Abstract
Considering the problems that initial clustering center selection is very sensitive to clustering results, it is easy to fall into local optimum and only globular clusters can be found for the k-means algorithm in human action recognition. This paper presents a method based on maximum entropy fuzzy clustering and a new interest points detecting method for human action recognition. Firstly, the interest points of the videos are detected by the new approach, and the 3D-SIFT features of the points are extracted, and then, the features of the training videos are clustered generating video words based on maximum entropy fuzzy clustering algorithm to construct the codebook. In the end, the histogram based on the codebook for every video is built, which is used to classify targets in the SVM multi-class classifier. Experimental results show that the proposed method can effectively improve the expression ability of the codebook and the efficiency of the recognition of human action.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Laptev I (2005) On space-time interest points. Int J Comput Vision 64(2):107–123
Wu D et al (2013) Silhouette analysis-based action recognition via exploiting human poses. IEEE Trans Circ Syst Video Technol 23(2):236–243
Willems G, Tuytelaars T, Luc VG (2008) An efficient dense and scale-invariant spatio-temporal interest point detector. In: 10th European conference on computer vision–ECCV, pp 650–663
Kong Y, Zhang X (2011) Adaptive learning codebook for action recognition. Pattern Recogn Lett 32:1178–1186
Dollár P, Rabaud V, Cottrell G, Belongie S (2005) Behavior recognition via sparse spatio-temporal features. IEEE
Scovanner P, Ali S, Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition. In: ACM multimedia, pp 357–360
Harris C, Stephens M (1988) A combined corner and edge detector. In: Proceedings of the 4th Alvey vision conference, Manchester, pp 147–151
Horn B, Schunck B (1981) Determining optical flow. Artif Intell 17:185–203
Amir HS et al (2012) Evaluation of local spatio-temporal salient feature detectors for human action recognition. In: Ninth conference on computer and robot vision
Schuldt C, Laptev I, Caputo B (2004) Recognizing human actions: a local SVM approach. In: ICPR, pp 32–36
Ghorbani M (2005) Maximum entropy-based fuzzy clustering by using L1-norm space. Turk J Math 29:431–438
Huang W, Wu QMJ (2010) Human action recognition based on self organizing map. In: IEEE international conference on digital object identifier, pp 2030–2033
Zhang E, Zhao YQ (2012) A multi-scale conditional random field model for human action recognition. In: CISP, pp 77–81
Wang H, Kläser A, Schmid C, Liu CL (2011) Action recognition by dense trajectories. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 3169–3176
Kovashka A, Grauman K (2010) Learning a hierarchy of discriminative space-time neighborhood features for human action recognition. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 2046–2053
Wang H, Ullah MM, Kläse A, Laptev I, Schmid C (2009) Evaluation of local spatio-temporal features for action recognition. In: Proceedings of British machine vision conference
Guha T, Ward RK (2012) Learning sparse representations for human action recognition. IEEE Trans Pattern Anal Mach Intell 34(8):1576–1588
Yeffet L, Wolf L (2009) Local trinary patterns for human action recognition. In: Proceedings of IEEE international conference on computer vision, pp 492–497
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tang, X., Xiao, G. (2014). Action Recognition Based on Maximum Entropy Fuzzy Clustering Algorithm. In: Wen, Z., Li, T. (eds) Foundations of Intelligent Systems. Advances in Intelligent Systems and Computing, vol 277. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54924-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-54924-3_15
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54923-6
Online ISBN: 978-3-642-54924-3
eBook Packages: EngineeringEngineering (R0)