-up robust features. In: Proceedings of the 4th Int. Symposium on 3D Data Processing, Visualization and Transmission, pp. 355–362 (2008)

  26. Torr, P.H.S.: Bayesian model estimation and selection for epipolar geometry and generic manifold fitting. Int. J. Computer Vis. 50(1), 35–61 (2002)

    Article  MATH  Google Scholar 

  27. Torr, P.H.S., Zisserman, A.: MLESAC: a new robust estimator with application to estimating image geometry. Computer Vis. Image Underst. 78, 138–156 (2000)

    Article  Google Scholar 

  28. Winker, P., Lyra, M., Sharpe, C.: Least median of squares estimation by optimization heuristics with an application to the CAPM and a multi-factor model. Comput. Manag. Sci. 8(1), 103–123 (2011)

    Article  MathSciNet  Google Scholar 

  29. Wu, C., Agarwal, S., Curless, B., Seitz, S.M.: Multicore bundle adjustment. In: Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 3057–3064 (2011)

Download references

Acknowledgments

This work was developed in the project AVIGLE funded by the State of North Rhine Westphalia (NRW), Germany, and the European Union, European Regional Development Fund “Europe—Investing in your future“. AVIGLE was conducted in cooperation with several industrial and academic partners. We thank all the project partners for their work and contributions to the project. Furthermore, we thank Cenalo GmbH for the image acquisition.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jan Roters.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Roters, J., Jiang, X. FestGPU: a framework for fast robust estimation on GPU. J Real-Time Image Proc 13, 759–772 (2017). https://doi.org/10.1007/s11554-014-0439-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-014-0439-5

Keywords

Navigation