Advertisement

Crosstalk Cascades for Frame-Rate Pedestrian Detection

  • Piotr Dollár
  • Ron Appel
  • Wolf Kienzle
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7573)

Abstract

Cascades help make sliding window object detection fast, nevertheless, computational demands remain prohibitive for numerous applications. Currently, evaluation of adjacent windows proceeds independently; this is suboptimal as detector responses at nearby locations and scales are correlated. We propose to exploit these correlations by tightly coupling detector evaluation of nearby windows. We introduce two opposing mechanisms: detector excitation of promising neighbors and inhibition of inferior neighbors. By enabling neighboring detectors to communicate, crosstalk cascades achieve major gains (4-30× speedup) over cascades evaluated independently at each image location. Combined with recent advances in fast multi-scale feature computation, for which we provide an optimized implementation, our approach runs at 35-65 fps on 640×480 images while attaining state-of-the-art accuracy.

Keywords

Object Detection Miss Rate Pedestrian Detection Unsupervised Approach Rejection Threshold 
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.

References

  1. 1.
    Felzenszwalb, P., Girshick, R., McAllester, D.: Cascade object detection with deformable part models. In: CVPR (2010)Google Scholar
  2. 2.
    Pedersoli, M., Vedaldi, A., Gonzalez, J.: A coarse-to-fine approach for fast deformable object detection. In: CVPR (2011)Google Scholar
  3. 3.
    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
  4. 4.
    Dollár, P., Belongie, S., Perona, P.: The fastest pedestrian detector in the west. In: BMVC (2010)Google Scholar
  5. 5.
    Benenson, R., Mathias, M., Timofte, R., Van Gool, L.: Pedestrian detection at 100 frames per second. In: CVPR (2012)Google Scholar
  6. 6.
    Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: An evaluation of the state of the art. PAMI 99 (2011)Google Scholar
  7. 7.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)Google Scholar
  8. 8.
    Bourdev, L., Brandt, J.: Robust object detection via soft cascade. In: CVPR (2005)Google Scholar
  9. 9.
    Zhang, C., Viola, P.: Multiple-instance pruning for learning efficient cascade detectors. In: NIPS (2007)Google Scholar
  10. 10.
    Xiao, R., Zhu, L., Zhang, H.: Boosting chain learning for object detection. In: ICCV (2003)Google Scholar
  11. 11.
    Šochman, J., Matas, J.: Waldboost - learning for time constrained sequential detection. In: CVPR (2005)Google Scholar
  12. 12.
    Masnadi-Shirazi, H., Vasconcelos, N.: High detection-rate cascades for real-time object detection. In: ICCV (2007)Google Scholar
  13. 13.
    Zhu, Q., Avidan, S., Yeh, M., Cheng, K.: Fast human detection using a cascade of histograms of oriented gradients. In: CVPR (2006)Google Scholar
  14. 14.
    Butko, N., Movellan, J.: Optimal scanning for faster object detection. In: CVPR (2009)Google Scholar
  15. 15.
    Gualdi, G., Prati, A., Cucchiara, R.: Multi-stage Sampling with Boosting Cascades for Pedestrian Detection in Images and Videos. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 196–209. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  16. 16.
    Gualdi, G., Prati, A., Cucchiara, R.: A multi-stage pedestrian detection using monolithic classifiers. In: AVSS (2011)Google Scholar
  17. 17.
    Felzenszwalb, P., Huttenlocher, D.: Efficient matching of pictorial structures. In: CVPR (2000)Google Scholar
  18. 18.
    Fleuret, F., Geman, D.: Coarse-to-fine face detection. IJCV 41, 85–107 (2001)zbMATHCrossRefGoogle Scholar
  19. 19.
    Vempati, S., Vedaldi, A., Zisserman, A., Jawahar, C.V.: Generalized RBF feature maps for efficient detection. In: BMVC (2010)Google Scholar
  20. 20.
    Dollár, P., Tu, Z., Perona, P., Belongie, S.: Integral channel features. In: BMVC (2009)Google Scholar
  21. 21.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. The Annals of Statistics 38, 337–374 (2000)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  23. 23.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. PAMI 99 (2009)Google Scholar
  24. 24.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. IJCV 88, 303–338 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Piotr Dollár
    • 1
  • Ron Appel
    • 2
  • Wolf Kienzle
    • 1
  1. 1.Microsoft ResearchRedmondUSA
  2. 2.California Institute of TechnologyUSA

Personalised recommendations