Cascaded Random Forest for Fast Object Detection

  • Florian Baumann
  • Arne Ehlers
  • Karsten Vogt
  • Bodo Rosenhahn
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7944)

Abstract

A Random Forest consists of several independent decision trees arranged in a forest. A majority vote over all trees leads to the final decision. In this paper we propose a Random Forest framework which incorporates a cascade structure consisting of several stages together with a bootstrap approach. By introducing the cascade, 99% of the test images can be rejected by the first and second stage with minimal computational effort leading to a massively speeded-up detection framework. Three different cascade voting strategies are implemented and evaluated. Additionally, the training and classification speed-up is analyzed. Several experiments on public available datasets for pedestrian detection, lateral car detection and unconstrained face detection demonstrate the benefit of our contribution.

Keywords

Random Forest Training Image Face Detection Weighted Vote 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.

References

  1. 1.
    Breiman, L.: Random forests. In: Machine Learning, vol. 45, pp. 5–32 (2001)Google Scholar
  2. 2.
    Breiman, L.: Bagging predictors. In: Machine Learning, vol. 24, pp. 123–140 (1996)Google Scholar
  3. 3.
    Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: Proceedings of the Thirteenth International Conference on Machine Learning, pp. 148–156. IEEE (1996)Google Scholar
  4. 4.
    Chen, C., Liaw, A., Breiman, L.: Using random forest to learn imbalanced data. Technical report, Department of Statistics, University of Berkeley (2004)Google Scholar
  5. 5.
    Khoshgoftaar, T.M., Golawala, M., Hulse, J.V.: An empirical study of learning from imbalanced data using random forest. In: 19th International Conference on Tools with Artificial Intelligence (ICTAI), vol. 2, pp. 310–317. IEEE (2007)Google Scholar
  6. 6.
    Strobl, C., Boulesteix, A.L., Zeileis, A., Hothorn, T.: Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinformatics (2007)Google Scholar
  7. 7.
    Munder, S., Gavrila, D.M.: An experimental study on pedestrian classification. Transactions on Pattern Analysis and Machine Intelligence (PAMI) 28, 1863–1868 (2006)Google Scholar
  8. 8.
    The MPLab GENKI Database, GENKI-4K Subset, http://mplab.ucsd.edu
  9. 9.
    Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 26(11), 1475–1490 (2004)CrossRefGoogle Scholar
  10. 10.
    Viola, P., Jones, M.J.: Robust real-time face detection. International Journal of Computer Vision 57(2), 137–154 (2004)CrossRefGoogle Scholar
  11. 11.
    Sung, K., Poggio, T.: Example based learning for view-based human face detection. Technical Report CBCL-112, Artificial Intelligence Laboratory, Massachusettes Inst. of Technology (1995)Google Scholar
  12. 12.
    Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from a single depth image. In: Computer Vision and Pattern Recognition (CVPR) (2011)Google Scholar
  13. 13.
    Khan, R., Hanbury, A., Stoettinger, J.: Skin detection: A random forest approach. In: 17th International Conference on Image Processing (ICIP), pp. 4613–4616. IEEE (2010)Google Scholar
  14. 14.
    Li, W., Xu, Z., Wang, S., Ma, G.: Pedestrian detection based on improved random forest in natural images. In: 3rd International Conference on Computer Research and Development (ICCRD), vol. 4, pp. 468–472. IEEE (2011)Google Scholar
  15. 15.
    Zaklouta, F., Stanciulescu, B., Hamdoun, O.: Traffic sign classification using k-d trees and random forests. In: The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 2151–2155. IEEE (2011)Google Scholar
  16. 16.
    Díaz-Uriarte, R., De Andres, S.: Gene selection and classification of microarray data using random forest. BMC Bioinformatics 7, 3 (2006)CrossRefGoogle Scholar
  17. 17.
    Bosch, A., Zisserman, A., Muoz, X.: Image classification using random forests and ferns. In: 11th International Conference on Computer Vision (ICCV), pp. 1–8. IEEE (2007)Google Scholar
  18. 18.
    Gall, J., Lempitsky, V.: Class-specific hough forests for object detection. In: Computer Vision and Pattern Recognition (CVPR). IEEE (2009)Google Scholar
  19. 19.
    Gall, J., Yao, A., Razavi, N., Van Gool, L., Lempitsky, V.: Hough forests for object detection, tracking, and action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 33(11), 2188–2202 (2011)CrossRefGoogle Scholar
  20. 20.
    Yao, A., Gall, J., Gool, L.V.: A hough transform-based voting framework for action recognition. In: Computer Vision and Pattern Recognition (CVPR), pp. 2061–2068. IEEE (2010)Google Scholar
  21. 21.
    Felzenszwalb, P., Girshick, R., McAllester, D.: Cascade object detection with deformable part models. In: Computer Vision and Pattern Recognition (CVPR), pp. 2241–2248. IEEE (2010)Google Scholar
  22. 22.
    Rematas, K., Leibe, B.: Efficient object detection and segmentation with a cascaded hough forest ISM. In: International Conference on Computer Vision Workshops (ICCVW), pp. 966–973. IEEE (November 2011)Google Scholar
  23. 23.
    Moutarde, F., Stanciulescu, B., Breheret, A.: Real-time visual detection of vehicles and pedestrians with new efficient adaboost features. In: IEEE IROS (2008)Google Scholar
  24. 24.
    Jain, V., Learned-Miller, E.: Fddb: A benchmark for face detection in unconstrained settings. Technical Report UM-CS-2010-009, University of Massachusetts, Amherst (2010)Google Scholar
  25. 25.
    Face Detection Data Set and Benchmark - Results, http://vis-www.cs.umass.edu/fddb/results.html

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Florian Baumann
    • 1
  • Arne Ehlers
    • 1
  • Karsten Vogt
    • 1
  • Bodo Rosenhahn
    • 1
  1. 1.Institut für InformationsverarbeitungLeibniz Universität HannoverHannoverGermany

Personalised recommendations