Skip to main content
Springer Nature Link
Log in

Learning Pairwise Dissimilarity Profiles for Appearance Recognition in Visual Surveillance

  • Conference paper
Advances in Visual Computing (ISVC 2008)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 5358))

Included in the following conference series:

  • 2598 Accesses

Abstract

Training discriminative classifiers for a large number of classes is a challenging problem due to increased ambiguities between classes. In order to better handle the ambiguities and to improve the scalability of classifiers to larger number of categories, we learn pairwise dissimilarity profiles (functions of spatial location) between categories and adapt them into nearest neighbor classification. We introduce a dissimilarity distance measure and linearly or nonlinearly combine it with direct distances. We illustrate and demonstrate the approach mainly in the context of appearance-based person recognition.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Nakajima, C., Pontil, M., Heisele, B., Poggio, T.: Full-body person recognition system. Pattern Recognition 36, 1997–2006 (2003)

    Article  MATH  Google Scholar 

  2. Hastie, T., Tibshirani, R.: Classification by pairwise coupling. In: NIPS (1997)

    Google Scholar 

  3. Roth, V., Tsuda, K.: Pairwise coupling for machine recognition of handprinted japanese characters. In: CVPR (2001)

    Google Scholar 

  4. Wu, T., Lin, C., Weng, R.C.: Probability estimates for multi-class classification by pairwise coupling. Journal of Machine Learning Research 5, 975–1005 (2004)

    MathSciNet  MATH  Google Scholar 

  5. Dietterich, T., Bakiri, G.: Solving multiclass learning problems via error-correcting output codes. Journal of Artificial Intelligence Research, 263–286 (1995)

    Google Scholar 

  6. Amit, Y., Geman, D., Wilder, K.: Joint induction of shape features and tree classifiers. IEEE Trans. PAMI 19, 1300–1305 (1997)

    Article  Google Scholar 

  7. Moghadam, B., Jebara, T., Pentland, A.: Bayesian face recognition, MERL Technical Report, TR-2000-42 (2002)

    Google Scholar 

  8. Zhang, H., Berg, A., Maire, M., Malik, J.: SVM-KNN: Discriminative nearest neighbor classification for visual category recognition. In: CVPR (2006)

    Google Scholar 

  9. Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: ICCV (2007)

    Google Scholar 

  10. Hastie, T., Tibshirani, R.: Discriminant adaptive nearest neighbor classification. IEEE Trans. PAMI 18, 607–616 (1996)

    Article  Google Scholar 

  11. Domeniconi, C., Gunopulos, D.: Adaptive nearest neighbor classification using support vector machines. In: NIPS (2001)

    Google Scholar 

  12. Xing, E., Ng, A., Jordan, M., Russell, S.: Distance metric learning, with application to clustering with side information. In: NIPS (2002)

    Google Scholar 

  13. Shalev-Shwartz, S., Singer, Y., Ng, A.: Online and batch learning of pseudo metrics. In: ICML (2004)

    Google Scholar 

  14. Weinberger, K.Q., Blitzer, J., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. In: NIPS (2005)

    Google Scholar 

  15. Schultz, M., Joachims, T.: Learning a distance metric from relative comparisons. In: NIPS (2003)

    Google Scholar 

  16. Frome, A., Singer, Y., Sha, F., Malik, J.: Learning globally-consistent local distance functions for shape-based image retreval and classification. In: ICCV (2007)

    Google Scholar 

  17. Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IJCV 25, 64–577 (2003)

    Google Scholar 

  18. Elgammal, A., Davis, L.S.: Probabilistic tracking in joint feature-spatial spaces. In: ICCV (2003)

    Google Scholar 

  19. Gheissari, N., Sebastian, T., Tu, P., Rittscher, J., Hartley, R.: Person reidentification using spatiotemporal appearance. In: CVPR (2006)

    Google Scholar 

  20. Wang, X., Doretto, G., Sebastian, T., Rittscher, J., Tu, P.: Shape and appearance context modeling. In: ICCV (2007)

    Google Scholar 

  21. Li, J., Zhou, S.K., Chellappa, R.: Appearance context modeling under geometric context. In: ICCV (2005)

    Google Scholar 

  22. Scott, D.: Multivariate density estimation. Wiley Interscience, Hoboken (1992)

    Book  MATH  Google Scholar 

  23. Zhao, L., Davis, L.S.: Iterative figure-ground discrimination. In: ICPR (2004)

    Google Scholar 

  24. Yu, Y., Harwood, D., Yoon, K., Davis, L.S.: Human appearance modeling for matching across video sequences. Mach. Vis. Appl. 18, 139–149 (2007)

    Article  MATH  Google Scholar 

  25. Kim, K., Chalidabhongse, T.H., Harwood, D., Davis, L.S.: Real-time foreground-background segmentation using codebook model. Real-Time Imaging 11, 172–185 (2005)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Advanced Computer Studies, University of Maryland, College Park, MD 20742, USA

    Zhe Lin & Larry S. Davis

Authors
  1. Zhe Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Larry S. Davis
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Computer Science and Engineering, University of Nevada, Reno, USA

    George Bebis

  2. NASA Ames Research Center, Moffett Field, CA, USA

    Richard Boyle

  3. Lawrence Berkeley National Laboratory, Berkeley, CA, USA

    Bahram Parvin

  4. Desert Research Institute, Reno, NV, USA

    Darko Koracin

  5. Digital Image Research Center, Kingston University, London, UK

    Paolo Remagnino

  6. Mitsubishi Electric Research Laboratories, P.O. Box 02139, Cambridge, MA, USA

    Fatih Porikli

  7. Computer and Information Science and Engineering, University of Florida, P.O. Box, FL 32611-6120, Gainsville, USA

    Jörg Peters

  8. IBM T.J. Watson Research Center, 19 Skyline Drive, NY 10532, Hawthorne, USA

    James Klosowski

  9. 128 Memorial Mall, Stewart B001, IN 47907, West Lafayette, USA

    Laura Arns

  10. Denver Museum of Nature and Space, 2001 Colorade Blvd. Denver,, CO 80205, USA

    Yu Ka Chun

  11. Departmen of Computer Science,, NC State University, Campus Box 8206, NC 27695-8206, Raleigh, USA

    Theresa-Marie Rhyne

  12. Los Alamos National Labs, P.O. Box 1663, NM 87545, Los Alamos, USA

    Laura Monroe

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Lin, Z., Davis, L.S. (2008). Learning Pairwise Dissimilarity Profiles for Appearance Recognition in Visual Surveillance. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2008. Lecture Notes in Computer Science, vol 5358. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-89639-5_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-89639-5_3

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-89638-8

  • Online ISBN: 978-3-540-89639-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics