Efficient Use of Geometric Constraints for Sliding-Window Object Detection in Video

  • Patrick Sudowe
  • Bastian Leibe
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6962)

Abstract

We systematically investigate how geometric constraints can be used for efficient sliding-window object detection. Starting with a general characterization of the space of sliding-window locations that correspond to geometrically valid object detections, we derive a general algorithm for incorporating ground plane constraints directly into the detector computation. Our approach is indifferent to the choice of detection algorithm and can be applied in a wide range of scenarios. In particular, it allows to effortlessly combine multiple different detectors and to automatically compute regions-of-interest for each of them. We demonstrate its potential in a fast CUDA implementation of the HOG detector and show that our algorithm enables a factor 2-4 speed improvement on top of all other optimizations.

Keywords

Object Detection Ground Plane Geometric Constraint Pedestrian Detection Scene Geometry 
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.
    Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian Detection: A Benchmark. In: CVPR (2009)Google Scholar
  2. 2.
    Gavrila, D., Munder, S.: Multi-Cue Pedestrian Detection and Tracking from a Moving Vehicle. IJCV 73(1), 41–59 (2007)CrossRefGoogle Scholar
  3. 3.
    Leibe, B., Schindler, K., Van Gool, L.: Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles. PAMI 30(10), 1683–1698 (2008)CrossRefGoogle Scholar
  4. 4.
    Ess, A., Leibe, B., Schindler, K., Van Gool, L.: Robust Multi-Person Tracking from a Mobile Platform. PAMI 31(10), 1831–1846 (2009)CrossRefGoogle Scholar
  5. 5.
    Viola, P., Jones, M.: Robust Real-Time Face Detection. IJCV 57(2) (2004)Google Scholar
  6. 6.
    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
  7. 7.
    Prisacariu, V., Reid, I.: fastHOG – a Real-Time GPU Implementation of HOG. Technical Report 2310/09, Dept. of Eng. Sc., Univ. of Oxford (2009)Google Scholar
  8. 8.
    Torralba, A., Murphy, K., Freeman, W.: Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection. In: CVPR (2004)Google Scholar
  9. 9.
    Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: Multiple kernels for object detection. In: ICCV (2009)Google Scholar
  10. 10.
    Felzenszwalb, P., Girshick, R., McAllester, D.: Cascade Object Detection with Deformable Part Models. In: CVPR (2010)Google Scholar
  11. 11.
    Dollar, P., Tu, Z., Perona, P., Belongie, S.: Integral Channel Features. In: BMVC (2009)Google Scholar
  12. 12.
    Dollar, P., Belongie, S., Perona, P.: The Fastest Pedestrian Detector in the West. In: BMVC (2010)Google Scholar
  13. 13.
    Lampert, C., Blaschko, M., Hofmann, T.: Efficient Subwindow Search: A Branch and Bound Framework for Object Localization. PAMI 31(12), 2129–2142 (2009)CrossRefGoogle Scholar
  14. 14.
    Hoiem, D., Efros, A., Hebert, M.: Putting Objects Into Perspective. In: CVPR (2006)Google Scholar
  15. 15.
    Geronimo, D., Sappa, A., Ponsa, D., Lopez, A.: 2D-3D-based On-Board Pedestrian Detection System. CVIU 114(5), 583–595 (2010)Google Scholar
  16. 16.
    Choi, W., Savarese, S.: Multiple target tracking in world coordinate with single, minimally calibrated camera. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 553–567. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  17. 17.
    Park, D., Ramanan, D., Fowlkes, C.: Multiresolution models for object detection. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 241–254. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  18. 18.
    Felzenszwalb, P., McAllester, D., Ramanan, D.: A Discriminatively Trained, Multiscale, Deformable Part Model. In: CVPR (2008)Google Scholar
  19. 19.
    Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: CVPR (2005)Google Scholar
  20. 20.
    Breitenstein, M., Sommerlade, E., Leibe, B., Van Gool, L., Reid, I.: Probabilistic Parameter Selection for Learning Scene Structure from Video. In: BMVC (2008)Google Scholar
  21. 21.
    Bao, Y., Sun, M., Savarese, S.: Toward Coherent Object Detection And Scene Layout Understanding. In: CVPR (2010)Google Scholar
  22. 22.
    Sun, M., Bao, Y., Savarese, S.: Object Detection with Geometrical Context Feedback Loop. In: BMVC (2010)Google Scholar
  23. 23.
    Bombini, L., Cerri, P., Grisleri, P., Scaffardi, S., Zani, P.: An Evaluation of Monocular Image Stabilization Algorithms for Automotive Applications. Intel. Transp. Syst (2006)Google Scholar
  24. 24.
    Schneiderman, H.: Feature-Centric Evaluation for Efficient Cascaded Object Detection. In: CVPR (2004)Google Scholar
  25. 25.
    Lehmann, A., Leibe, B., Van Gool, L.: Feature-Centric Efficient Subwindow Search. In: ICCV (2009)Google Scholar
  26. 26.
    Hartley, R., Zisserman, A.: Multiple view geometry in computer vision. Cambridge University Press, Cambridge (2000)MATHGoogle Scholar
  27. 27.
    Everingham, M., et al.: (34 authors): The 2005 PASCAL Visual Object Classes Challenge. In: Quiñonero-Candela, J., Dagan, I., Magnini, B., d’Alché-Buc, F. (eds.) MLCW 2005. LNCS (LNAI), vol. 3944, pp. 117–176. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Patrick Sudowe
    • 1
  • Bastian Leibe
    • 1
  1. 1.UMIC Research CentreRWTH Aachen UniversityGermany

Personalised recommendations