Unsupervised Discovery of Structure in Activity Data Using Multiple Eigenspaces

  • Tâm Huỳnh
  • Bernt Schiele
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3987)


In this paper we propose a novel scheme for unsupervised detection of structure in activity data. Our method is based upon an algorithm that represents data in terms of multiple low-dimensional eigenspaces. We describe the algorithm and propose an extension that allows to handle multiple time scales. The validity of the approach is demonstrated on several data sets and using two types of acceleration features. Finally, we report on experiments that indicate that our approach can yield recognition rates comparable to other, supervised approaches.


Activity Recognition Reconstruction Error Inertial Sensor Acceleration Data Segment Size 
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.
    Philipose, M., Fishkin, K.P., Perkowitz, M., Patterson, D.J., Hahnel, D., Fox, D., Kautz, H.: Inferring Activities from Interactions with Objects. In: IEEE Pervasive Computing: Mobile and Ubiquitous Systems, vol. 3, pp. 50–57. IEEE, Los Alamitos (2004)Google Scholar
  2. 2.
    Bao, L., Intille, S.: Activity recognition from user-annotated acceleration data. In: Ferscha, A., Mattern, F. (eds.) PERVASIVE 2004. LNCS, vol. 3001, pp. 1–17. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Laerhoven, K.V., Gellersen, H.W.: Spine versus porcupine: A study in distributed wearable activity recognition. In: ISWC, pp. 142–149 (2004)Google Scholar
  4. 4.
    Kern, N., Antifakos, S., Schiele, B., Schwaninger, A.: A model of human interruptability: Experimental evaluation and automatic estimation from wearable sensors. In: Proc. ISWC, Washington DC, USA (2004)Google Scholar
  5. 5.
    Choudhury, T., Pentland, A.: Sensing and modeling human networks using the sociometer. In: Proc. ISWC, pp. 216–222 (2003)Google Scholar
  6. 6.
    Davis, J., Bobick, A.: The representation and recognition of action using temporal templates. In: Proceedings Computer Vision and Pattern Recognition, pp. 928–934 (1997)Google Scholar
  7. 7.
    Jebara, T., Pentland, A.: Action reaction learning: Automatic visual analysis and synthesis of interactive behaviour. In: ICVS, pp. 273–292 (1999)Google Scholar
  8. 8.
    Shi, Y., Huang, Y., Minnen, D., Bobick, A.F., Essa, I.A.: Propagation networks for recognition of partially ordered sequential action. In: CVPR (2), pp. 862–869 (2004)Google Scholar
  9. 9.
    Lester, J., Choudhury, T., Kern, N., Borriello, G., Hannaford, B.: A hybrid discriminative/generative approach for modeling human activities. In: Proc. of the Nineteenth Intl. Joint Conf. on A.I., Morgan-Kaufmann Publishers, Edinburgh (2005)Google Scholar
  10. 10.
    Clarkson, B., Pentland, A.: Unsupervised clustering of ambulatory audio and video. In: Proc. ICASSP (1999)Google Scholar
  11. 11.
    Clarkson, B.: Life Patterns: structure from wearable sensors. PhD thesis, Massachusetts Institute of Technology (2002)Google Scholar
  12. 12.
    Patterson, D.J., Liao, L., Fox, D., Kautz, H.: Inferring high-level behavior from low-level sensors. In: Dey, A.K., Schmidt, A., McCarthy, J.F. (eds.) UbiComp 2003. LNCS, vol. 2864, pp. 73–89. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  13. 13.
    Leonardis, A., Bischof, H., Maver, J.: Multiple eigenspaces. Pattern Recognition 35(11), 2613–2627 (2002)CrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tâm Huỳnh
    • 1
  • Bernt Schiele
    • 1
  1. 1.Computer Science DepartmentTU DarmstadtGermany

Personalised recommendations