Abstract Human action recognition is a very important component of visual surveillance systems. The demand for automatic surveillance systems play a crucial role in the circumstances where continuous patrolling by human guards are not possible. The analysis in surveillance scenarios often requires the detection of certain specific human actions. The automated recognition of human actions in detecting certain human actions are considered here. The main aim is to develop a novel 3D Convolutional Neural Network (CNN) model for human action recognition in realistic environment. The features are extracted from both the spatial and the temporal dimensions by performing 3D convolutions, by which, capturing the motion information encoded in multiple adjacent frames. The evolved model generates multiple information from the input frames, and the information from all the channels are combined and that is to be the final feature. The developed model automatically tends to recognize specific human actions which needs attention in the real world environment like in pathways or in corridors of any organization. This proposed work is well suitable for the situations like where continuous patrolling of humans are not possible, to prevent certain human actions which are not allowed inside the organisation premises.

References

[1] Barnachon M., Bouakaz S., Boufama B., and Guillou E., Ongoing Human Action Recognition with Motion Capture, Pattern Recognition, vol. 47, no. 1, pp. 238-247, 2014.

[2] Charara N., Jarkass I., Sokhn M., and Khaled O., ADABeV: Automatic Detection of Abnormal Behavior in Video Surveillance, in Proceedings of International Conference on Image, Signal and Vision Computing, Oslo, pp.172-178, 2012.

[3] Duffner S. and Garcia C., An Online Backpropagation Algorithm with Validation Error-Based Adaptive Learning Rate, in Proceedings of the 17th international conference Artificial Neural Networks, Berlin, pp. 249-258, 2007.

[4] El-Sisi A., Design and Implementation Biometic Access Control System using Fingerprint for Restricted Area Based on Gabor Filter, The International Arab Journal of Information Technology, vol. 8, no. 4, pp. 355-363, 2011.

[5] Fan J., Xu W., Wu Y., and Gong Y., Human Tracking using Convolutional Neural Networks, IEEE Transactions on Neural Networks, vol. 21, no. 10, pp. 1610-1623, 2010.

[6] Gowsikhaa D., Abirami S., and Baskaran R., Automated Human Behaviour Analysis from Surveillance Videos: A Survey, Artificial Intelligence Review, vol. 42, no. 4, pp. 747-765, 2014.

[7] Gowsikhaa D., Manjunath M., and Abirami S., Suspicious Human Activity Detection from Surveillance Videos, International Journal on Internet and Distributed Computing Systems, vol. 2, no. 2, pp. 141-148, 2012.

[8] Guo Y., Chen Y., Tang F., Li A., Luo W., and Liu M., Object Tracking using Learned Feature Manifolds, Computer Vision and Image Understanding, vol. 118, pp. 128-139, 2014.

[9] Han J. and Kamber M., Data Mining: Concepts and Techniques, Morgan Kaufmann Publisher, 2006.

[10] Huo F. and Hendriks E., Multiple People Tracking and Pose Estimation with Occlusion Estimation, Computer Vision and Image Understanding, vol. 116, no. 5, pp. 634-647, 2012.

[11] Huo F. and Hendriks E., Real Time Multiple People Tracking and Pose Estimation, in Proceedings of the 1st ACM International Workshop on Multimodal Pervasive Video Analysis, Firenze, pp. 5-10, 2010.

[12] Iosifidis A., Tefas A., and Pitas I., Minimum Class Variance Extreme Learning Machine for Human Action Recognition, IEEE Transactions on Circuits and Systems for Video Technology, vol. 23, no. 11, pp. 1968-1979, 2013.

[13] Ji S., Xu W., Yang M., and Yu K., 3D Convolutional Neural Networks for Human Action Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 1, pp. 221-231, 2013.

[14] Oluwatoyin P. and Wang K., Video-Based Abnormal Human Behavior Recognition-A Review, IEEE Transactions on Systems, Man and Cybernetics-Part C: Applications and Review, vol. 42, no. 6, pp. 865-878, 2012.

[15] Paul M., Haque S., and Chakraborty S., Human Detection in Surveillance Videos and its Applications-A Review, EURASIP Journal on Advances in Signal Processing, pp. 1-16, 2013.

[16] Yao B., Liu Z., Nie B., and Zhu S., Animated Pose Templates for Modelling and Detecting Human Actions, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 3, pp. 436-452, 2013. 700 The International Arab Journal of Information Technology, Vol. 15, No. 4, July 2018 Sathyashrisharmilha Pushparaj received bachelors degree and masters degree in Computer Science and Engineering from Anna University of Chennai, India, in 2012 and 2014 respectively. Her current research interests include computer vision, pattern recognition and machine learning. Sakthivel Arumugam is currently working as a Professor in Department of Information Technology, Woldia University, Woldia, Ethiopia. He has 15 years of experience in research and teaching. He obtained his BE, ME and Ph.D. degrees in Computer Science and Engineering. His areas of interest are mobile computing, soft computing, Cloud Computing, Green Computing and Security models. He has published 10 papers in international journals and 5 papers in international/national conferences. He is reviewer of IAJIT and IEEE and got the best active reviewer award twice. He reviewed two text books published by Oxford University Press and TMGH in India. He is a life member of ISTE, ACCS and IAENG.