Integrating Spatial Layout of Object Parts into Classification without Pairwise Terms - Application to Fast Body Parts Estimation from Depth Images

Mingyuan Jiu, Christian Wolf, Atilla Baskurt

2013

Abstract

Object recognition or human pose estimation methods often resort to a decomposition into a collection of parts. This local representation has significant advantages, especially in case of occlusions and when the “object” is non-rigid. Detection and recognition requires modeling the appearance of the different object parts as well as their spatial layout. The latter can be complex and requires the minimization of complex energy functions, which is prohibitive in most real world applications and therefore often omitted. However, ignoring the spatial layout puts all the burden on the classifier, whose only available information is local appearance. We propose a new method to integrate the spatial layout into the parts classification without costly pairwise terms. We present an application to body parts classification for human pose estimation. As a second contribution, we introduce edge features from gray images as a complement to the well known depth features used for body parts classification from Kinect data.

References

  1. Barrow, H., tenenbaum, J., Bolles, R., and Wolf, H. (1977). Parametric correspondence and chamfer matching: two new techniques for image matching. In Joint conference on artificial intelligence, pages 659-663.
  2. Duchenne, O., Bach, F. R., Kweon, I.-S., and Ponce, J. (2009). A tensor-based algorithm for high-order graph matching. In CVPR, pages 1980-1987.
  3. Farabet, C., Couprie, C., Najman, L., and LeCun, Y. (2012). Scene parsing with multiscale feature learning, purity trees, and optimal covers. In ICML.
  4. Felzenszwalb, P., Girshick, R., McAllester, D., and Ramanan, D. (2010). Object detection with discriminatively trained part based models. IEEE Transactions on PAMI, 32(9):1627-1645.
  5. Felzenszwalb, P. F. and Huttenlocher, D. P. (2005). Pictorial Structures for Object Recognition. IJCV, 61(1):55- 79.
  6. Ferrari, V., Marin-Jimenez, M., and Zisserman, A. (2008). Progressive search space reduction for human pose estimation. In CVPR, pages 1-8.
  7. Fischler, M. and Bolles, R. (1981). Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communcations of the ACM, 24:381395.
  8. Fischler, M. and Elschlager, R. (1973). The representation and matching of pictorial structures. IEEE Transactions on Computer, 22(1):6792.
  9. Geman, S. and Geman, D. (1984). Stochastic Relaxation,
Download


Paper Citation


in Harvard Style

Jiu M., Wolf C. and Baskurt A. (2013). Integrating Spatial Layout of Object Parts into Classification without Pairwise Terms - Application to Fast Body Parts Estimation from Depth Images . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 626-631. DOI: 10.5220/0004278206260631


in Bibtex Style

@conference{visapp13,
author={Mingyuan Jiu and Christian Wolf and Atilla Baskurt},
title={Integrating Spatial Layout of Object Parts into Classification without Pairwise Terms - Application to Fast Body Parts Estimation from Depth Images},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={626-631},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004278206260631},
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 - Integrating Spatial Layout of Object Parts into Classification without Pairwise Terms - Application to Fast Body Parts Estimation from Depth Images
SN - 978-989-8565-47-1
AU - Jiu M.
AU - Wolf C.
AU - Baskurt A.
PY - 2013
SP - 626
EP - 631
DO - 10.5220/0004278206260631