Abstract
Multi-view head-pose estimation in low-resolution, dynamic scenes is difficult due to blurred facial appearance and perspective changes as targets move around freely in the environment. Under these conditions, acquiring sufficient training examples to learn the dynamic relationship between position, face appearance and head-pose can be very expensive. Instead, a transfer learning approach is proposed in this work. Upon learning a weighted-distance function from many examples where the target position is fixed, we adapt these weights to the scenario where target positions are varying. The adaptation framework incorporates reliability of the different face regions for pose estimation under positional variation, by transforming the target appearance to a canonical appearance corresponding to a reference scene location. Experimental results confirm effectiveness of the proposed approach, which outperforms state-of-the-art by 9.5% under relevant conditions. To aid further research on this topic, we also make DPOSE- a dynamic, multi-view head-pose dataset with ground-truth publicly available with this paper.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
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
Murphy-Chutorian, E., Trivedi, M.M.: Head pose estimation in computer vision: A survey. IEEE PAMI 31, 607–626 (2009)
Tosato, D., Farenzena, M., Cristani, M., Spera, M., Murino, V.: Multi-class Classification on Riemannian Manifolds for Video Surveillance. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 378–391. Springer, Heidelberg (2010)
Zabulis, X., Sarmis, T., Argyros, A.A.: 3d head pose estimation from multiple distant views. In: BMVC (2009)
Orozco, J., Gong, S., Xiang, T.: Head pose classification in crowded scenes. In: BMVC, pp. 1–11 (2009)
Benfold, B., Reid, I.: Unsupervised learning of a scene-specific coarse gaze estimator. In: ICCV (2012)
Chen, C., Odobez, J.M.: We are not contortionists: coupled adaptive learning for head and body orientation estimation in surveillance video. In: CVPR (2012)
Voit, M., Stiefelhagen, R.: A system for probabilistic joint 3d head tracking and pose estimation in low-resolution, multi-view environments. In: ICVS, pp. 415–424 (2009)
Stiefelhagen, R., Bowers, R., Fiscus, J.G. (eds.): RT 2007 and CLEAR 2007. LNCS, vol. 4625. Springer, Heidelberg (2008)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 1345–1359 (2010)
Dai, W., Yang, Q., Xue, G.R., Yu, Y.: Boosting for transfer learning. In: ICML, pp. 193–200 (2007)
HOSDB: Imagery library for intelligent detection systems (i-lids). IEEE Crime and Security (2006)
Muñoz-Salinas, R., Yeguas-Bolivar, E., Saffiotti, A., Carnicer, R.M.: Multi-camera head pose estimation. Mach. Vis. Appl. 23, 479–490 (2012)
Yang, W., Wang, Y., Mori, G.: Efficient Human Action Detection Using a Transferable Distance Function. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) ACCV 2009, Part II. LNCS, vol. 5995, pp. 417–426. Springer, Heidelberg (2010)
Lim, J.J., Salakhutdinov, R., Torralba, A.: Transfer learning by borrowing examples for multiclass object detection. In: NIPS, pp. 118–126 (2011)
Kulis, B., Saenko, K., Darrell, T.: What you saw is not what you get: Domain adaptation using asymmetric kernel transforms. In: CVPR (2011)
Zhang, Y., Yeung, D.Y.: A convex formulation for learning task relationships in multi-task learning. In: UAI, pp. 733–742 (2010)
Zhang, Y., Yeung, D.Y.: Transfer metric learning by learning task relationships. In: KDD (2010)
Wang, X., Huang, X., Gao, J., Yang, R.: Illumination and Person-Insensitive Head Pose Estimation Using Distance Metric Learning. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 624–637. Springer, Heidelberg (2008)
Ricci, E., Odobez, J.M.: Learning large margin likelihoods for realtime head pose tracking. In: ICIP (2009)
Lanz, O.: Approximate bayesian multibody tracking. IEEE PAMI (2006)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)
Wang, X., Han, T.X., Yan, S.: An hog-lbp human detector with partial occlusion handling. In: ICCV, pp. 32–39 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
K. Rajagopal, A. et al. (2013). An Adaptation Framework for Head-Pose Classification in Dynamic Multi-view Scenarios. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds) Computer Vision – ACCV 2012. ACCV 2012. Lecture Notes in Computer Science, vol 7725. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37444-9_51
Download citation
DOI: https://doi.org/10.1007/978-3-642-37444-9_51
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37443-2
Online ISBN: 978-3-642-37444-9
eBook Packages: Computer ScienceComputer Science (R0)