An Action Recognition Model Based on the Bayesian Networks

Abstract:

In this paper, we propose a novel human action recognition method based on Bayesian network model and high-level semantic concept (human action attribute). Firstly, we extract 3D-SIFT descriptors for each spatio-temporal interest point in the videos. Secondly, the bag of words is used as the low-level feature to represent these videos. Finally, Bayesian networks related to action attributes are trained based on MAP (Maximum A Posterior Probability) to recognize human behavior. The experimental results show that the proposed model is effective on action recognition.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 1886-1889
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.1886
• Online since: February 2014
• Authors: Wen Qiang Chen, Guo Qiang Xiao*, Xiao Qin Tang
• Keywords: 3D-SIFT, Action Recognition, Bayesian Network (BN), Spatio-Temporal Interest Point

References

[1] Laptev I. On space-time interest points[C]. IJCV，2005，64. 107-123.

[2] Dollar P, Rabaud V, Cottrell G, et al. Behavior recognition via sparse spatio-temporal features[C]. VS-PETS，(2005).

DOI: 10.1109/vspets.2005.1570899

[3] Willems Geert, Tuytelaars Tinne, Van Gool Luc. An efficient dense and scale-invariant spatio-temporal interest point detector[C]. Proceedings of European Conference on Computer Vision． Marseille: IEEE, 2008, 650-663.

DOI: 10.1007/978-3-540-88688-4_48

[4] Scovanner Paul，Ali Saad，Shah Mubarak． A 3-dimensional SIFT descriptor and its application to action recognition [C]. Proceedings of International Conference on Multimedia. New York: IEEE, 2007, 56-60.

DOI: 10.1145/1291233.1291311

[5] Di Wu., et al. Silhouette Analysis-Based Action Recognition Via Exploiting Human Poses[C]. IEEE Transaction on Circuits and Systems for Video Technology, 2013, 23(2).

DOI: 10.1109/tcsvt.2012.2203731

[6] Kong, Y., & Zhang, X. Adaptive learning codebook for action recognition[C]. Pattern Recognition Letters, 2011, 32, 1178–1186.

DOI: 10.1016/j.patrec.2011.03.006

[7] Schuldt, C., Laptev, I., & Caputo, B. Recognizing human actions: A local svm approach[C]. In ICPR, 2004, 32-36.

DOI: 10.1109/icpr.2004.1334462

[8] Huang, W., & Wu,Q. M. J. Human action recognition based on Self Organizing Map[C]. IEEE International Conference on Digital Object Identifier, 2010, 2030-(2033).

[9] Zhang, E., & Zhao, Y.Q. A Multi-scale Conditional Random Field Model for Human Action Recognition[C]. CISP , 2012, 77-81.

[10] Wang, H ., Kl¨aser, A ., Schmid, C ., & Liu, C.L. Action recognition by dense trajectories[C]. Proc IEEE Conf: Computer Vision and Pattern Recognition, 2011, 3169-3176.

[11] Kovashka, A ., & Grauman, K. Learning a hierarchy of discriminative space-time neighborhood features for human action recognition[C]. Proc IEEE Conf: Computer Vision and Pattern Recognition, 2010, 2046-(2053).

DOI: 10.1109/cvpr.2010.5539881

[12] Liu Jingen, Kuipers Benjamin, Savarese Silvio. Recognizing human actions by attributes[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Colorado Springs : IEEE, 2011 , 3337-3344.

DOI: 10.1109/cvpr.2008.4587527

[13] Liu Quan-zhong, Chen C, Zhang Yang, et al. Feature selection for support vector machines with RBF kernel[J]. Artificial Intelligence Review, 2011, 36(2), 99-115.

DOI: 10.1007/s10462-011-9205-2

[14] Cooper G, Hersk ovits E. A Bayesian method for the induction of probabilistic networks from data[J]. Machine Learning, 1992, 9, 309-347.