Efficient Object Detection Using Orthogonal NMF Descriptor Hierarchies

  • Thomas Mauthner
  • Stefan Kluckner
  • Peter M. Roth
  • Horst Bischof
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6376)


Recently descriptors based on Histograms of Oriented Gradients (HOG) and Local Binary Patterns (LBP) have shown excellent results in object detection considering the precision as well as the recall. However, since these descriptors are based on high dimensional representations such approaches suffer from enormous memory and runtime requirements. The goal of this paper is to overcome these problems by introducing hierarchies of orthogonal Non-negative Matrix Factorizations (NMF). In fact, in this way a lower dimensional feature representation can be obtained without loosing the discriminative power of the original features. Moreover, the hierarchical structure allows to represent parts of patches on different scales allowing for a more robust classification. We show the effectiveness of our approach for two publicly available datasets and compare it to existing state-of-the-art methods. In addition, we demonstrate it in context of aerial imagery, where high dimensional images have to be processed requiring efficient methods.


Object Detection Local Binary Pattern Nonnegative Matrix Factorization Aerial Image Equal Error Rate 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gall, J., Lempitsky, V.: Class-specific hough forests for object detection. In: Proc. CVPR (2009)Google Scholar
  2. 2.
    Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. Int’l. Journal of Computer Vision 77(1-3), 259–289 (2008)CrossRefGoogle Scholar
  3. 3.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR (2005)Google Scholar
  4. 4.
    Viola, P., Jones, M.J., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: Proc. ICCV (2003)Google Scholar
  5. 5.
    Wang, X., Han, T.X., Yan, S.: An HOG-LBP human detector with partial occlusion handling. In: Proc. ICCV (2009)Google Scholar
  6. 6.
    Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: Proc. CVPR (2008)Google Scholar
  7. 7.
    Zhu, Q., Yeh, M.C., Cheng, K.T., Avidan, S.: Fast human detection using a cascade of histograms of oriented gradients. In: Proc. CVPR (2006)Google Scholar
  8. 8.
    Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: Proc. CVPR (2008)Google Scholar
  9. 9.
    Lampert, C., Blaschko, M., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: Proc. CVPR (2008)Google Scholar
  10. 10.
    Ommer, B., Malik, J.: Multi-scale detection by clustering lines. In: Proc. ICCV (2009)Google Scholar
  11. 11.
    Maji, S., Malik, J.: Object detection using a max-margin hough transform. In: Proc. CVPR (2009)Google Scholar
  12. 12.
    Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. In: Advances in NIPS, pp. 556–562 (2001)Google Scholar
  13. 13.
    Agarwal, A., Triggs, B.: A local basis representation for estimating human pose from cluttered images. In: Narayanan, P.J., Nayar, S.K., Shum, H.-Y. (eds.) ACCV 2006. LNCS, vol. 3851, pp. 50–59. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    Thurau, C., Hlaváč, V.: Pose primitive based human action recognition in videos or still images. In: Proc. CVPR (2008)Google Scholar
  15. 15.
    Ikizler-Cinbis, N., Cinbis, R.G., Sclaroff, S.: Learning actions from the web. In: Proc. ICCV (2009)Google Scholar
  16. 16.
    Cheriyadat, A.M., Radke, R.J.: Non-negative matrix factorization of partial track data for motion segmentation. In: Proc. ICCV (2009)Google Scholar
  17. 17.
    Ding, C., Li, T., Peng, W., Park, H.: Orthogonal nonnegative matrix tri-factorizations for clustering. In: Proc. Int’l. Conf. on Knowledge Discovery and Data Mining, pp. 126–135 (2006)Google Scholar
  18. 18.
    Yoo, J., Choi, S.: Orthogonal nonnegative matrix factorization: Multiplicative updates on stiefel manifolds. In: Fyfe, C., Kim, D., Lee, S.-Y., Yin, H. (eds.) IDEAL 2008. LNCS, vol. 5326, pp. 140–147. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  19. 19.
    Stiefel, E.: Richtungsfelder und Fernparallelismus in n-dimensionalen Mannigfaltigkeiten. Commentarii Mathematici Helvetici 9(1), 305–353 (1935)CrossRefMathSciNetGoogle Scholar
  20. 20.
    Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: Proc. ICCV (2007)Google Scholar
  21. 21.
    Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE Trans. PAMI 26(11), 1475–1490 (2004)Google Scholar
  22. 22.
    Andriluka, M., Roth, S., Schiele, B.: People-tracking-by-detection and people-detection-by-tracking. In: Proc. CVPR (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Thomas Mauthner
    • 1
  • Stefan Kluckner
    • 1
  • Peter M. Roth
    • 1
  • Horst Bischof
    • 1
  1. 1.Institute for Computer Graphics and VisionGraz University of TechnologyAustria

Personalised recommendations