Advertisement

Learning to Efficiently Detect Repeatable Interest Points in Depth Data

  • Stefan Holzer
  • Jamie Shotton
  • Pushmeet Kohli
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7572)

Abstract

Interest point (IP) detection is an important component of many computer vision methods. While there are a number of methods for detecting IPs in RGB images, modalities such as depth images and range scans have seen relatively little work. In this paper, we approach the IP detection problem from a machine learning viewpoint and formulate it as a regression problem. We learn a regression forest (RF) model that, given an image patch, tells us if there is an IP in the center of the patch. Our RF based method for IP detection allows an easy trade-off between speed and repeatability by adapting the depth and number of trees used for approximating the interest point response maps. The data used for training the RF model is obtained by running state-of-the-art IP detection methods on the depth images. We show further how the IP response map used for training the RF can be specifically designed to increase repeatability by employing 3D models of scenes generated by reconstruction systems such as KinectFusion [1]. Our experiments demonstrate that the use of such data leads to considerably improved IP detection.

Keywords

Random Forest Regression Tree Interest Point Depth Image Depth Data 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Newcombe, R.A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A.J., Kohli, P., Shotton, J., Hodges, S., Fitzgibbon, A.: Kinectfusion: Real-time dense surface mapping and tracking. In: ISMAR (2011)Google Scholar
  2. 2.
    Steder, B., Grisetti, G., Burgard, W.: Robust place recognition for 3D range data based on point features. In: ICRA (2010)Google Scholar
  3. 3.
    Steder, B., Rusu, R.B., Konolige, K., Burgard, W.: Point feature extraction on 3D range scans taking into account object boundaries. In: ICRA (2011)Google Scholar
  4. 4.
    Unnikrishnan, R.: Statistical approaches to multi-scale point cloud processing (2008)Google Scholar
  5. 5.
    Rosten, E., Drummond, T.: Fusing points and lines for high performance tracking. In: ICCV (2005)Google Scholar
  6. 6.
    Rosten, E., Drummond, T.W.: Machine Learning for High-Speed Corner Detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 430–443. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  7. 7.
    Rosten, E., Porter, R., Drummond, T.: Faster and better: A machine learning approach to corner detection. PAMI (2010)Google Scholar
  8. 8.
    Šochman, J., Matas, J.: Learning a Fast Emulator of a Binary Decision Process. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds.) ACCV 2007, Part II. LNCS, vol. 4844, pp. 236–245. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Sochman, J., Matas, J.: Waldboost - learning for time constrained sequential detection. In: CVPR (2005)Google Scholar
  10. 10.
    Schapire, R.E., Singer, Y.: Improved boosting algorithms using confidence-rated predictions. In: Machine Learning, pp. 80–91 (1999)Google Scholar
  11. 11.
    Viola, P., Jones, M.: Fast and robust classification using asymmetric adaboost and a detector cascade. In: Advances in Neural Information Processing System 14, pp. 1311–1318. MIT Press (2001)Google Scholar
  12. 12.
    Foresti, G.: Invariant feature extraction and neural trees for range surface classification. IEEE Transactions on Systems, Man, and Cybernetics (2002)Google Scholar
  13. 13.
    Lepetit, V., Fua, P.: Keypoint recognition using randomized trees. PAMI (2006)Google Scholar
  14. 14.
    Özuysal, M., Calonder, M., Lepetit, V., Fua, P.: Fast keypoint recognition using random ferns. PAMI (2010)Google Scholar
  15. 15.
    Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from a single depth image. In: CVPR (2011)Google Scholar
  16. 16.
    Stückler, J., Behnke, S.: Interest point detection in depth images through scale-space surface analysis. In: ICRA (2011)Google Scholar
  17. 17.
    Gelfand, N., Mitra, N.J., Guibas, L.J., Pottmann, H.: Robust global registration. In: Eurographics Symposium on Geometry Processing (2005)Google Scholar
  18. 18.
    Hinterstoisser, S., Holzer, S., Cagniart, C., Ilic, S., Konolige, K., Navab, N., Lepetit, V.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: ICCV (2011)Google Scholar
  19. 19.
    Criminisi, A., Shotton, J., Konukoglu, E.: Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. In: Foundations and Trends in Computer Graphics and Vision (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Stefan Holzer
    • 1
    • 2
  • Jamie Shotton
    • 2
  • Pushmeet Kohli
    • 2
  1. 1.Department of Computer Science, CAMPTechnische Universität München (TUM)Germany
  2. 2.Microsoft Research CambridgeUK

Personalised recommendations