Advertisement

Multi-class Classification on Riemannian Manifolds for Video Surveillance

  • Diego Tosato
  • Michela Farenzena
  • Mauro Spera
  • Vittorio Murino
  • Marco Cristani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6312)

Abstract

In video surveillance, classification of visual data can be very hard, due to the scarce resolution and the noise characterizing the sensors’ data. In this paper, we propose a novel feature, the ARray of COvariances (ARCO), and a multi-class classification framework operating on Riemannian manifolds. ARCO is composed by a structure of covariance matrices of image features, able to extract information from data at prohibitive low resolutions. The proposed classification framework consists in instantiating a new multi-class boosting method, working on the manifold \(Sym^{+}_d\) of symmetric positive definite d×d (covariance) matrices. As practical applications, we consider different surveillance tasks, such as head pose classification and pedestrian detection, providing novel state-of-the-art performances on standard datasets.

Keywords

Riemannian Manifold Tangent Space Sectional Curvature Covariance Matrice Video Surveillance 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

978-3-642-15552-9_28_MOESM1_ESM.pdf (633 kb)
Electronic Supplementary Material (634 KB)

References

  1. 1.
    Murphy-Chutorian, E., Trivedi, M.M.: Head pose estimation in computer vision: A survey. IEEE Trans. PAMI 31, 607–626 (2009)Google Scholar
  2. 2.
    Enzweiler, M., Gavrila, D.M.: Monocular pedestrian detection: Survey and experiments. IEEE Trans. PAMI 31, 2179–2195 (2009)Google Scholar
  3. 3.
    Yang, M., Kriegman, D., Ahuja, N.: Detecting faces in images: A survey. IEEE Trans. PAMI 24, 34–58 (2002)Google Scholar
  4. 4.
    Viola, P., Jones, M.: Rapid Object Detection using a Boosted Cascade of Simple. In: Proc. CVPR (2001)Google Scholar
  5. 5.
    Li, S., Zhu, L., Zhang, Z., Blake, A., Zhang, H., Shum, H.: Statistical learning of multi-view face detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 67–81. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  6. 6.
    Viola, M., Jones, M.J., Viola, P.: Fast multi-view face detection. In: Proc. CVPR (2003)Google Scholar
  7. 7.
    Huang, C., Ai, H., Li, Y., Lao, S.: Vector boosting for rotation invariant multi-view face detection. In: Proc. ICCV, pp. 446–453 (2005)Google Scholar
  8. 8.
    Wu, B., Ai, H., Huang, C., Lao, S.: Fast rotation invariant multi-view face detection based on real adaboost. In: FGR, pp. 79–84 (2004)Google Scholar
  9. 9.
    Li, S., Zhang, Z.: Floatboost learning and statistical face detection. IEEE Trans. PAMI 26 (2004)Google Scholar
  10. 10.
    Bar-Hillel, A., Hertz, T., Weinshall, D.: Object class recognition by boosting a part-based model. In: Proc. CVPR, pp. 702–709 (2005)Google Scholar
  11. 11.
    Tuzel, O., Porikli, F., Meer, P.: Pedestrian detection via classification on riemannian manifolds. IEEE Trans. PAMI, 1713–1727 (2008)Google Scholar
  12. 12.
    Yao, J., Odobez, J.: Fast Human Detection from Videos Using Covariance Features. In: The Eighth International Workshop on Visual Surveillance (2008)Google Scholar
  13. 13.
    Wu, B., Nevatia, R.: Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection. In: Proc. CVPR (2008)Google Scholar
  14. 14.
    Paisitkriangkrai, S., Shen, C., Zhang, J.: Performance evaluation of local features in human classification and detection. IET-CV 2, 236–246 (2008)CrossRefGoogle Scholar
  15. 15.
    Freund, Y., Schapire, R.: A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences 55, 119–139 (1997)zbMATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Schapire, R., Singer, Y.: Improved boosting algorithms using confidence-rated predictions. Mach. Learn. 37, 297–336 (1999)zbMATHCrossRefGoogle Scholar
