Advertisement

Bounding Part Scores for Rapid Detection with Deformable Part Models

  • Iasonas Kokkinos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7585)

Abstract

Computing part scores is the main computational bottleneck in object detection with Deformable Part Models. In this work we introduce an efficient method to obtain bounds on part scores, which we then integrate with deformable model detection. As in [1] we rapidly approximate the inner product between a weight vector and HOG-based features by quantizing the HOG cells onto a codebook and replace their inner product with the lookup of a precomputed score. The novelty in our work consists in combining this lookup-based estimate with the codebook quantization error so as to construct probabilistic bounds to the exact inner product.

In particular we use Chebyshev’s inequality to obtain probably correct bounds for the inner product at each image location. We integrate these bounds with both the Dual-Tree Branch-and-Bound work of [2,3] and the Cascade-DPMs of [4]; in both cases the bounds are used in a first phase to conservatively construct a short-list of locations, for which the exact inner products are subsequently evaluated.

We quantitatively evaluate our method and demonstrate that it allows for approximately a twofold speedup over both [2] and [4] with negligible loss in accuracy.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Vedaldi, A., Zisserman, A.: Sparse Kernel Approximations for Efficient Classification and Detection. In: CVPR (2012)Google Scholar
  2. 2.
    Kokkinos, I.: Rapid deformable object detection using dual-tree branch-and-bound. In: NIPS (2011)Google Scholar
  3. 3.
    Kokkinos, I.: Rapid Deformable Object Detection using Bounding-based Techniques. Technical Report 7940, INRIA (2012)Google Scholar
  4. 4.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A.: Cascade object detection with deformable part models. In: CVPR (2010)Google Scholar
  5. 5.
    Felzenszwalb, P.F., Huttenlocher, D.: Efficient Matching of Pictorial Structures. In: CVPR (2000)Google Scholar
  6. 6.
    Felzenszwalb, P.F., Girshick, R., McAllester, D., Ramanan, D.: Object Detection with Discriminatively Trained Part-Based Models. IEEE T. PAMI (2010)Google Scholar
  7. 7.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: Discriminatively trained deformable part models, release 4, http://people.cs.uchicago.edu/~pff/latent-release4/
  8. 8.
    Pedersoli, M., Vedaldi, A., Gonzàlez, J.: A coarse-to-fine approach for fast deformable object detection. In: CVPR (2011)Google Scholar
  9. 9.
    Viola, P., Jones, M.: Rapid Object Detection using a Boosted Cascade of Simple Features. In: CVPR (2001)Google Scholar
  10. 10.
    Fleuret, F., Geman, D.: Coarse-to-fine face detection. IJCV (2001)Google Scholar
  11. 11.
    Sapp, B., Toshev, A., Taskar, B.: Cascaded Models for Articulated Pose Estimation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 406–420. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Lampert, C., Blaschko, M., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: CVPR (2008)Google Scholar
  13. 13.
    Lampert, C.H.: An efficient divide-and-conquer cascade for nonlinear object detection. In: CVPR (2010)Google Scholar
  14. 14.
    Kokkinos, I., Yuille, A.: HOP: Hierarchical Object Parsing. In: CVPR (2009)Google Scholar
  15. 15.
    Sun, M., Telaprolu, M., Lee, H., Savarese, S.: An efficient branch-and-bound algorithm for optimal human pose estimation. In: CVPR (2012)Google Scholar
  16. 16.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 2, pp. 886–893 (2005)Google Scholar
  17. 17.
    Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/
  18. 18.
    Mitzenmacher, M., Upfal, E.: Probability and computing - randomized algorithms and probabilistic analysis. Cambridge University Press (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Iasonas Kokkinos
    • 1
    • 2
    • 3
  1. 1.Center for Visual ComputingÉcole Centrale ParisFrance
  2. 2.INRIA Saclay, Île-de-FranceÉquipe GalenFrance
  3. 3.LIGM (UMR CNRS), École des Ponts ParisTechUniversité Paris-EstFrance

Personalised recommendations