Visual Hybrid SLAM: An Appearance-Based Approach to Loop Closure

  • Lorenzo Fernández
  • Luis Payá
  • Oscar Reinoso
  • Arturo Gil
  • David Valiente
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 252)

Abstract

This paper proposes an appearance-based method to detect loop closure in visual SLAM (Simultaneous Localization and Mapping). To solve this problem, we make use of omnidirectional images and the internal odometry captured by a robot in a real indoor environment. We build an appearance-based model and, subsequently, two maps of the environment are constructed, one metric and other topological with relationships between them. These relationships are updated in each step of our hybrid approach. The topological map is a graph built from the appearance information in the scenes. A new node is added when the new visual information is different enough from the previous information. At the same time, we check a possible topological loop closure with previous nodes. On the other hand we estimate the metric position of the new pose using a Monte-Carlo approach with the aim of building a metric map. The experimental results demonstrate the reasonable performance of our method.

Keywords

Appearance-base descriptor Omnidirectional Images Monte-Carlo SLAM Hybrid Metric-Topological mapping Loop closure detection 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Amorós, F., Payá, L., Reinoso, Ó., Fernández, L., Marín, J.M.: Visual map building and localization with an appearance-based approach - comparisons of techniques to extract information of panoramic images. In: Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2010, pp. 423–426 (2010)Google Scholar
  2. 2.
    Amorós, F., Payá, L., Reinoso, Ó., Jiménez, L.M.: Comparison of global-appearance techniques applied to visual map building and localization. In: Proceedings of the International Conference on Computer Vision Theory and Applications, VISAPP 2012, pp. 395–398 (2012)Google Scholar
  3. 3.
    Fox, D., Burgard, W., Thrun, S.: Markov localization for mobile robots in dynamic environments. Journal of Artificial Intelligence Research (JAIR) 11, 391–427 (1999)MATHGoogle Scholar
  4. 4.
    Gil, A., Reinoso, O., Ballesta, M., Juliá, M.: Multi-robot visual SLAM using a rao-blackwellized particle filter. Robotics and Autonomous Systems, enviado (2008)Google Scholar
  5. 5.
    Lui, W.L.D., Jarvis, R.: A pure vision-based topological slam system. Int. J. Rob. Res. 31(4), 403–428 (2012)CrossRefGoogle Scholar
  6. 6.
    Lui, W., Jarvis, R.: A pure vision-based approach to topological slam. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3784–3791 (2010)Google Scholar
  7. 7.
    Paya, L., Fernandez, L., Reinoso, O., Gil, A., Ubeda, D.: Appearance-based dense maps creation. comparison of compression techniques with panoramic images. In: Proc. of the Int. Conf. on Informatics in Control, Automation and Robotics, pp. 238–246. INSTICC, Milan (2009)Google Scholar
  8. 8.
    Paya, L., Fernandez, L., Gil, A., Reinoso, O.: Map building and monte carlo localization using global appearance of omnidirectional images. Sensors 10(12), 11468–11497 (2010)CrossRefGoogle Scholar
  9. 9.
    Romero, A., Cazorla, M.: Topological slam using omnidirectional images: Merging feature detectors and graph-matching. In: Blanc-Talon, J., Bone, D., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2010, Part I. LNCS, vol. 6474, pp. 464–475. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  10. 10.
    Seber, G.: Multivariate observations. Wiley Interscience (1984)Google Scholar
  11. 11.
    Thrun, S., Fox, D., Burgard, W., Dellaert, F.: Robust monte carlo localization for mobile robots. Artificial Intelligence 128(1-2), 99–141 (2000)CrossRefGoogle Scholar
  12. 12.
    Tully, S., Kantor, G., Choset, H.: A unified bayesian framework for global localization and slam in hybrid metric/topological maps. Int. J. Rob. Res. 31(3), 271–288 (2012)CrossRefGoogle Scholar
  13. 13.
    Valgren, C., Lilienthal, A.: SIFT, SURF and seasons: Long-term outdoor localization ugin local features. In: Proc. of the 3rd European Conference on Mobile Robots (ECMR), Freiburg, Germany (2007)Google Scholar
  14. 14.
    Valiente, D., Fernandez, L., Aparicio, A.G., Castello, L.P., Garcia, O.R.: Visual odometry through appearance and feature-based method with omnidirectional images. Trans. Rob. 26(6), 1051–1064 (2010)CrossRefGoogle Scholar
  15. 15.
    Zhiwei, L., Xiang, G., Yanyan, C., Songhao, Z.: A novel loop closure detection method in monocular slam. Intell. Serv. Robot. 6(2), 79–87 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Lorenzo Fernández
    • 1
  • Luis Payá
    • 1
  • Oscar Reinoso
    • 1
  • Arturo Gil
    • 1
  • David Valiente
    • 1
  1. 1.Departamento de Ingeniería de Sistemas IndustrialesMiguel Hernández UniversityElche (Alicante)Spain

Personalised recommendations