Omnidirectional Localization in vSLAM with Uncertainty Propagation and Bayesian Regression

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10617)


This article presents a visual localization technique based solely on the use of omnidirectional images, within the framework of mobile robotics. The proposal makes use of the epipolar constraint, adapted to the omnidirectional reference, in order to deal with matching point detection, which ultimately determines a motion transformation for localizing the robot. The principal contributions lay on the propagation of the current uncertainty to the matching. Besides, a Bayesian regression technique is also implemented, in order te reinforce the robustness. As a result, we provide a reliable adaptive matching, which proves its stability and consistency against non-linear and dynamic effects affecting the image frame, and consequently the final application. In particular, the search for matching points is highly reduced, thus aiding in the search and avoiding false correspondes. The final outcome is reflected by real data experiments, which confirm the benefit of these contributions, and also test the suitability of the localization when it is embedded on a vSLAM application.


Omnidirectional images Visual SLAM Feature matching Visual localization 


  1. 1.
    Bay, H., Tuytelaars, T., Van Gool, L.: Speeded up robust features. Comput. Vis. Image Underst. 110, 346–359 (2008)CrossRefGoogle Scholar
  2. 2.
    Brand, C., Schuster, M.J., Hirschmller, H., Suppa, M.: Submap matching for stereo-vision based indoor/outdoor slam. In: IEEE IROS, pp. 5670–5677 (2015)Google Scholar
  3. 3.
    Brown, M.Z., Burschka, D., Hager, G.D.: Advances in computational stereo. IEEE Trans. PAMI 25(8), 993–1008 (2003)CrossRefGoogle Scholar
  4. 4.
    Caruso, D., Engel, J., Cremers, D.: Large-scale direct slam for omni directional cameras. In: IEEE IROS, pp. 141–148 (2015)Google Scholar
  5. 5.
    Davison, A.J.: Real-time simultaneous localisation and mapping with a single camera. In: ICCV, vol. 2, pp. 1403–1410, France (2003)Google Scholar
  6. 6.
    Engel, J., Stuckler, J., Cremers, D.: Large-scale direct slam with stereo cameras. In: IEEE IROS, pp. 1935–1942 (2015)Google Scholar
  7. 7.
    Ghaffari Jadidi, M., Valls Miro, J., Valencia, R., Andrade-Cetto, J.: Exploration on continuous Gaussian process frontier maps. In: IEEE ICRA, pp. 6077–6082, China (2014)Google Scholar
  8. 8.
    Gil, A., Reinoso, O., Ballesta, M., Juliá, M., Payá, L.: Estimation of visual maps with a robot network equipped with vision sensors. Sensors 10, 5209–5232 (2010)CrossRefGoogle Scholar
  9. 9.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2004)CrossRefzbMATHGoogle Scholar
  10. 10.
    Huang, S., Dissanayake, G.: Convergence and consistency analysis for extended Kalman filter based slam. IEEE Trans. Rob. 23(5), 1036–1049 (2007)CrossRefGoogle Scholar
  11. 11.
    Joly, C., Rives, P.: Bearing-only SAM using a minimal inverse depth parametrization. In: ICINCO, vol. 2, pp. 281–288 (2010)Google Scholar
  12. 12.
    Kulback, S., Leiber, R.A.: On information and sufficiency. Ann. Math. Stat. 22, 79–86 (1951)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Lee, S.J., Song, J.B.: A new sonar salient feature structure for EKF-based slam. In: IEEE IROS, pp. 5966–5971 (2010)Google Scholar
  14. 14.
    Leung, C., Huang, S., Dissanayake, G.: Active slam in structured environments. In: IEEE ICRA, pp. 1898–1903 (2008)Google Scholar
  15. 15.
    Longuet-Higgins, H.C.: A computer algorithm for reconstructing a scene from two projections. Nature 293(5828), 133–135 (1985)CrossRefGoogle Scholar
  16. 16.
    Paya, L., Amoros, F., Fernandez, L., Reinoso, O.: Performance of global-appearance descriptors in map building and localization using omnidirectional vision. Sensors 14, 3033–3064 (2014)CrossRefGoogle Scholar
  17. 17.
    Rasmussen, C.E., Williams, C.K.I.: Gaussian processes for machine learning. In: Adaptive Computation and Machine Learning series. Massachusetts Institute of Technology (2006)Google Scholar
  18. 18.
    Scaramuzza, D., Martinelli, A., Siegwart, R.: A toolbox for easily calibrating omni directional cameras. In: IEEE IROS, pp. 5695–5701, China (2006)Google Scholar
  19. 19.
    Servos, J., Smart, M., Waslander, S.: Underwater stereo slam with refraction correction. In: IEEE IROS, pp. 3350–3355 (2013)Google Scholar
  20. 20.
    Shuang, Y., Baoyuan, C., Lei, Z., Xiaoyang, Y., Haibin, W., Jixun, Z., Deyun, C.: Encoded light image active feature matching approach in binocular stereo vision. In: IFOST, pp. 406–409 (2016)Google Scholar
  21. 21.
    Valiente, D., Gil, A., Fernandez, L., Reinoso, O.: A modified stochastic gradient descent algorithm for view-based slam using omnidirectional images. Inf. Sci. 279, 326–337 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Systems Engineering and Automation DepartmentMiguel Hernández UniversityElcheSpain

Personalised recommendations