Feature Recycling Cascaded SVM Classifier Based on Feature Selection of HOGs for Pedestrian Detection

  • Alexandros Gavriilidis
  • Carsten Stahlschmidt
  • Jörg Velten
  • Anton Kummert
Part of the Communications in Computer and Information Science book series (CCIS, volume 368)


Since to pedestrian detection in driver assistance as well as surveillance systems is a challenging task of the recent years this paper introduces a fast cascaded classifier based on linear and non-linear support vector machines (SVMs). To yield high and accurate detection rates, histogram of oriented gradients (HOGs) will be preselected by the fisher score. These features will be a basis for the training algorithm of the cascaded classifier. A non-maximum suppression algorithm will be used and evaluated in respect to reject HOG features which have a huge overlap in a joint image area. By variation of the non-maximum suppression parameter different numbers of preselected HOG features will be used to create the cascaded classifier. The different cascaded classifiers will be evaluated and compared between each other and in relation to the HOG procedure from Dalal and Triggs combined with a support vector machine.


Pedestrian Detection Cascaded Classifier Feature Selection Support Vector Machine 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chang, Y.W., Lin, C.J.: Feature Ranking Using Linear SVM. Journal of Machine Learning Research - Proceedings Track 3, 53–64 (2008)MathSciNetGoogle Scholar
  2. 2.
    Cortes, C., Vapnik, V.: Support Vector Networks. Machine Learning 20, 273–297 (1995)MATHGoogle Scholar
  3. 3.
    Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, San Diego, California, USA, vol. 1, pp. 886–893 (June 2005)Google Scholar
  4. 4.
    Ding, C., Peng, H.: Minimum Redundancy Feature Selection from Microarray Gene Expression Data. In: Proceedings of the 2nd IEEE Computer Society Conference on Bioinformatics, CSB 2003, Stanford, CA, USA, pp. 523–528 (August 2003)Google Scholar
  5. 5.
    Haselhoff, A., Hoehmann, L., Nunn, C., Meuter, M., Kummert, A.: On Occlusion-Handling for People Detection Fusion in Multi-camera Networks. In: Dziech, A., Czyżewski, A. (eds.) MCSS 2011. CCIS, vol. 149, pp. 113–119. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  6. 6.
    He, X., Cai, D., Niyogi, P.: Laplacian Score for Feature Selection. In: Neural Information Processing Systems, vol. 18, pp. 507–514. MIT Press, Lake Tahoe (2005)Google Scholar
  7. 7.
    Platt, J.C.: Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines. Tech. rep., Microsoft Research (April 1998)Google Scholar
  8. 8.
    Viola, P., Jones, M.: Rapid Object Detection Using a Boosted Cascade of Simple Features. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, Kauai, HI, USA, vol. 1, pp. 511–518 (December 2001)Google Scholar
  9. 9.
    Xing, W., Zhao, Y., Cheng, R., Xu, J., Lv, S., Wang, X.: Fast Pedestrian Detection Based on Haar Pre-Detection. International Journal of Computer and Communication Engineering 1(3), 207–209 (2012)Google Scholar
  10. 10.
    Zhu, Q., Avidan, S., Yeh, M.C., Cheng, K.T.: Fast Human Detection Using a Cascade of Histograms of Oriented Gradients. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, USA, vol. 2, pp. 1491–1498 (June 2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Alexandros Gavriilidis
    • 1
  • Carsten Stahlschmidt
    • 1
  • Jörg Velten
    • 1
  • Anton Kummert
    • 1
  1. 1.Faculty of Electrical Engineering and Media TechnologiesUniversity of WuppertalWuppertalGermany

Personalised recommendations