The Multi-level Learning and Classification of Multi-class Parts-Based Representations of U.S. Marine Postures

  • Deborah Goshorn
  • Juan Wachs
  • Mathias Kölsch
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5856)


This paper primarily investigates the possibility of using multi-level learning of sparse parts-based representations of US Marine postures in an outside and often crowded environment for training exercises. To do so, the paper discusses two approaches to learning parts-based representations for each posture needed. The first approach uses a two-level learning method which consists of simple clustering of interest patches extracted from a set of training images for each posture, in addition to learning the nonparametric spatial frequency distribution of the clusters that represents one posture type. The second approach uses a two-level learning method which involves convolving interest patches with filters and in addition performing joint boosting on the spatial locations of the first level of learned parts in order to create a global set of parts that the various postures share in representation. Experimental results on video from actual US Marine training exercises are included.


Training Image Interest Point Object Type Learning Module Head Orientation 
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.


  1. 1.
    Ross, D.A., Zemel, R.S.: Learning Parts-Based Representations of Data. J. Mach. Learn. Research 7, 2369–2397 (2006)MathSciNetGoogle Scholar
  2. 2.
    Torralba, A., Murphy, K., Freeman, W.: Sharing visual features for multiclass and multiview object detection. In: IEEE PAMI (2007)Google Scholar
  3. 3.
    Fergus, R., Perona, P., Zisserman, A.: Object recognition by unsupervised scaleinvariant learning. In: CVPR 2003 (2003)Google Scholar
  4. 4.
    FeiFei, L., Fergus, R., Perona, P.: OneShot learning of object categories. In: PAMI 2006 (2006)Google Scholar
  5. 5.
    Leibe, B., Leonardis, A., Schiele, B.: Robust Object Detection with Interleaved Categorization and Segmentation. In: IJCV (2007)Google Scholar
  6. 6.
    Wachs, J.P., Goshorn, D., Kölsch, M.: Recognizing Human Postures and Poses in Monocular Still Images. In: IPCV 2009 (2009)Google Scholar
  7. 7.
    Felzenszwalb, P., McAllester, D., Ramanan, D.: A Discriminatively Trained, Multiscale, Deformable Part Model. In: CVPR 2008 (2008)Google Scholar
  8. 8.
    Harris, C., Stephens, M.J.: A combined corner and edge detector. In: AVC (1988)Google Scholar
  9. 9.
    BASE-IT: Behavior Analysis and Synthesis for Intelligent Training,

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Deborah Goshorn
    • 1
  • Juan Wachs
    • 1
  • Mathias Kölsch
    • 1
  1. 1.MOVES InstituteNaval Postgraduate SchoolMontereyUSA

Personalised recommendations