Advertisement

Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features

  • Sakrapee Paisitkriangkrai
  • Chunhua Shen
  • Anton van den Hengel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8692)

Abstract

We propose a simple yet effective approach to the problem of pedestrian detection which outperforms the current state-of-the-art. Our new features are built on the basis of low-level visual features and spatial pooling. Incorporating spatial pooling improves the translational invariance and thus the robustness of the detection process. We then directly optimise the partial area under the ROC curve (pAUC) measure, which concentrates detection performance in the range of most practical importance. The combination of these factors leads to a pedestrian detector which outperforms all competitors on all of the standard benchmark datasets. We advance state-of-the-art results by lowering the average miss rate from 13% to 11% on the INRIA benchmark, 41% to 37% on the ETH benchmark, 51% to 42% on the TUD-Brussels benchmark and 36% to 29% on the Caltech-USA benchmark.

Keywords

Local Binary Pattern IEEE Conf Sparse Code Weak Learner Pedestrian Detection 
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.
    Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: An evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34, 743–761 (2012)CrossRefGoogle Scholar
  2. 2.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., vol. 1 (2005)Google Scholar
  3. 3.
    Shen, C., Wang, P., Paisitkriangkrai, S., van den Hengel, A.: Training effective node classifiers for cascade classification. Int. J. Comp. Vis. 103 (2013)Google Scholar
  4. 4.
    Paisitkriangkrai, S., Shen, C., Zhang, J.: Fast pedestrian detection using a cascade of boosted covariance features. IEEE Trans. Circuits Syst. Video Technol. 18, 1140–1151 (2008)CrossRefGoogle Scholar
  5. 5.
    Tuzel, O., Porikli, F., Meer, P.: Pedestrian detection via classification on Riemannian manifolds. IEEE Trans. Pattern Anal. Mach. Intell. 30, 1713–1727 (2008)CrossRefGoogle Scholar
  6. 6.
    Viola, P., Jones, M.J.: Robust real-time face detection. Int. J. Comp. Vis. 57, 137–154 (2004)CrossRefGoogle Scholar
  7. 7.
    Wang, X., Han, T.X., Yan, S.: An HOG-LBP human detector with partial occlusion handling. In: Proc. IEEE Int. Conf. Comp. (2009)Google Scholar
  8. 8.
    Park, D., Zitnick, C.L., Ramanan, D., Dollár, P.: Exploring weak stabilization for motion feature extraction. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2013)Google Scholar
  9. 9.
    Sermanet, P., Kavukcuoglu, K., Chintala, S., LeCun, Y.: Pedestrian detection with unsupervised multi-stage feature learning. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2013)Google Scholar
  10. 10.
    Wang, X., Yang, M., Zhu, S., Lin, Y.: Regionlets for generic object detection. In: Proc. IEEE Int. Conf. Comp. Vis. (2013)Google Scholar
  11. 11.
    Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2009)Google Scholar
  12. 12.
    Dollár, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 1 (2014)Google Scholar
  13. 13.
    Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1627–1645 (2010)CrossRefGoogle Scholar
  14. 14.
    Ouyang, W., Zeng, X., Wang, X.: Modeling mutual visibility relationship with a deep model in pedestrian detection. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2013)Google Scholar
  15. 15.
    Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: A benchmark. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2009)Google Scholar
  16. 16.
    Benenson, R., Mathias, M., Tuytelaars, T., Gool, L.V.: Seeking the strongest rigid detector. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2013)Google Scholar
  17. 17.
    Lim, J.J., Zitnick, C.L., Dollár, P.: Sketch Tokens: A learned mid-level representation for contour and object detection. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2013)Google Scholar
  18. 18.
    Dollár, P., Tu, Z., Perona, P., Belongie, S.: Integral channel features. In: Proc. of British Mach. Vis. Conf. (2009)Google Scholar
  19. 19.
    Walk, S., Majer, N., Schindler, K., Schiele, B.: New features and insights for pedestrian detection. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., San Francisco, US (2010)Google Scholar
  20. 20.
    Boureau, Y., Roux, N.L., Bach, F., Ponce, J., LeCun, Y.: Ask the locals: multi-way local pooling for image recognition. In: Proc. IEEE Int. Conf. Comp. Vis. (2011)Google Scholar
  21. 21.
    Chatfield, K., Lempitsky, V., Vedaldi, A., Zisserman, A.: The devil is in the details: an evaluation of recent feature encoding methods. In: Proc. of British Mach. Vis. Conf. (2011)Google Scholar
  22. 22.
    Coates, A., Ng, A.: The importance of encoding versus training with sparse coding and vector quantization. In: Proc. Int. Conf. Mach. Learn. (2011)Google Scholar
  23. 23.
    Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24, 971–987 (2002)CrossRefGoogle Scholar
  24. 24.
    Tuzel, O., Porikli, F., Meer, P.: Region covariance: A fast descriptor for detection and classification. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. Part II. LNCS, vol. 3952, pp. 589–600. Springer, Heidelberg (2006)Google Scholar
  25. 25.
    Jia, Y., Huang, C., Darrell, T.: Beyond spatial pyramids: Receptive field learning for pooled image features. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2012)Google Scholar
  26. 26.
    Bo, L., Ren, X., Fox, D.: Multipath sparse coding using hierarchical matching pursuit. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2013)Google Scholar
  27. 27.
    Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms. In: Int. Conf. on Multimedia (2010)Google Scholar
  28. 28.
    Paisitkriangkrai, S., Shen, C., van den Hengel, A.: Efficient pedestrian detection by directly optimizing the partial area under the roc curve. In: Proc. IEEE Int. Conf. Comp. Vis. (2013)Google Scholar
  29. 29.
    Wu, J., Brubaker, S.C., Mullin, M.D., Rehg, J.M.: Fast asymmetric learning for cascade face detection. IEEE Trans. Pattern Anal. Mach. Intell. 30, 369–382 (2008)CrossRefGoogle Scholar
  30. 30.
    Narasimhan, H., Agarwal, S.: \(\textrm{SVM}_\textrm{pAUC}^\textrm{tight}\): A new support vector method for optimizing partial auc based on a tight convex upper bound. In: ACM Int. Conf. on Knowl. Disc. and Data Mining (2013)Google Scholar
  31. 31.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Prediction, Inference and Data Mining. Springer (2009)Google Scholar
  32. 32.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: A statistical view of boosting. Ann. Stat. 28, 337–407 (2000)CrossRefzbMATHMathSciNetGoogle Scholar
  33. 33.
    Appel, R., Fuchs, T., Dollár, P., Perona, P.: Quickly boosting decision a trees-pruning underachieving features early. In: Proc. Int. Conf. Mach. Learn. (2013)Google Scholar
  34. 34.
    Rizzi, A., Gatta, C., Marini, D.: A new algorithm for unsupervised global and local color correction. Patt. Recogn. 24, 1663–1677 (2003)CrossRefGoogle Scholar
  35. 35.
    Ouyang, W., Wang, X.: Single-pedestrian detection aided by multi-pedestrian detection. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2013)Google Scholar
  36. 36.
    Getreuer, P.: Automatic color enhancement (ACE) and its fast implementation. Image Proc. On Line 2012 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Sakrapee Paisitkriangkrai
    • 1
  • Chunhua Shen
    • 1
  • Anton van den Hengel
    • 1
  1. 1.The University of AdelaideAustralia

Personalised recommendations