Advertisement

Machine Vision and Applications

, Volume 27, Issue 6, pp 833–844 | Cite as

Accurate keyframe selection and keypoint tracking for robust visual odometry

  • Marco Fanfani
  • Fabio Bellavia
  • Carlo Colombo
Original Paper

Abstract

This paper presents a novel stereo visual odometry (VO) framework based on structure from motion, where a robust keypoint tracking and matching is combined with an effective keyframe selection strategy. In order to track and find correct feature correspondences a robust loop chain matching scheme on two consecutive stereo pairs is introduced. Keyframe selection is based on the proportion of features with high temporal disparity. This criterion relies on the observation that the error in the pose estimation propagates from the uncertainty of 3D points—higher for distant points, that have low 2D motion. Comparative results based on three VO datasets show that the proposed solution is remarkably effective and robust even for very long path lengths.

Keywords

Visual odometry Structure from motion RANSAC Feature matching Keyframe selection 

Notes

Acknowledgments

This work was supported by the SUONO project (Safe Underwater Operations iN Oceans), SCN_00306, ranked first in the challenge on “Sea Technologies” of the competitive call named “Smart Cities and Communities” issued by the Italian Ministry of Education and Research.

References

  1. 1.
    Badino, H., Yamamoto, A., Kanade, T.: Visual odometry by multi-frame feature integration. In: Proceedings of the International Workshop on Computer Vision for Autonomous Driving at ICCV (2013)Google Scholar
  2. 2.
    Bellavia, F., Fanfani, M., Pazzaglia, F., Colombo, C.: Robust selective stereo SLAM without loop closure and bundle adjustment. In: Proceedings of 17th International Conference on Image Analysis and Processing, ICIAP 2013, pp. 462–471 (2013)Google Scholar
  3. 3.
    Bellavia, F., Tegolo, D., Valenti, C.: Improving Harris corner selection strategy. IET Comput. Vis. 5(2), 87–96 (2011)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Bellavia, F., Tegolo, D., Valenti, C.: Keypoint descriptor matching with context-based orientation estimation. Image Vis. Comput. 32(9), 559–567 (2014)CrossRefGoogle Scholar
  5. 5.
    Cvisic, I., Petrovic, I.: Stereo odometry based on careful feature selection and tracking. In: Proceedings of the European Conference on Mobile Robots ECMR, pp. 1–6 (2015)Google Scholar
  6. 6.
    Davison, A.: Real-time simultaneous localization and mapping with a single camera. In: Proceedings of the 9th IEEE International Conference on Computer Vision, pp. 1403–1410 (2003)Google Scholar
  7. 7.
    Davison, A., Reid, I., Molton, N., Stasse, O.: MonoSLAM: real-time single camera SLAM. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1052–1067 (2007)CrossRefGoogle Scholar
  8. 8.
    Fanfani, M., Bellavia, F., Pazzaglia, F., Colombo, C.: SAMSLAM: simulated annealing monocular SLAM. In: Proceedings of 15th International Conference on Computer Analysis of Images and Patterns, CAIP 2013, pp. 515–522 (2013)Google Scholar
  9. 9.
    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)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proceedings of Computer Vision and Pattern Recognition. URL http://www.cvlibs.net/datasets/kitti/eval_odometry.php (2012)
  11. 11.
    Geiger, A., Ziegler, J., Stiller, C.: StereoScan: Dense 3D reconstruction in real-time. In: IEEE Intelligent Vehicles Symposium (2011)Google Scholar
  12. 12.
    Getreuer, P.: A survey of gaussian convolution algorithms. Image Process. On Line 3, 286–310 (2013)CrossRefGoogle Scholar
  13. 13.
    Hartley, R., Sturm, P.: Triangulation. Comput. Vis. Image Underst. 68(2), 146–157 (1997)CrossRefGoogle Scholar
  14. 14.
    Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)CrossRefzbMATHGoogle Scholar
  15. 15.
    Ho, K., Newman, P.: Detecting loop closure with scene sequences. Int. J. Comput. Vis. 74(3), 261–286 (2007)CrossRefGoogle Scholar
