Efficient Object Pixel-Level Categorization Using Bag of Features

  • David Aldavert
  • Arnau Ramisa
  • Ricardo Toledo
  • Ramon Lopez de Mantaras
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5875)

Abstract

In this paper we present a pixel-level object categorization method suitable to be applied under real-time constraints. Since pixels are categorized using a bag of features scheme, the major bottleneck of such an approach would be the feature pooling in local histograms of visual words. Therefore, we propose to bypass this time-consuming step and directly obtain the score from a linear Support Vector Machine classifier. This is achieved by creating an integral image of the components of the SVM which can readily obtain the classification score for any image sub-window with only 10 additions and 2 products, regardless of its size. Besides, we evaluated the performance of two efficient feature quantization methods: the Hierarchical K-Means and the Extremely Randomized Forest. All experiments have been done in the Graz02 database, showing comparable, or even better results to related work with a lower computational cost.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: Workshop on Stat. Learning in Computer Vision, ECCV, pp. 1–22 (2004)Google Scholar
  3. 3.
    Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: Proc. of Computer Vision and Pattern Recognition, pp. 2161–2168 (2006)Google Scholar
  4. 4.
    Fulkerson, B., Vedaldi, A., Soatto, S.: Localizing objects with smart dictionaries. In: Proc. of European Conference on Computer Vision, pp. 179–192 (2008)Google Scholar
  5. 5.
    Sastre, R., Tuytelaars, T., Bascon, S.: Class representative visual words for category-level object recognition. In: IbPRIA 2009: Proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis, pp. 184–191 (2009)Google Scholar
  6. 6.
    Moosmann, F., Nowak, E., Jurie, F.: Randomized clustering forests for image classification. IEEE Trans. on Pat. Anal. and Machine Intel. 30, 1632–1646 (2008)CrossRefGoogle Scholar
  7. 7.
    Shotton, J., Johnson, M., Cipolla, R., Center, T., Kawasaki, J.: Semantic texton forests for image categorization and segmentation. In: Proc. of Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
  8. 8.
    Ramisa, A.: Localization and Object Recognition for Mobile Robots. PhD thesis, Universitat Autonoma de Barcelona (2009)Google Scholar
  9. 9.
    Lampert, C.H., Blaschko, M.B., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: Proc. of Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
  10. 10.
    Nowak, E., Jurie, F., Triggs, B.: Sampling strategies for bag-of-features image classification. In: Proc. of European Conference on Computer Vision, pp. 490–503 (2006)Google Scholar
  11. 11.
    Opelt, A., Pinz, A., Fussenegger, M., Auer, P.: Generic object recognition with boosting. IEEE Trans. on Pat. Anal. and Machine Intel. 28(3), 416–431 (2006)CrossRefGoogle Scholar
  12. 12.
    Zhu, Q., Yeh, M.C., Cheng, K.T., Avidan, S.: Fast human detection using a cascade of histograms of oriented gradients. In: Proc. of Computer Vision and Pattern Recognition, pp. 1491–1498 (2006)Google Scholar
  13. 13.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. of Computer Vision and Pattern Recognition, pp. 886–893 (2005)Google Scholar
  14. 14.
    Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: A comprehensive study. Int. Journal of Computer Vision 73, 213–238 (2007)CrossRefGoogle Scholar
  15. 15.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. of Computer Vision and Pattern Recognition, pp. 511–518 (2001)Google Scholar
  16. 16.
    Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Surf: Speeded up robust features. Computer Vision and Image Understanding (CVIU) 110, 346–359 (2008)CrossRefGoogle Scholar
  17. 17.
    Porikli, F.: Integral histogram: A fast way to extract histograms in cartesian spaces. In: Proc. of Computer Vision and Pattern Recognition, pp. 829–836 (2005)Google Scholar
  18. 18.
    Marszalek, M., Schmid, C.: Accurate object localization with shape masks. In: Proc. of Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar
  19. 19.
    Lin, C.-J., Weng, R.C., Keerthi, S.S.: Trust region newton methods for large-scale logistic regression. In: Int. Conf. on Machine Learning, pp. 561–568 (2007)Google Scholar
  20. 20.
    Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., Lin, C.-J.: Liblinear: A library for large linear classification. J. Mach. Learn. Res. 9, 1871–1874 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • David Aldavert
    • 1
  • Arnau Ramisa
    • 2
  • Ricardo Toledo
    • 1
  • Ramon Lopez de Mantaras
    • 2
  1. 1.Computer Vision Center (CVC), Dept. Ciències de la ComputacióUniversitat Autònoma de Barcelona (UAB)BellaterraSpain
  2. 2.Artificial Intelligence Research Institute (IIIA-CSIC), Campus de la UABBellaterraSpain

Personalised recommendations