Journal of Computing Science and Engineering

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

An Efficient Pedestrian Detection Approach Using a Novel Split Function of Hough Forests

  • Do, Trung Dung (School of Information and Communication Engineering, Inha University) ;
  • Vu, Thi Ly (School of Information and Communication Engineering, Inha University) ;
  • Nguyen, Van Huan (School of Information and Communication Engineering, Inha University) ;
  • Kim, Hakil (School of Information and Communication Engineering, Inha University) ;
  • Lee, Chongho (School of Information and Communication Engineering, Inha University)
  • Received : 2014.04.17
  • Accepted : 2014.11.16
  • Published : 2014.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

In pedestrian detection applications, one of the most popular frameworks that has received extensive attention in recent years is widely known as a 'Hough forest' (HF). To improve the accuracy of detection, this paper proposes a novel split function to exploit the statistical information of the training set stored in each node during the construction of the forest. The proposed split function makes the trees in the forest more robust to noise and illumination changes. Moreover, the errors of each stage in the training forest are minimized using a global loss function to support trees to track harder training samples. After having the forest trained, the standard HF detector follows up to search for and localize instances in the image. Experimental results showed that the detection performance of the proposed framework was improved significantly with respect to the standard HF and alternating decision forest (ADF) in some public datasets.

Keywords

References

  1. I. Cohen, and G. Medioni, "Detecting and tracking moving objects for video surveillance," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, 1999, pp. 2319-2325.
  2. A. Ess, K. Schindler, B. Leibe, and L. Van Gool, "Object detection and tracking for autonomous navigation in dynamic environments," International Journal of Robotics Research , vol. 29, no. 14, pp. 1707-1725, 2010. https://doi.org/10.1177/0278364910365417
  3. Y. Kong, Y. Jia, and Y. Fu, "Learning human interaction by interactive phrases," in Proceedings of the 12th European Conference on Computer Vision, Florence, Italy, 2012, pp. 300-313.
  4. V. N. Vapnik, Statistical Learning Theory, New York: Wiley, pp. 493-520, 1998.
  5. R. Rojas, Neural Networks: A Systematic Introduction, Berlin: Springer, 1996.
  6. Y. Freund and R. E. Schapire, "A decision-theoretic generalization of on-line learning and an application to boosting," Journal of Computer and System Sciences, vol. 55, no. 1, pp. 119-139, 1997. https://doi.org/10.1006/jcss.1997.1504
  7. R. E. Schapire, "The boosting approach to machine learning: an overview," in Nonlinear Estimation and Classification, New York: Springer, pp. 149-171, 2003.
  8. L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5-32, 2001. https://doi.org/10.1023/A:1010933404324
  9. A. Criminisi and J. Shotton, Decision Forests for Computer Vision and Medical Image Analysis, New York: Springer, pp. 25-46, 2013.
  10. D. Tang, Y. Liu, and T. K. Kim, "Fast pedestrian detection by cascaded random forest with dominant orientation template," in Proceedings of the British Machine Vision Conference (BMVC2012), Surrey, UK, 2012, pp. 1-11.
  11. S. Hinterstoisser, V. Lepetit, S. Ilic, P. Fua, and N. Navab, "Dominant orientation templates for real-time detection of texture-less objects," in Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010), San Francisco, CA, 2010, pp. 2257-2264.
  12. N. Dalal and B. Triggs, "Histogram of oriented gradients for human detection," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2005), San Diego, CA, 2005, pp. 886-893.
  13. K. Murphy, A. Torralba, D. Eaton, and W. Freeman, "Object detection and localization using local and global features," in Toward Category-Level Object Recognition, New York: Springer, pp. 382-400, 2006.
  14. B. Leibe, E. Seemann, and B. Schiele, "Pedestrian detection in crowded scenes," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2005), San Diego, CA, 2005, pp. 878-885.
  15. A. Bosch, A. Zisserman, and X. Muoz, "Image classification using random forests and ferns," in Proceedings of the 11th International Conference on Computer Vision (ICCV2007), Rio de Janeiro, Brazil, 2007, pp. 1-8.
  16. B. Xu, Y. Ye, and L. Nie, "An improved random forest classifier for image classification," in Proceedings of the International Conference on Information and Automation (ICIA2012), Shenyang, China, 2012, pp. 795-800.
  17. J. Gall and V. Lempitsky, "Class-specific Hough forests for object detection," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2009), Miami, FL, 2009, pp. 1022-1029.
  18. S. Schulter, P. Wohlhart, C. Leistner, A. Saffari, P. M. Roth, and H. Bischof, "Alternating decision forests," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2013), Portland, OR, 2013, pp. 508-515.
  19. P. Wohlhart, S. Schulter, M. Kostinger, P. M. Roth, and H. Bischof, "Discriminative Hough forests for object detection," in Proceedings of the British Machine Vision Conference (BMVC2012), Surrey, UK, 2012, pp. 1-11.
  20. H. Masnadi-Shirazi, V. Mahadevan, and N. Vasconcelos, "On the design of robust classifiers for computer vision," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010), San Francisco, CA, 2010, pp. 779-786.
  21. M. Kobetski and J. Sullivan, "Improved boosting performance by exclusion of ambiguous positive examples," in Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods (ICPRAM2013), Barcelona, Spain, 2013, pp. 11-21.
  22. M. Andriluka, S. Roth, and B. Schiele, "People-tracking-bydetection and people-detection-by-tracking," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2008), Anchorage, AK, 2008, pp. 1-8.
  23. P. Dollar, C. Wojek, B. Schiele, and P. Perona, "Pedestrian detection: an evaluation of the state of the art on pattern analysis and machine intelligent," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 4, pp. 743-761, 2012. https://doi.org/10.1109/TPAMI.2011.155
  24. M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, "The pascal visual object classes (VOC) challenge," International Journal of Computer Vision, vol. 88, no. 2, pp. 303-338, 2010. https://doi.org/10.1007/s11263-009-0275-4