Human Action Recognition Based on Ridgelet Transform and SVM

In this paper, a novel algorithm based on Ridgelet Transform and support vector machine is proposed for human action recognition. The Ridgelet transform is a directional multi-resolution transform and it is more suitable for describing the human action by performing its directional information to form spatial features vectors. The dynamic transition between the spatial features is carried out using both the Principal Component Analysis and clustering algorithm K-means. First, the Principal Component Analysis is used to reduce the dimensionality of the obtained vectors. Then, the kmeans algorithm is then used to perform the obtained vectors to form the spatio-temporal pattern, called set-of-labels, according to given periodicity of human action. Finally, a Support Machine classifier is used to discriminate between the different human actions. Different tests are conducted on popular Datasets, such as Weizmann and KTH. The obtained results show that the proposed method provides more significant accuracy rate and it drives more robustness in very challenging situations such as lighting changes, scaling and dynamic environment

Authors:

• A. Ouanane
• A. Serir

Keywords:

• Human action
• Ridgelet Transform
• PCA
• K-means
• SVM.

References:

[1] J. C. Niebles and F.Li. "A hierarchical model of shape and appearance
for human action classification," in Proc. IEEE Conf. Comput. Vis.
Pattern Recog., Jun.17-22,pp. 1-8. 2007.
[2] C.Rougier, J.Meunier, A. St-Arnaud, and J.Rousseau. "Fall detection
from human shape and motion history using video surveillance," in
Proc.21st Int. Conf. Adv. Inf. Netw. Appl. Workshops, pp. 875-880.
2007.
[3] S. Ali and M. Shah. "Human Action Recognition in Videos Using
Kinematic Features and Multiple Instance Learning", IEEE Transactions
on Pattern Analysis and Machine Intelligence (PAMI), Volume 32, Issue
2, pp: 288-303, 2010.
[4] E.B. Ermis, V. Saligrama, P. Jodoin and J. Konrad. "Motion
segmentation and abnormal behavior detection via behavior clustering,"
in Proc. IEEE Int. Conf. Image Process., Oct. 12-15, pp. 769-772.2008.
[5] J. Li, Q. Pan, H. Zhang, P. Cui. "Image recognition using Radon
transform," Intelligent Transportation Systems,. Proceedings. IEEE,
vol.1, no., pp. 741- 744. 2003.
[6] M. Singh, M. Mandal, A. Basu. "Pose recognition using the Radon
transform". In: 48th Midwest Symposium on Circuits and Systems, pp.
1091-1094. 2005.
[7] Y. Wang, K. Huang, T. Tan. "Human activity recognition based on R
transform". In: IEEE Conference on Computer Vision and Pattern
Recognition, CVPR, pp. 1-8. 2007.
[8] A. Ouanane and A. Serir. "Fingerprint Compression by Ridgelet
Transform", IEEE ISSPIT, 16-19 Décembre 2008 Sarajevo
[9] Z. Zhang, H. Yu, J. Zhang, X. Zhang. "Digital image watermark
embedding and blind extracting in the ridgelet domain", Journal of
Communication and Computer, vol.3, No.5.pp.1-7, may 2006.
[10] Candes, E. " Ridgelets: theory and applications," Ph.D. thesis,
Department of Statistics, Stanford University; 1998.
[11] J. L. Starck, E. J. Candès and D. L. Donoho. The curvelet transform for
image denoising. IEEE Transactions on Image Processing, vol.11, pp.
670-684. 2000
[12] L. Sirovich and M. Kirby. "Low dimensional procedure for the
characterization of human faces". Journal of the Optical Society of
America. A, Optics, Image Science, and Vision, vol 4(3), pp.519-524.
1987.
[13] I.T.Jolliffe. " Principal component analysis". Springer, New York. 2002.
[14] Y. Wang, H. Jiang, M. Drew, Z. Li, G.Mori. "Unsupervised discovery of
action classes". IEEE Computer Vision and Pattern Recognition. vol.2,
no., pp.1654-1661, 2006.
[15] V.N. Vapnik. "The Nature of Statistical Learning Theory". New York:
Springer-Verlag,1995.
[16] M.Blank, L.Gorelick, E.Shechtman, M.Irani and R. Basri. "Actions as
space-time shapes," in Proc. IEEE Int. Conf. Comput. Vision, pp. 1395-
1402. 2005.
[17] C. Schuldt, I. Laptev, and B.I Caputo. "Recognizing human actions: a
local SVM approach". ICPR (17), pp. 32-36, 2004.
[18] C.-W. Hsu and C.-J. Lin. "A comparison of methods for multi-class
support vector machines," IEEE Trans. Neural Netw. , vol. 13, no. 2, pp.
415-425, Mar. 2002.
[19] C.C. Chang and C.J Lin. "LIBSVM: A Library for Support Vector
Machines", 2001.http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[20] J. Liu and M. Shah. "Learning Human Actions via Information
Maximization," Proc. IEEE Conf. Computer Vision and Pattern
Recognition, 2008.
[21] I. Laptev.I, M. Marsza¶Çâí, C.Schmid and B. Rozenfeld. "Learning realistic
human actions from movies". CVPR, pp 1-8, 2008.
[22] K. Schindler and L.V. Gool. "Action snippets: how many frames does
human action recognition require". In: CVPR, pp. 1-8, 2008.