Advertisement

Active Deformable Part Models Inference

  • Menglong Zhu
  • Nikolay Atanasov
  • George J. Pappas
  • Kostas Daniilidis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8695)

Abstract

This paper presents an active approach for part-based object detection, which optimizes the order of part filter evaluations and the time at which to stop and make a prediction. Statistics, describing the part responses, are learned from training data and are used to formalize the part scheduling problem as an offline optimization. Dynamic programming is applied to obtain a policy, which balances the number of part evaluations with the classification accuracy. During inference, the policy is used as a look-up table to choose the part order and the stopping time based on the observed filter responses. The method is faster than cascade detection with deformable part models (which does not optimize the part order) with negligible loss in accuracy when evaluated on the PASCAL VOC 2007 and 2010 datasets.

Keywords

Part Order Object Detection Average Precision Part Evaluation Score Likelihood 
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

978-3-319-10584-0_19_MOESM1_ESM.mp4 (12 mb)
Electronic Supplementary Material (MP4 12,285 KB)

References

  1. 1.
    Bertsekas, D.P.: Dynamic Programming and Optimal Control, vol. 1. Athena Scientific (1995)Google Scholar
  2. 2.
    Bourdev, L., Brandt, J.: Robust object detection via soft cascade. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2, pp. 236–243. IEEE (2005)Google Scholar
  3. 3.
    Brubaker, S.C., Wu, J., Sun, J., Mullin, M.D., Rehg, J.M.: On the design of cascades of boosted ensembles for face detection. IJCV 77(1-3), 65–86 (2008)CrossRefGoogle Scholar
  4. 4.
    Dollár, P., Appel, R., Kienzle, W.: Crosstalk cascades for frame-rate pedestrian detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 645–659. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  5. 5.
    Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The Pascal Visual Object Classes (VOC) Challenge. IJCV 88(2), 303–338 (2010)CrossRefGoogle Scholar
  6. 6.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: Cascade object detection with deformable part models. In: CVPR, pp. 2241–2248. IEEE (2010)Google Scholar
  7. 7.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. PAMI 32(9), 1627–1645 (2010)CrossRefGoogle Scholar
  8. 8.
    Fleuret, F., Geman, D.: Coarse-to-fine face detection. IJCV (2001)Google Scholar
  9. 9.
    Gao, T., Koller, D.: Active classification based on value of classifier. In: NIPS (2011)Google Scholar
  10. 10.
    Gualdi, G., Prati, A., Cucchiara, R.: Multistage particle windows for fast and accurate object detection. PAMI 34(8), 1589–1604 (2012)CrossRefGoogle Scholar
  11. 11.
    Kapoor, A., Grauman, K., Urtasun, R., Darrell, T.: Gaussian processes for object categorization. IJCV (2010)Google Scholar
  12. 12.
    Karayev, S., Fritz, M., Darrell, T.: Anytime recognition of objects and scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (oral, to appear, 2014)Google Scholar
  13. 13.
    Kokkinos, I.: Rapid deformable object detection using dual-tree branch-and-bound. In: NIPS (2011)Google Scholar
  14. 14.
    Lampert, C.H.: An efficient divide-and-conquer cascade for nonlinear object detection. In: CVPR. IEEE (2010)Google Scholar
  15. 15.
    Lampert, C.H., Blaschko, M.B., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: CVPR, pp. 1–8. IEEE (2008)Google Scholar
  16. 16.
    Lehmann, A., Gehler, P.V., Van Gool, L.J.: Branch&rank: Non-linear object detection. In: BMVC (2011)Google Scholar
  17. 17.
    Lehmann, A., Leibe, B., Van Gool, L.: Fast prism: Branch and bound hough transform for object class detection. IJCV 94(2), 175–197 (2011)CrossRefzbMATHGoogle Scholar
  18. 18.
    Pedersoli, M., Vedaldi, A., Gonzalez, J.: A coarse-to-fine approach for fast deformable object detection. In: CVPR, pp. 1353–1360. IEEE (2011)Google Scholar
  19. 19.
    Rahtu, E., Kannala, J., Blaschko, M.: Learning a category independent object detection cascade. In: ICCV (2011)Google Scholar
  20. 20.
    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
  21. 21.
    Sznitman, R., Becker, C., Fleuret, F., Fua, P.: Fast object detection with entropy-driven evaluation. In: CVPR (June 2013)Google Scholar
  22. 22.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR. IEEE (2001)Google Scholar
  23. 23.
    Weiss, D., Sapp, B., Taskar, B.: Structured prediction cascades. arXiv preprint arXiv:1208.3279 (2012)Google Scholar
  24. 24.
    Wu, T., Zhu, S.-C.: Learning near-optimal cost-sensitive decision policy for object detection. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 753–760. IEEE (2013)Google Scholar
  25. 25.
    Zhang, Z., Warrell, J., Torr, P.H.: Proposal generation for object detection using cascaded ranking svms. In: CVPR, pp. 1497–1504. IEEE (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Menglong Zhu
    • 1
  • Nikolay Atanasov
    • 1
  • George J. Pappas
    • 1
  • Kostas Daniilidis
    • 1
  1. 1.GRASP LaboratoryUniversity of PennsylvaniaPhiladelphiaUSA

Personalised recommendations