Branch and Bound Strategies for Non-maximal Suppression in Object Detection

  • Matthew B. Blaschko
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6819)

Abstract

In this work, we are concerned with the detection of multiple objects in an image. We demonstrate that typically applied objectives have the structure of a random field model, but that the energies resulting from non-maximal suppression terms lead to the maximization of a submodular function. This is in general a difficult problem to solve, which is made worse by the very large size of the output space. We make use of an optimal approximation result for this form of problem by employing a greedy algorithm that finds one detection at a time. We show that we can adopt a branch-and-bound strategy that efficiently explores the space of all subwindows to optimally detect single objects while incorporating pairwise energies resulting from previous detections. This leads to a series of inter-related branch-and-bound optimizations, which we characterize by several new theoretical results. We then show empirically that optimal branch-and-bound efficiency gains can be achieved by a simple strategy of reusing priority queues from previous detections, resulting in speedups of up to a factor of three on the PASCAL VOC data set as compared with serial application of branch-and-bound.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barinova, O., Lempitsky, V., Kohli, P.: On the detection of multiple object instances using Hough transforms. In: IEEE Conference on Computer Vision and Pattern Recognition (2010)Google Scholar
  2. 2.
    Blaschko, M.B., Lampert, C.H.: Learning to localize objects with structured output regression. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 2–15. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  3. 3.
    Blaschko, M.B., Vedaldi, A., Zisserman, A.: Simultaneous object detection and ranking with weak supervision. In: Proc. NIPS (2010)Google Scholar
  4. 4.
    Blaschko, M.B., Lampert, C.H.: Object localization with global and local context kernels. In: BMVC (2009)Google Scholar
  5. 5.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR (2005)Google Scholar
  6. 6.
    Desai, C., Ramanan, D., Fowlkes, C.: Discriminative models for multi-class layout. In: Proc. ICCV (2009)Google Scholar
  7. 7.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes (VOC) challenge. International Journal of Computer Vision 88(2), 303–338 (2010)CrossRefGoogle Scholar
  8. 8.
    Felzenszwalb, P.F., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: Proc. CVPR (2008)Google Scholar
  9. 9.
    Gall, J., Lempitsky, V.: Class-specific hough forests for object detection. In: Proc. CVPR (2010)Google Scholar
  10. 10.
    Goldengorin, B., Sierksma, G., Tijssen, G.A., Tso, M.: The data-correcting algorithm for the minimization of supermodular functions. Management Science 45(11), 1539–1551 (1999)CrossRefMATHGoogle Scholar
  11. 11.
    Guestrin, C., Krause, A., Singh, A.: Near-optimal sensor placements in Gaussian processes. In: International Conference on Machine Learning, ICML (August 2005)Google Scholar
  12. 12.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. of The Fourth Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  13. 13.
    Hemery, B., Laurent, H., Rosenberger, C.: Comparative study of metrics for evaluation of object localisation by bounding boxes. In: Fourth International Conference on Image and Graphics, ICIG 2007, pp. 459–464 (August 2007)Google Scholar
  14. 14.
    Hollinger, G., Singh, S.: Proofs and experiments in scalable, near-optimal search by multiple robots. In: Robotics: Science and Systems (June 2008)Google Scholar
  15. 15.
    Joachims, T., Finley, T., Yu, C.N.J.: Cutting-plane training of structural SVMs. Mach. Learn. 77(1) (2009)Google Scholar
  16. 16.
    Kempe, D., Kleinberg, J., Tardos, E.: Maximizing the spread of influence through a social network. In: Proc. KDD (2003)Google Scholar
  17. 17.
    Krause, A.: Sfo: A toolbox for submodular function optimization. Journal of Machine Learning Research 11, 1141–1144 (2010)MATHGoogle Scholar
  18. 18.
    Krause, A., Guestrin, C., Gupta, A., Kleinberg, J.: Near-optimal sensor placements: Maximizing information while minimizing communication cost. In: International Symposium on Information Processing in Sensor Networks (IPSN) (April 2006)Google Scholar
  19. 19.
    Lampert, C.H., Blaschko, M.B., Hofmann, T.: Beyond sliding windows: Object localizationby efficient subwindow search. In: Proc. CVPR (2008)Google Scholar
  20. 20.
    Lampert, C.H., Blaschko, M.B., Hofmann, T.: Efficient subwindow search: A branch and bound framework for object localization. PAMI 31, 2129–2142 (2009)CrossRefGoogle Scholar
  21. 21.
    Laptev, I.: Improvements of object detection using boosted histograms. In: Proc. ECCV (2006)Google Scholar
  22. 22.
    Lehmann, A., Leibe, B., van Gool, L.: Feature-centric efficient subwindow search. In: Proc. ICCV (2009)Google Scholar
  23. 23.
    Lehmann, A., Leibe, B., Van Gool, L.: Fast prism: Branch and bound hough transform for object class detection. International Journal of Computer Vision, 1–23 (2010)Google Scholar
  24. 24.
    Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with implicit shape model. In: ECCV Workshop on Statistical Learning in Comp. Vision (2004)Google Scholar
  25. 25.
    Nemhauser, G.L., Wolsey, L.A., Fisher, M.L.: An analysis of approximations for maximizing submodular set functions. Mathematical Programming 14, 265–294 (1978)MathSciNetCrossRefMATHGoogle Scholar
  26. 26.
    Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: Multiple kernels for object detection. In: Proc. ICCV (2009)Google Scholar
  27. 27.
    Vedaldi, A., Zisserman, A.: Structured output regression for detection with partial occulsion. In: Proc. NIPS (2009)Google Scholar
  28. 28.
    Viola, P., Jones, M.J.: Robust real-time object detection. In: IJCV (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Matthew B. Blaschko
    • 1
  1. 1.Visual Geometry Group, Department of Engineering ScienceUniversity of OxfordUnited Kingdom

Personalised recommendations