  16. 16.
    Horn, B.K.P.: Closed-form solution of absolute orientation using unit quaternions. J. Opt. Soc. Am. A 4(4), 629–642 (1987)CrossRefGoogle Scholar
  17. 17.
    Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In: Proceedings of the IEEE/ACM International Symposium on Mixed and Augmented Reality, pp. 225–234 (2007)Google Scholar
  18. 18.
    Klein, G., Murray, D.: Improving the agility of keyframe-based SLAM. In: Proceedings of the 10th European Conference on Computer Vision, pp. 802–815 (2008)Google Scholar
  19. 19.
    Lee, G.H., Fraundorfer, F., Pollefeys, M.: RS-SLAM: RANSAC sampling for visual FastSLAM. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1655–1660 (2011)Google Scholar
  20. 20.
    Lim, J., Pollefeys, M., Frahm, J.M.: Online environment mapping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2011)Google Scholar
  21. 21.
    Martull, S., Martorell, M.P., Fukui, K.: Realistic CG Stereo Image Dataset with Ground Truth Disparity Maps. In: Proceedings of the ICPR2012 workshop TrakMark2012, pp. 40–42. URL http://www.cvlab.cs.tsukuba.ac.jp/dataset/tsukubastereo.php (2012)
  22. 22.
    Mei, C., Sibley, G., Cummins, M., Newman, P., Reid, I.: RSLAM: a system for large-scale mapping in constant-time using stereo. Int. J. Comput. Vis. 94, 198–214 (2011)CrossRefGoogle Scholar
  23. 23.
    Montiel, J., Civera, J., Davison, A.: Unified inverse depth parametrization for monocular SLAM. In: Proceedings of Robotics: Science and Systems. IEEE Press (2006)Google Scholar
  24. 24.
    Mouragnon, E., Lhuillier, M., Dhome, M., Dekeyser, F., Sayd, P.: Real time localization and 3D reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 363–370 (2006)Google Scholar
  25. 25.
    Newcombe, R., Lovegrove, S., Davison, A.: DTAM: Dense tracking and mapping in real-time. In: Proceedings of the 13th International Conference on Computer Vision (2011)Google Scholar
  26. 26.
    Nistér, D., Naroditsky, O., Bergen, J.R.: Visual odometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–659 (2004)Google Scholar
  27. 27.
    Paz, L., Piniés, P., Tardós, J., Neira, J.: Large-scale 6-DoF SLAM with stereo-in-hand. IEEE Trans. Robot. 24(5), 946–957 (2008)CrossRefGoogle Scholar
  28. 28.
    Persson, M., Piccini, T., Felsberg, M., Mester, R.: Robust stereo visual odometry from monocular techniques. In: Proceedings of the IEEE Intelligent Vehicles Symposium IV2015, pp. 686–691 (2015)Google Scholar
  29. 29.
    Pretto, A., Menegatti, E., Bennewitz, M., Burgard, W.: A visual odometry framework robust to motion blur. In: Proceedings of the IEEE International Conference on Robotics and Automation (2009)Google Scholar
  30. 30.
    Scaramuzza, D., Fraundorfer, F.: Visual odometry: part I: the first 30 years and fundamentals. IEEE Robot. Autom. Mag. 18(4), 80–92 (2011)CrossRefGoogle Scholar
  31. 31.
    Smith, M., Baldwin, I., Churchill, W., Paul, R., Newman, P.: The new college vision and laser data set. Int. J. Robot. Res 28(5), 595–599. URL http://www.robots.ox.ac.uk/NewCollegeData/ (2009)
  32. 32.
    Strasdat, H., Davison, A.J., Montiel, J.M.M., Konolige, K.: Double window optimisation for constant time visual SLAM. In: Proceedings of the International Conference on Computer Vision, pp. 2352–2359 (2011)Google Scholar
  33. 33.
    Strasdat, H., Montiel, J., Davison, A.: Visual SLAM: why filter? Image Vis. Comput. 30, 65–77 (2012)CrossRefGoogle Scholar
  34. 34.
    Strasdat, H., Montiel, J.M.M., Davison, A.J.: Scale drift-aware large scale monocular SLAM. In: Proceedings of Robotics: Science and Systems (2010)Google Scholar
  35. 35.
    Triggs, B., McLauchlan, P., Hartley, R., Fitzgibbon, A.: Bundle adjustment - a modern synthesis. In: Proceedings of the International Workshop on Vision Algorithms: Theory and Practice, pp. 298–372 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Computational Vision Group (CVG)University of FlorenceFlorenceItaly

Personalised recommendations