  17. 17.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: A statistical view of boosting. The Annals of Statistics 28, 337–374 (2000)zbMATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Wu, B., Nevatia, R.: Detection and segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses. IJCV 82 (2009)Google Scholar
  19. 19.
    Tuzel, O., Porikli, F., Meer, P.: Region covariance: A fast descriptor for detection and classification. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 589–600. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  20. 20.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR, vol. 1, p. 886 (2005)Google Scholar
  21. 21.
    Zhang, J., Zhou, S., McMillan, L., Comaniciu, D.: Joint real-time object detection and pose estimation using probabilistic boosting network. In: Proc. CVPR, vol. 8 (2007)Google Scholar
  22. 22.
    Wu, B., Nevatia, R.: Detection and segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses. In: Sanderson, J.G. (ed.) A Relational Theory of Computing. LNCS, vol. 82, pp. 185–204. Springer, Heidelberg (1980)Google Scholar
  23. 23.
    Chen, Y.-T., Chen, C.-S., Hung, Y.-P., Chang, K.-Y.: Multi-Class Multi-Instance Boosting for Part-Based Human Detection. In: ICCV 2009 Workshops, pp. 1177–1184 (2009)Google Scholar
  24. 24.
    Karcher, H.: Riemannian Center of Mass and Mollifier Smoothing. Comm. Pure and Applied Math. 30, 509–541 (1997)CrossRefMathSciNetGoogle Scholar
  25. 25.
    Chavel, I.: Riemannian Geometry - A modern introduction. Cambridge University Press, Cambridge (2006)zbMATHCrossRefGoogle Scholar
  26. 26.
    Pennec, X.: Probabilities and statistics on Riemannian manifolds: a geometric approach. Technical report, INRIA (2004)Google Scholar
  27. 27.
    Arsigny, V., Fillard, P., Pennec, X., Ayache, N.: Fast and simple calculus on tensors in the Log-Euclidean framework. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3749, pp. 115–122. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  28. 28.
    Breiman, L., Friedman, J., Olshen, R., Stone, C., Breiman, L., Hoeffding, W., Serfling, R., Friedman, J., Hall, O., Buhlmann, P., et al: Classification and Regression Trees. Ann. Math. Statist. 19, 293–325Google Scholar
  29. 29.
    Orozco, J., Gong, S., Xiang, T.: Head pose classification in Crowded Scenes. In: Proc. BMVC (2009)Google Scholar
  30. 30.
    Schwartz, W., Kembhavi, A., Harwood, D., Davis, L.: Human Detection Using Partial Least Squares Analysis. In: Proc. ICCV (2009)Google Scholar
  31. 31.
    Maji, S., Berg, A., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: Proc. CVPR, vol. 1, p. 4 (2008)Google Scholar
  32. 32.
    Lin, Z., Davis, L.: A pose-invariant descriptor for human detection and segmentation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 423–436. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  33. 33.
    Wu, B., Nevatia, R.: Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In: ICCV (2005)Google Scholar
  34. 34.
    Dollár, P., Babenko, B., Belongie, S., Perona, P., Tu, Z.: Multiple component learning for object detection. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 211–224. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  35. 35.
    Li, M., Zhang, Z., Huang, K., Tan, T.: Estimating the number of people in crowded scenes by MID based foreground segmentation and head-shoulder detection. In: Proc. ICPR, pp. 1–4 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Diego Tosato
    • 1
  • Michela Farenzena
    • 1
  • Mauro Spera
    • 1
    • 2
  • Vittorio Murino
    • 1
  • Marco Cristani
    • 1
    • 2
  1. 1.Dipartimento di InformaticaUniversity of VeronaItaly
  2. 2.Istituto Italiano di Tecnologia (IIT)GenovaItaly

Personalised recommendations