Modeling Pose/Appearance Relations for Improved Object Localization and Pose Estimation in 2D images

  • Damien Teney
  • Justus Piater
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7887)

Abstract

We propose a multiview model of appearance of objects that explicitly represents their variations of appearance with respect to their 3D pose. This results in a probabilistic, generative model capable of precisely synthesizing novel views of the learned object in arbitrary poses, not limited to the discrete set of trained viewpoints. We show how to use this model on the task of localization and full pose estimation in 2D images, which benefits from its particular capabilities in two ways. First, the generative model is used to improve the precision of the pose estimate much beyond nearest-neighbour matching with training views. Second, the pose/appearance relations stored within the model are used to resolve ambiguous test cases (e.g. an object facing towards/away from the camera). Here, changes of appearance as a function of incremental pose changes are detected in the test scene, using a pair or triple of views, and are then matched with those stored in the model. We demonstrate the effectiveness of this method on several datasets of very different nature, and show results superior to state-of-the-art methods in terms of accuracy. The pose estimation of textureless objects in cluttered scenes also benefits from the proposed contributions.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Avidan, S., Shashua, A.: Novel view synthesis in tensor space. In: CVPR (1997)Google Scholar
  2. 2.
    Chen, S.E., Williams, L.: View interpolation for image synthesis. In: SIGGRAPH (1993)Google Scholar
  3. 3.
    Chen, S., Li, Y., Kwok, N.M.: Active vision in robotic systems: A survey of recent developments. Int. J. of Rob. Res. 30(11), 1343–1377 (2011)CrossRefGoogle Scholar
  4. 4.
    Johansson, B., Moe, A.: Patch-duplets for object recognition and pose estimation. In: CRV (2005)Google Scholar
  5. 5.
    Kushal, A., Schmid, C., Ponce, J.: Flexible object models for category-level 3D object recognition. In: CVPR (2007)Google Scholar
  6. 6.
    Liu, C.: Beyond Pixels: Exploring New Representations and Applications for Motion Analysis. Ph.D. thesis. MIT (2009)Google Scholar
  7. 7.
    Martinez Torres, M., Collet Romea, A., Srinivasa, S.: MOPED: A scalable and low latency object recognition and pose estimation system. In: ICRA (2010)Google Scholar
  8. 8.
    Ozuysal, M., Lepetit, V., Fua, P.: Pose estimation for category specific multiview object localization. In: CVPR (2009)Google Scholar
  9. 9.
    Savarese, S., Fei-Fei, L.: View synthesis for recognizing unseen poses of object classes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 602–615. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  10. 10.
    Savarese, S., Fei-Fei, L.: 3D generic object categorization, localization and pose estimation. In: IEEE Int. Conf. on Comp. Vis. (2007)Google Scholar
  11. 11.
    Seitz, S.M., Dyer, C.R.: Toward image-based scene representation using view morphing. In: Int. Conf. on Patt. Rec., pp. 84–89 (1996)Google Scholar
  12. 12.
    Sipe, M.A., Casasent, D.: Best viewpoints for active vision classification and pose estimation. In: Intelligent Robots and Comp. Vis., pp. 382–393 (1997)Google Scholar
  13. 13.
    Sun, M., Su, H., Savarese, S., Fei-Fei, L.: A multi-view probabilistic model for 3D object classes. In: CVPR (2009)Google Scholar
  14. 14.
    Teney, D., Piater, J.: Generalized Exemplar-Based Full Pose Estimation from 2D Images without Correspondences. In: DICTA (2012)Google Scholar
  15. 15.
    Teney, D., Piater, J.: Continuous pose estimation in 2D images at instance and category levels (submitted, 2013)Google Scholar
  16. 16.
    Thomas, A., Ferrari, V., Leibe, B., Tuytelaars, T., Schiel, B., Van Gool, L.: Towards multi-view object class detection. In: CVPR (2006)Google Scholar
  17. 17.
    Torki, M., Elgammal, A.M.: Regression from local features for viewpoint and pose estimation. In: ICCV (2011)Google Scholar
  18. 18.
    Vikstén, F., Soderberg, R., Nordberg, K., Perwass, C.: Increasing pose estimation performance using multi-cue integration. In: ICRA (2006)Google Scholar
  19. 19.
    Vikstén, F., Forssén, P.E., Johansson, B., Moe, A.: Comparison of local image descriptors for full 6 degree-of-freedom pose estimation. In: ICRA (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Damien Teney
    • 1
  • Justus Piater
    • 2
  1. 1.University of LiègeBelgium
  2. 2.University of InnsbruckAustria

Personalised recommendations