Iterative Human Segmentation from Detection Windows using Contour Segment Analysis

Cyrille Migniot, Pascal Bertolino, Jean-Marc Chassery

Abstract

This paper presents a new algorithm for human segmentation in images. The human silhouette is estimated in positive windows that are already obtained with an existing efficient detection method. This accurate segmentation uses the data previously computed in the detection. First, a pre-segmentation step computes the likelihood of contour segments as being a part of a human silhouette. Then, a contour segment oriented graph is constructed from the shape continuity cue and the prior cue obtained by the pre-segmentation. Segmentation is so posed as the computation of the shortest-path cycle which corresponds to the human silhouette. Additionally, the process is achieved iteratively to eliminate irrelevant paths and to increase the segmentation performance. The approach is tested on a human image database and the segmentation performance is evaluated quantitatively.

References

  1. Alonso, I., Llorca, D., Sotelo, M., Bergasa, L., Toro, P. D., Nuevo, J., Ocania, M., and Garrido, M. (2007). Combination of feature extraction methods for svm pedestrian detection. IEEE Transactions on Intelligent Transportation Systems, 30:292-307.
  2. Bertozzi, M., Broggi, A., Rose, M. D., Felisa, M., Rakotomamonjy, A., and Suard, F. (2007). A pedestrian detector using histograms of oriented gradients and a support vector machine classifier. IEEE Intelligent Transportation Systems Conference, pages 143-148.
  3. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. IEEE International Conference on Computer Vision and Pattern Recognition, 2:886-893.
  4. Elder, J. and Zucker, S. (1996). Computing contour closure. European Conference on Computer Vision, 1:399- 412.
  5. Felzenszwalb, P., Girshik, R., McAllester, D., and Ramanan, D. (2010). Object detection with discriminatively trained part based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32:1627-1645.
  6. Ferrari, V., Tuytelaars, T., and Gool, L. V. (2006). Object detection by contour segment networks. European Conference on Computer Vision, 3953:14-28.
  7. Freund, Y. and Schapire, R. (1995). A decision-theoretic generalization of on-line learning and an application to boosting. European Conference on Computational Learning Theory, pages 23-37.
  8. Gao, W., Ai, H., and Lao, S. (2009). Adaptive contour features in oriented granular space for human detection and segmentation. IEEE International Conference on Computer Vision and Pattern Recognition, pages 1786-1793.
  9. Hariharan, B., Arbelaez, P., Bourdev, L., Maji, S., and Malik, J. (2011). Semantic contours from inverse detectors. IEEE International Conference in Computer Vision, pages 991-998.
  10. Hernandez, A., Reyes, M., Escalera, S., and Radeva, P. (2010). Spatio-temporal grabcut human segmentation for face and pose recovery. IEEE International Conference on Computer Vision and Pattern Recognition, pages 33-40.
  11. Joachims, T. (1999). Making large-scale svm learning practical. Advances in Kernel Methods - Support Vector Learning.
  12. Kang, S., Byun, H., and Lee, S. (2002). Real-time pedestrian detection using support vector machines. International Journal of Pattern Recognition and Artificial Intelligence, pages 268-277.
  13. Lin, Z. and Davis, L. (2010). Shape-based human detection and segmentation via hierarchical part-template matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32:604-618.
  14. Mori, G., Ren, X., Efros, A., and Malik, J. (2007). Recovering human body configurations: Combining segmentation and recognition. IEEE International Conference on Computer Vision and Pattern Recognition, 2:326-333.
  15. Munder, S. and Gavrila, D. (2006). An experimental study on pedestrian classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28:1863- 1868.
  16. Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., and Poggio, T. (1997). Pedestrian detection using wavelet templates. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 193- 199.
  17. Philipp-Foliguet, S. and Guigues, L. (2008). Multi-scale criteria for the evaluation of image segmentation algorithms. Journal of Multimedia, pages 42-56.
  18. Pishchulin, L., Jain, A., Andriluka, M., Thormaehlen, T., and Schiele, B. (2012). Articulated people detection and pose estimation: Reshaping the future. IEEE Conference on Computer Vision and Pattern Recognition, pages 1-8.
  19. Sharma, V. and Davis, J. (2007). Integrating appearance and motion cues for simultaneous detection and segmentation of pedestrians. IEEE International Conference on Computer Vision, pages 1-8.
  20. Shotton, J., Blake, A., and Cipolla, R. (2008). Multiscale categorical object recognition using contour fragments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30:1270-1281.
  21. Vapnik, V. (1995). The Nature of Statistical Learning Theory. Springer-Verlag.
  22. Wang, H. and Koller, D. (2011). Multi-level inference by relaxed dual decomposition for human pose segmentation. IEEE Conference on Computer Vision and Pattern Recognition, pages 2433-2440.
  23. Wu, B. and Nevatia, R. (2007). Simultaneous object detection and segmentation by boosting local shape feature based classifier. IEEE Conference on Computer Vision and Pattern Recognition, pages 1-8.
  24. Zhu, Q., Yeh, M., Cheng, K., and Avidan, S. (2006). Fast human detection using a cascade of histograms of oriented gradients. IEEE Conference on Computer Vision and Pattern Recognition, 2:1491-1498.
Download


Paper Citation


in Harvard Style

Migniot C., Bertolino P. and Chassery J. (2013). Iterative Human Segmentation from Detection Windows using Contour Segment Analysis . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 405-412. DOI: 10.5220/0004209404050412


in Bibtex Style

@conference{visapp13,
author={Cyrille Migniot and Pascal Bertolino and Jean-Marc Chassery},
title={Iterative Human Segmentation from Detection Windows using Contour Segment Analysis},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={405-412},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004209404050412},
isbn={978-989-8565-47-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - Iterative Human Segmentation from Detection Windows using Contour Segment Analysis
SN - 978-989-8565-47-1
AU - Migniot C.
AU - Bertolino P.
AU - Chassery J.
PY - 2013
SP - 405
EP - 412
DO - 10.5220/0004209404050412