Advertisement

Multi-stage Sampling with Boosting Cascades for Pedestrian Detection in Images and Videos

  • Giovanni Gualdi
  • Andrea Prati
  • Rita Cucchiara
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6316)

Abstract

Many works address the problem of object detection by means of machine learning with boosted classifiers. They exploit sliding window search, spanning the whole image: the patches, at all possible positions and sizes, are sent to the classifier. Several methods have been proposed to speed up the search (adding complementary features or using specialized hardware). In this paper we propose a statistical-based search approach for object detection which uses a Monte Carlo sampling approach for estimating the likelihood density function with Gaussian kernels. The estimation relies on a multi-stage strategy where the proposal distribution is progressively refined by taking into account the feedback of the classifier (i.e. its response). For videos, this approach is plugged in a Bayesian-recursive framework which exploits the temporal coherency of the pedestrians. Several tests on both still images and videos on common datasets are provided in order to demonstrate the relevant speedup and the increased localization accuracy with respect to sliding window strategy using a pedestrian classifier based on covariance descriptors and a cascade of Logitboost classifiers.

Keywords

Object Detection Proposal Distribution Miss Rate Pedestrian Detection Slide Window 
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.

References

  1. 1.
    Viola, P.A., Jones, M.J., Snow, D.: Detecting pedestrians using patterns of motion and appearance. IJCV 63, 153–161 (2005)CrossRefGoogle Scholar
  2. 2.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 1, pp. 886–893 (2005)Google Scholar
  3. 3.
    Tuzel, O., Porikli, F., Meer, P.: Pedestrian detection via classification on riemannian manifolds. IEEE T-PAMI 30, 1713–1727 (2008)Google Scholar
  4. 4.
    Lampert, C.H., Blaschko, M.B., Hofmann, T.: Efficient subwindow search: A branch and bound framework for object localization. IEEE T-PAMI 31 (2009)Google Scholar
  5. 5.
    Tao, J., Odobez, J.M.: Fast human detection from videos using covariance features. In: Workshop on VS at ECCV (2008)Google Scholar
  6. 6.
    Ess, A., Leibe, B., Schindler, K., van Gool, L.: Robust multiperson tracking from a mobile platform. IEEE T-PAMI 31, 1831–1846 (2009)Google Scholar
  7. 7.
    Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. IJCV 80, 3–15 (2008)CrossRefGoogle Scholar
  8. 8.
    Wojek, C., Dorkó, G., Schulz, A., Schiele, B.: Sliding-windows for rapid object class localization: A parallel technique. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 71–81. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  9. 9.
    Lehmann, A., Leibe, B., Van Gool, L.: Feature-centric efficient subwindow search. In: ICCV (2009)Google Scholar
  10. 10.
    Butko, N., Movellan, J.: Optimal scanning for faster object detection. In: IEEE Conference on CVPR 2009, pp. 2751–2758 (2009)Google Scholar
  11. 11.
    Zhang, W., Zelinsky, G., Samaras, D.: Real-time accurate object detection using multiple resolutions. In: IEEE Conference on ICCV 2007, pp. 1–8 (2007)Google Scholar
  12. 12.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE T-PAMI 25, 564–575 (2003)Google Scholar
  13. 13.
    Han, B., Zhu, Y., Comaniciu, D., Davis, L.S.: Visual tracking by continuous density propagation in sequential bayesian filtering framework. IEEE T-PAMI 31 (2009)Google Scholar
  14. 14.
    Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. IJCV 29, 5–28 (1998)CrossRefGoogle Scholar
  15. 15.
    Hue, C., Le Cadre, J.P., Perez, P.: Tracking multiple objects with particle filtering. IEEE Transactions on Aerospace and Electronic Systems 38, 791–812 (2002)CrossRefGoogle Scholar
  16. 16.
    Isard, M., MacCormick, J.: Bramble: A bayesian multiple-blob tracker. In: ICCV, pp. 34–41 (2001)Google Scholar
  17. 17.
    Okuma, K., Taleghani, A., de Freitas, N., Little, J.J., Lowe, D.G.: A boosted particle filter: Multitarget detection and tracking. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 28–39. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  18. 18.
    Vermaak, J., Doucet, A., Pérez, P.: Maintaining multi-modality through mixture tracking. In: ICCV, pp. 1110–1116 (2003)Google Scholar
  19. 19.
    Papageorgiou, C., Poggio, T.: A trainable system for object detection. IJCV 38, 15–33 (2000)MATHCrossRefGoogle Scholar
  20. 20.
    Wojek, C., Schiele, B.: A performance evaluation of single and multi-feature people detection. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 82–91. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  21. 21.
    Sabzmeydani, P., Mori, G.: Detecting pedestrians by learning shapelet features. In: CVPR, pp. 1–8 (2007)Google Scholar
  22. 22.
    Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: CVPR, pp. 1–8 (2008)Google Scholar
  23. 23.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: A statistical view of boosting. Annals of Statistics 28, 337–407 (2000)MATHCrossRefMathSciNetGoogle Scholar
  24. 24.
    Babenko, B., Dollár, P., Tu, Z., Belongie, S.: Simultaneous learning and alignment: Multi-instance and multi-pose learning. In: Faces in Real-Life Images (2008)Google Scholar
  25. 25.
    Han, B., Comaniciu, D., Zhu, Y., Davis, L.: Incremental density approximation and kernel-based bayesian filtering for object tracking. In: CVPR (2004)Google Scholar
  26. 26.
    Philomin, V., Duraiswami, R., Davis, L.: Quasi-random sampling for condensation. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 134–149. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  27. 27.
    Opelt, A., Pinz, A., Fussenegger, M., Auer, P.: Generic object recognition with boosting. IEEE T-PAMI 28, 416–431 (2006)Google Scholar
  28. 28.
    Ponce, J., Berg, T., Everingham, M., Forsyth, D., Hebert, M., Lazebnik, S., Marszalek, M., Schmid, C., Russell, C., Torralba, A., Williams, C., Zhang, J., Zisserman, A.: In: Dataset issues in object recognition, pp. 29–48. Springer, Heidelberg (2006)Google Scholar
  29. 29.
    Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: A benchmark. In: CVPR, pp. 304–311 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Giovanni Gualdi
    • 1
  • Andrea Prati
    • 1
  • Rita Cucchiara
    • 1
  1. 1.University of Modena and Reggio EmiliaItaly

Personalised recommendations