Histogram of Multi-Directional Gabor Filter Bank for Motion Trajectory Feature Extraction

AUTHOR(S):

Ngoc Nam Bui, Tan Dat Trinh, Min Kyung Park, Jin Young Kim

TITLE

Histogram of Multi-Directional Gabor Filter Bank for Motion Trajectory Feature Extraction

ABSTRACT

In this paper, we decompose motion flow using multidirectional Gabor filter bank to create robust descriptors for action recognition problem. The dense trajectory is utilized to allocate the Region of Interest (ROI) for extracting Gabor descriptors. In addition, the feature distribution is adopted instead of the conventional sum of energy. Our experiments are conducted in an open data set (UCF11) and our self-constructed one (CNU). The results indicate that the proposed feature outperforms all other ones in both individually and collectively.

KEYWORDS

Gabor histogram, GMM supervector, dense trajectory features

REFERENCES

[1] M. Blank, L. Gorelick, E. Shechtman, M. Irani, and R. Basri, "Actions as Space-Time Shapes," Proceeding of Tenth IEEE International Conference on Computer Vision, Beijing, vol. 2, no., pp. 1395 - 1402, Oct. 2005 2005.

[2] I. Laptev and T. Lindeberg, "Local Descriptors for Spatio-temporal Recognition," Proceeding of First International Workshop, SCVMA, vol. 3667, no., pp. 91-103, 2004.

[3] N. N. Bui and J. Y. Kim, "Human Action Recognition based on GMM-UBM Supervector using SVM with non-linear GMM KL and GUMI," Proceeding of Int. Conf. Digital Image Processing, vol. 9631, no., pp. 96311G-96311G-7, April 2015.

[4] J. Liu, J. Luo, and M. Shah, "Recognizing realistic actions from videos "in the wild"," Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1996 - 2003, 2009.

[5] H. Wang, A. Kläser, C. Schmid, and C.-L. Liu, "Dense Trajectories and Motion Boundary Descriptors for Action Recognition," International N. N. Bui et al. International Journal of Computers http://www.iaras.org/iaras/journals/ijc ISSN: 2367-8895 87 Volume 1, 2016 Journal of Computer Vision, vol. 103, no. 1, pp. 60- 79, May 2013.

[6] F. Perronnin, J. Sánchez, and T. Mensink, "Improving the Fisher Kernel for Large-Scale Image Classification," Proceeding of Computer Vision – ECCV, vol. 6314, no., pp. 143-156, January 2010.

[7] N. N. Bui, J. Y. Kim, and T. D. Trinh, "A nonlinear GMM KL and GUMI kernel for SVM using GMM-UBM supervector in home acoustic event classification," The Institute of Electronics, Information and Communication Engineers., vol. E97-A, no. 8, pp. 1791-1794, August, 2014.

[8] E. A. Perez, V. F. Mota, L. M. Maciel, D. Sad, and M. B. Vieira, "Combining gradient histograms using orientation tensors for human action recognition," Proceeding of 21st International Conference on Pattern Recognition (ICPR), pp. 3460-3463, 11-15 Nov. 2012 2012.

[9] M. Hasan and A. K. Roy-Chowdhury, "Incremental Activity Modeling and Recognition in Streaming Videos," Proceeding of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 796-803, 23-28 June 2014 2014.

[10] V. F. Mota, E. A. Perez, L. M. Maciel, M. B. Vieira, and P. H. Gosselin, "A tensor motion descriptor based on histograms of gradients and optical flow," Pattern Recognition Letters, vol. 39, no., pp. 85-91, 4/1/ 2014.

Cite this paper

Ngoc Nam Bui, Tan Dat Trinh, Min Kyung Park, Jin Young Kim. (2016) Histogram of Multi-Directional Gabor Filter Bank for Motion Trajectory Feature Extraction. International Journal of Computers, 1, 83-88