Revisiting Pose Estimation with Foreshortening Compensation and Color Information

Achint Setia, Anoop R. Katti, Anurag Mittal

2014

Abstract

This paper addresses the problem of upper body pose estimation. The task is to detect and estimate 2D human configuration in static images for six parts: head, torso, and left-right upper and lower arms. The common approach to solve this has been the Pictorial Structure method (Felzenszwalb and Huttenlocher, 2005). We present this as a graphical model inference problem and use the loopy belief propagation algorithm for inference. When a human appears in fronto-parallel plane, fixed size part detectors are sufficient and give reliable detection. But when parts like lower and upper arms move out of the plane, we observe foreshortening and the part detectors become erroneous. We propose an approach that compensates foreshortening in the upper and lower arms, and effectively prunes the search state space of each part. Additionally, we introduce two extra pairwise constraints to exploit the color similarity information between parts during inference to get better localization of the upper and lower arms. Finally, we present experiments and results on two challenging datasets (Buffy and ETHZ Pascal), showing improvements on the lower arms accuracy and comparable results for other parts.

References

  1. Andriluka, M., Roth, S., and Schiele, B. (2009). Pictorial structures revisited: People detection and articulated pose estimation. In Proc. CVPR 2009. IEEE.
  2. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In Proc. CVPR 2005. IEEE.
  3. Eichner, M. and Ferrari, V. (2009). Better appearance models for pictorial structures. In Proc. BMVC 2009. British Machine Vision Association.
  4. Felzenszwalb, P., McAllester, D., and Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In Proc. CVPR 2008.
  5. Felzenszwalb, P. F. and Huttenlocher, D. P. (2005). Pictorial structures for object recognition. IJCV 2005.
  6. Ferrari, V., Marin-Jimenez, M., and Zisserman, A. (2008). Progressive search space reduction for human pose estimation. In Proc. CVPR 2008. IEEE.
  7. Fischler, M. A. and Elschlager, R. A. (1973). The representation and matching of pictorial structures. IEEE Transactions on Computers 1973.
  8. Friedman, J., Hastie, T., and Tibshirani, R. (2000). Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). The Annals of Statistics.
  9. Gupta, A., Mittal, A., and Davis, L. S. (2008). Constraint integration for efficient multiview pose estimation with self-occlusions. PAMI 2008.
  10. Karlinsky, L. and Ullman, S. (2012). Using linking features in learning non-parametric part models. In Proc. ECCV 2012. Springer Berlin Heidelberg.
  11. Koller, D. and Friedman, N. (2009). Probabilistic graphical models : principles and techniques. MIT Press.
  12. Ramanan, D. (2006). Learning to parse images of articulated bodies. In Proc. NIPS 2006.
  13. Ramanan, D. and Sminchisescu, C. (2006). Training deformable models for localization. In Proc. CVPR 2006. IEEE.
  14. Rother, C., Kolmogorov, V., and Blake, A. (2004). ”grabcut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph.
  15. Sapp, B., Jordan, C., and Taskar, B. (2010a). Adaptive pose priors for pictorial structures. In Proc. CVPR 2010. IEEE.
  16. Sapp, B., Toshev, A., and Taskar, B. (2010b). Cascaded models for articulated pose estimation. In Proc. ECCV 2010. Springer Berlin / Heidelberg.
  17. Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proc. CVPR 2001. IEEE.
  18. Yang, Y. and Ramanan, D. (2011). Articulated pose estimation with flexible mixtures-of-parts. In Proc. CVPR 2011. IEEE.
Download


Paper Citation


in Harvard Style

Setia A., R. Katti A. and Mittal A. (2014). Revisiting Pose Estimation with Foreshortening Compensation and Color Information . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 31-38. DOI: 10.5220/0004669300310038


in Bibtex Style

@conference{visapp14,
author={Achint Setia and Anoop R. Katti and Anurag Mittal},
title={Revisiting Pose Estimation with Foreshortening Compensation and Color Information},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={31-38},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004669300310038},
isbn={978-989-758-004-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Revisiting Pose Estimation with Foreshortening Compensation and Color Information
SN - 978-989-758-004-8
AU - Setia A.
AU - R. Katti A.
AU - Mittal A.
PY - 2014
SP - 31
EP - 38
DO - 10.5220/0004669300310038