The International Arab Journal of Information Technology (IAJIT)


Vision-Based Human Activity Recognition Using LDCRFs

In this paper, an innovative approach for human activity relies on affine-invariant shape descriptors and motion flow is proposed. The first phase of this approach is to employ the modelling background that uses an adaptive Gaussian mixture to distinguish moving foregrounds from their moving cast shadows. Accordingly, the extracted features are derived from 3D spatio-temporal action volume like elliptic Fourier, Zernike moments, mass center and optical flow. Finally, the discriminative model of Latent-dynamic Conditional Random Fields (LCDRFs) performs the training and testing action processes using the combined features that conforms vigorous view-invariant task. Our experiment on an action Weizmann dataset demonstrates that the proposed approach is robust and more efficient to problematic phenomena than previously reported. It also can take place with no sacrificing real-time performance for many practical action applications.

[1] Ahmad M. and Lee S., Human Action Recognition Using Shape and CLG-Motion Flow from Multi-View Image Sequences, Pattern Recognition, vol. 41, no. 7, pp. 2237-2252, 2008.

[2] Bar-Shalom Y. and Li X., Estimation and Tracking: Principles, Techniques, and Software, Artech House, 1993.

[3] Bobick A. and Davis J., The Recognition of Human Movement Using Temporal Templates, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 3, pp. 257-267, 2001.

[4] Efros A., Berg A., Mori G., and Malik J., Recognizing Action at a Distance, in Proceedings of 9thIEEE International Conference on Computer Vision, Nice, pp. 726-733, 2003.

[5] Fathi A. and Mori G., Action Recognition by Learning Mid-Level Motion Features, in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, pp. Vision-Based Human Activity Recognition Using LDCRFs 395 1-8, 2008.

[6] Ganapathy S., Vijayakumar P., Yogesh P., and Kannan A., An Intelligent CRF Based Feature Selection for Effective Intrusion Detection, The International Arab Journal of Information Technology, vol. 13, no. 1, pp. 44-50, 2015.

[7] Gorelick L., Blank M., Shechtman E., Irani M., and Basri R., Actions as Space Time Shapes, Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no.12, pp. 2247-2253, 2007.

[8] Lafferty J., McCallum A., and Pereira F., Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data, in Proceedings of the 8th International Conference on Machine Learning, Williamstown, pp. 282-289, 2001.

[9] McCallum A., Efficiently Inducing Features of Conditional Random Fields, in Proceedings of the 9th Conference on Uncertainty in Artificial Intelligence, Acapulco, pp. 403-410, 2003.

[10] McKenna S., Raja Y., and Gong S., Tracking Colour Objects Using Adaptive Mixture Models, Image and Vision Computing, vol. 17, no. 3, pp. 225-231, 1999.

[11] Niebles J., Wang H., and Fei-Fei L., Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words, Journal of Computer Vision, vol. 79, no. 3, pp. 299-318, 2008.

[12] Nixon M. and Aguado A., Feature Extraction and Image Processing, Newnes, 2002.

[13] Poppe R., A Survey on Vision-Based Human Action Recognition, Image and Vision Computing, vol. 28, no. 6, pp. 976-990, 2010.

[14] Sadek S., Al-Hamadi A., Elmezain M., Michaelis B., and Sayed U., Human Activity Recognition via Temporal Moment Invariants, in Proceedings of 10th IEEE International Symposium on Signal Processing and Information Technology, Luxor, pp. 79-84, 2010.

[15] Sadek S., AI-Hamadi A., Krell G., and Michaelis B., Affine-Invariant Feature Extraction for Activity Recognition, ISRN Machine Vision, vol. 2013, pp.1-7, 2013.

[16] Shechtman E. and Irani M., Space-Time Behavior Based Correlation, in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, pp. 405-412, 2005.

[17] Zelnik-Manor L. and Irani M., Event-Based Analysis of Video, in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, pp. 1-8, 2001.

[18] Zhang Z., Hu Y., Chan S., and Chia L., Motion Context: A new Representation for Human Action Recognition, in Proceedings of European Conference on Computer Vision, Marseille, pp. 817-829, 2008. Mahmoud Elmezain was born in Egypt. Between1997 and 2004 he worked as demonstrator in Dept. of Statistic and Computer Science, Tanta University, Egypt. He received his Masters Degree in Computer Science from Helwan University, Egypt in 2004. He received PhD Degree in Computer Science from Institute for Electronics, Signal Processing and Communication sat Otto-von-Guericke-University of Magdeburg, Germany. His work focuses on image processing, pattern recognition, human-computer interaction and action recognition. Dr.-Ing. Elmezain is the author of more than 55 articles in peer-reviewed international journals and conferences. Ayoub Al-Hamadi was born in Yemen. He obtained his master s degree and PhD degree from Otto- von-Guericke-University of Magdeburg, Germany between 1997 and 2001. He had been a Junior Research Group Leader in 2003 at Magdeburg University, Germany. He obtained a position of Junior Professor for Neuro Information Technology in 2008. He obtained the Habilitation degree in the fields of Image Processing, Artificial Intelligence and Pattern Recognition in 2010. He is the author of more than 325 papers in international conferences, international journals and books.