Growing Regression Forests by Classification: Applications to Object Pose Estimation

  • Kota Hara
  • Rama Chellappa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8690)


In this work, we propose a novel node splitting method for regression trees and incorporate it into the regression forest framework. Unlike traditional binary splitting, where the splitting rule is selected from a predefined set of binary splitting rules via trial-and-error, the proposed node splitting method first finds clusters of the training data which at least locally minimize the empirical loss without considering the input space. Then splitting rules which preserve the found clusters as much as possible are determined by casting the problem into a classification problem. Consequently, our new node splitting method enjoys more freedom in choosing the splitting rules, resulting in more efficient tree structures. In addition to the Euclidean target space, we present a variant which can naturally deal with a circular target space by the proper use of circular statistics. We apply the regression forest employing our node splitting to head pose estimation (Euclidean target space) and car direction estimation (circular target space) and demonstrate that the proposed method significantly outperforms state-of-the-art methods (38.5% and 22.5% error reduction respectively).


Pose Estimation Direction Estimation Regression Tree Random Forest 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Baltieri, D., Vezzani, R., Cucchiara, R.: People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 270–283. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  2. 2.
    Bissacco, A., Yang, M.H., Soatto, S.: Fast Human Pose Estimation using Appearance and Motion via Multi-dimensional Boosting Regression. In: CVPR (2007)Google Scholar
  3. 3.
    Breiman, L.: Random Forests. Machine Learning (2001)Google Scholar
  4. 4.
    Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. Chapman and Hall/CRC (1984)Google Scholar
  5. 5.
    Cao, X., Wei, Y., Wen, F., Sun, J.: Face alignment by Explicit Shape Regression. In: CVPR (2012)Google Scholar
  6. 6.
    Chang, C.C., Lin, C.J.: LIBSVM: A Library for Support Vector Machines. ACM Transactions on Intelligent Systems and Technology (2011)Google Scholar
  7. 7.
    Chou, P.A.: Optimal Partitioning for Classification and Regression Trees. PAMI (1991)Google Scholar
  8. 8.
    Criminisi, A., Shotton, J.: Decision Forests for Computer Vision and Medical Image Analysis. Springer (2013)Google Scholar
  9. 9.
    Criminisi, A., Shotton, J., Robertson, D., Konukoglu, E.: Regression Forests for Efficient Anatomy Detection and Localization in CT Studies. Medical Computer Vision (2010)Google Scholar
  10. 10.
    Dantone, M., Gall, J., Fanelli, G., Van Gool, L.: Real-time Facial Feature Detection using Conditional Regression Forests. In: CVPR (2012)Google Scholar
  11. 11.
    Dobra, A., Gehrke, J.: Secret: A scalable linear regression tree algorithm. In: SIGKDD (2002)Google Scholar
  12. 12.
    Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: A Library for Large Linear Classification. JMLR (2008)Google Scholar
  13. 13.
    Fenzi, M., Leal-Taixé, L., Rosenhahn, B., Ostermann, J.: Class Generative Models based on Feature Regression for Pose Estimation of Object Categories. In: CVPR (2013)Google Scholar
  14. 14.
    Fisher, N.I.: Statistical Analysis of Circular Data. Cambridge University Press (1996)Google Scholar
  15. 15.
    Gaile, G.L., Burt, J.E.: Directional Statistics (Concepts and techniques in modern geography). Geo Abstracts Ltd. (1980)Google Scholar
  16. 16.
    Gourier, N., Hall, D., Crowley, J.L.: Estimating Face Orientation from Robust Detection of Salient Facial Structures. In: ICPRW (2004)Google Scholar
  17. 17.
    Haj, M.A., Gonzàlez, J., Davis, L.S.: On partial least squares in head pose estimation: How to simultaneously deal with misalignment. In: CVPR (2012)Google Scholar
  18. 18.
    Hara, K., Chellappa, R.: Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation. In: CVPR (2013)Google Scholar
  19. 19.
    Herdtweck, C., Curio, C.: Monocular Car Viewpoint Estimation with Circular Regression Forests. In: Intelligent Vehicles Symposium (2013)Google Scholar
  20. 20.
    Huang, C., Ding, X., Fang, C.: Head Pose Estimation Based on Random Forests for Multiclass Classification. In: ICPR (2010)Google Scholar
  21. 21.
    Kashyap, R.L.: A Bayesian Comparison of Different Classes of Dynamic Models Using Empirical Data. IEEE Trans. on Automatic Control (1977)Google Scholar
  22. 22.
    Mardia, K.V., Jupp, P.: Directional Statistics, 2nd edn. John Wiley and Sons Ltd. (2000)Google Scholar
  23. 23.
    Orozco, J., Gong, S., Xiang, T.: Head Pose Classification in Crowded Scenes. In: BMVC (2009)Google Scholar
  24. 24.
    Ozuysal, M., Lepetit, V., Fua, P.: Pose Estimation for Category Specific Multiview Object Localization. In: CVPR (2009)Google Scholar
  25. 25.
    Pelleg, D., Moore, A.: X-means: Extending K-means with Efficient Estimation of the Number of Clusters. In: ICML (2000)Google Scholar
  26. 26.
    Rosipal, R., Trejo, L.J.: Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space. JMLR (2001)Google Scholar
  27. 27.
    Schwarz, G.: Estimating the Dimension of a Model. The Annals of Statistics (1978)Google Scholar
  28. 28.
    Sun, M., Kohli, P., Shotton, J.: Conditional Regression Forests for Human Pose Estimation. In: CVPR (2012)Google Scholar
  29. 29.
    Torgo, L., Gama, J.: Regression by classification. In: Brazilian Symposium on Artificial Intelligence (1996)Google Scholar
  30. 30.
    Torki, M., Elgammal, A.: Regression from local features for viewpoint and pose estimation. In: ICCV (2011)Google Scholar
  31. 31.
    Vapnik, V.: Statistical Learning Theory. Wiley (1998)Google Scholar
  32. 32.
    Weiss, S.M., Indurkhya, N.: Rule-based Machine Learning Methods for Functional Prediction. Journal of Artificial Intelligence Research (1995)Google Scholar
  33. 33.
    Yan, Y., Ricci, E., Subramanian, R., Lanz, O., Sebe, N.: No matter where you are: Flexible graph-guided multi-task learning for multi-view head pose classification under target motion. ICCV (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Kota Hara
    • 1
  • Rama Chellappa
    • 1
  1. 1.Center for Automation ResearchUniversity of MarylandCollege ParkUSA

Personalised recommendations