Abstract
Human action classification plays a challenging role in the field of robotics and other human–computer interaction systems. It also helps people in crime analysis, security tasks, and human support systems. The main purpose of this work is to design and implement a system to classify human actions in videos using encapsulated features and multi-objective deep belief network. Encapsulated features include space–time interest points, shape, and coverage factor. Initially, frames having actions had been separated from the input videos by means of structural similarity measure. Later, spatiotemporal interest points, shape and coverage factor are extracted and combined to form encapsulated features. To improve the accuracy in classification, MODBN classifier was designed by combining multi-objective dragonfly algorithm and deep belief network. Datasets such as Weizmann and KTH are used in MODBN classifier to carry the experimentation. Accuracy, sensitivity, and specificity are measured to evaluate the classification network. This proposed classifier with encapsulated features can produce better performance with 99% of accuracy, 97% of sensitivity, and 95% of specificity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes (2007)
Tong, M., Li, M., Bai, H., Ma, L., Zhao, M.: DKD–DAD: a novel framework with discriminative kinematic descriptor and deep attention-pooled descriptor for action recognition. Neural Comput. Appl. 1 (2019)
Jia, C.C., et al.: Incremental multi-linear discriminant analysis using canonical correlations for action recognition. Neurocomputing 83, 56–63 (2012)
Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior Recognition via Sparse Spatio-Temporal Features, pp. 65–72. IEEE (2005)
Schuldt, C., Barbara, L., Stockholm, S.: Recognizing human actions: a local SVM approach. In: Proceedings of 17th International Conference, vol. 3, pp. 32–36 (2004)
Moussa, M.M., Hemayed, E.E., El Nemr, H.A., Fayek, M.B.: Human action recognition utilizing variations in skeleton dimensions. Arab. J. Sci. Eng. 43, 597–610 (2018)
Huynh-The, T., Le, B.V., Lee, S., Yoon, Y.: Interactive activity recognition using pose-based spatio–temporal relation features and four-level Pachinko Allocation model. Inf. Sci. (NY) 369, 317–333 (2016)
Kong, Y., Jia, Y.: A hierarchical model for human interaction recognition. In: Proceedings of IEEE International Conference Multimedia Expo, pp. 1–6 (2012)
Bregonzio, M., Gong, S., Xiang, T.: Recognising action as clouds of space-time interest points. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1948–1955 (2009)
Liu, J., Shah, M.: Learning human actions via information maximization. In: 26th IEEE Conference Computer Vision and Pattern Recognition, CVPR (2008)
Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR 2009. IEEE Conference, pp. 1778–1785 (2009)
Wu, D., Shao, L.: Silhouette analysis-based action recognition via exploiting human poses. IEEE Trans. Circuits Syst. Video Technol. 23, 236–243 (2013)
Rodriguez, M., Orrite, C., Medrano, C., Makris, D.: A time flexible kernel framework for video-based activity recognition. Image Vis. Comput. 48–49, 26–36 (2016)
Li, H., Chen, J., Hu, R.: Multiple feature fusion in convolutional neural networks for action recognition. Wuhan Univ. J. Nat. Sci. 22, 73–78 (2017)
Wang, H., Yuan, C., Hu, W., Ling, H., Yang, W., Sun, C.: Action recognition using nonnegative action component representation and sparse basis selection. IEEE Trans. Image Process. 23(2), 570–581 (2014)
Li, W.X., Vasconcelos, N.: Complex activity recognition via attribute dynamics. Int. J. Comput. Vis. 122, 334–370 (2017)
Nigam, S., Khare, A.: Integration of moment invariants and uniform local binary patterns for human activity recognition in video sequences. Multimed. Tools Appl. 75, 17303–17332 (2016)
Hasan, M., Roy-Chowdhury, A.K.: A continuous learning framework for activity recognition using deep hybrid feature models. IEEE Trans. Multimed. 17, 1909–1922 (2015)
Meng, H., Pears, N., Bailey, C.: Human action classification using SVM_2K classifier on motion features, pp. 458–465 (2006)
Everts, I., Van Gemert, J.C., Gevers, T.: Evaluation of color spatio-temporal interest points for human action recognition. IEEE Trans. Image Process. 23, 1569–1580 (2014)
Laptev, I., Lindeberg, T.: Velocity adaptation of space-time interest points. In: Proceedings of International Conference on Pattern Recognition, vol. 1, pp. 52–56 (2004)
Vojt, J.: Deep neural networks and their implementation (2016)
KTH dataset from, http://www.nada.kth.se/cvap/actions/
Weizmann dataset from, http://www.wisdom.weizmann.ac.il/~vision/SpaceTimeActions.html
Sopharak, A., Uyyanonvara, B., Barman, S., Williamson, T.H.: Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods. Comput. Med. Imaging Graph. 32, 720–727 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sheeba, P.T., Murugan, S. (2020). Encapsulated Features with Multi-objective Deep Belief Networks for Action Classification. In: Mallick, P., Balas, V., Bhoi, A., Chae, GS. (eds) Cognitive Informatics and Soft Computing. Advances in Intelligent Systems and Computing, vol 1040. Springer, Singapore. https://doi.org/10.1007/978-981-15-1451-7_23
Download citation
DOI: https://doi.org/10.1007/978-981-15-1451-7_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1450-0
Online ISBN: 978-981-15-1451-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)