Abstract
With the pervasive of the definition of the smart city, the data volume of the surveillance system, huge number of video surveillance devices is now rapidly expanding. The research to surveillance data mining and analytics has attracted increasing attention due to its applications. Cluster analysis as an important task of data mining in video surveillance has recently been highly explored. K-means algorithm is the most popular and widely-used partitional clustering algorithm in practice. However, traditional k-means algorithm suffers from sensitive initial selection of cluster centers, and it is not easy to specify the number of clusters in advance. In this paper, we propose a robust k-means algorithm that can automatically split and merge clusters which incorporates the new ideas in dealing with huge scale of video data. This novel algorithm not only addresses the sensitivity in selecting initial cluster centers, but also is resilient to the initial number of clusters. The performance is experimentally verified using synthetic and publicly available datasets. The experiments demonstrate the effectiveness and robustness of the proposed algorithm. Moreover, experiment is conducted on a real video surveillance dataset and the result shows that the novel approach can be applicated friendly in video surveillance.
Similar content being viewed by others
References
Abubaker M, Ashour W (2013) Efficient data clustering algorithms: improvements over K-means. Int J Intell Syst Appl 5(3):37–49
Agha MEI, Ashour WM (2012) Efficient and fast initializtion algorithm for K-means clustering. Intell Syst Appl 4(1):21–31
Ahamed Shafeeq BM, Hareesha KS (2012) Dynamic clustering of data with modified K-Means algorithm. International Conference on Information and Computer Networks (ICICN 2012), 27: 221–225
Arai K, Barakha AR (2007) Hierarchical K-means: an algorithm for centroids initialization for K-means. Reports of the Faculty of Science and Engineering, 36(1): 25–31
Bennewitz M, Burgard W, Cielniak G, Thrun S (2005) Learning motion patterns of people for compliant robot motion. Int J Rob Res 24(1):31–48
Chadha A, Kumar S (2014) An improved K-means clustering algorithm: a step forward for removal of dependency on K. 2014 International Conference on Reliability, Optimization and Information Technology. pp. 136–140
Clustering Datasets [Online]. Available: http://cs.joensuu.fi/sipu/datasets/
Dahlbom A, Niklasson L (2007) Trajectory clustering for coastal surveillance. FUSION 2007
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc 39(1):1–38
Deng A, Xiao B, Yuan H (2012) Adaptive K-means algorithm with dynamically changing cluster centers and K-value. Adv Mater Res 532–533:1373–7
Ester M, Kriegel HP, Sander J et al (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In Proc. of the 2nd International Conference on Knowledge Discovery and Data Mining. pp. 226–231
Han J, Kamber M (2006) Data mining: concepts and techniques, Second Edition. pp. 251–153
Hunter DR, Lange K (2004) A tutorial on MM algorithms. Am Stat 58:30–7
Jain A, Dubes R (1988) Algorithms for clustering data. Prentice Hall
Jamshidian M, Jennrich RI (1997) Acceleration of the EM algorithm by using quasi-newton methods. J R Stat Soc 59(2):569–87
Jiang F, Wu Y, Katsaggelos AK (2007) Abnormal event detection from surveillance video by dynamic hierarchical clustering. IEEE Int Conf Image Process 5:145–8
Katsavounidis I (1994) A new initialization technique for generalized Lloyd iteration. IEEE Signal Process Lett 1(10):144–6
Kaufman L, Rousseeuw PJ (1990) Finding groups in data. An introduction to cluster analysis. Wiley, Canada
Kwedlo W, Iwanowicz P (2010) Using genetic algorithm for selection of initial cluster centers for the K-means method. Lect Notes Comput Sci 6114(2):165–72
Leela V, Sakthipriya K, Manikandan R (2013) A comparative analysis between K-means and Y-means algorithms in fisher’s iris data sets. Int J Eng Technol 5(1):245–9
MacQueen JB (1967) Some methods for classification and analysis of multivariate observations. pp. 281–297
Matsuyama Y (2003) The α-EM algorithm: surrogate likelihood maximization using α-logarithmic information measures. IEEE Trans Inf Theory 49(3):692–706
Matsuyama Y (2011) Hidden Markov model estimation based on alpha-EM algorithm: discrete and continuous alpha-HMMs. International Joint Conference on Neural Networks, pp. 808–816
Mehar AM, Matawie K, Maeder A (2013) Determining an optimal value of K in K-means clustering. 2013 I.E. International Conference on Bioinformatics and Biomedicine, pp. 51–55
Meng X, Rubin DB (1993) Maximum likelihood estimation via the ECM algorithm: a general framework. Biometrika 80(2):267–78
Piciarelli C, Foresti GL (2006) On-line trajectory clustering for anomalous events detection. Pattern Recogn Lett 27(15):1835–42
Radhakrishna Rao C, Toutenburg H (1999) Linear models: least squares and alternatives, Second Edition. pp. 70–71
Shehroz A (2004) Cluster center initiation algorithm for K-means clustering. Pattern Recogn Lett 25:1293–302
Sung C, Feldman D, Rus D (2012) Trajectory clustering for motion prediction. 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1547–1552
UCI Machine Learning Repository. Available: http://archive.ics.uci.edu/ml/datasets.html
Vasquez D, Fraichard T, Laugier C (2009) Growing Hidden Markov Models: an incremental tool for learning and predicting human and vehicle motion. Int J Rob Res 28(11–12):1486–506
Xu R, Wunsch DII (2005) Survey of clustering algorithms. IEEE Trans Neural Netw 16(3):645–78
Yadav J, Sharma M (2013) Automatic K-detection algorithm. 2013 International Conference on Machine Intelligence and Research Advancement, pp. 269–273
Yang H, Xie L, Xie F (2007) Research on cluster remote video surveillance system. 2006 I.E. International Conference on Industrial Informatics, INDIN’06. pp. 1171–1174
Ye Y, Chen X, Zhou S et al (2006) Neighborhood density method for selecting initial cluster centers in K-means clustering. Lect Notes Comput Sci 3918:189–98
Yin J, Zhang Y, Gao L (2012) Accelerating expectation-maximization algorithms with frequent updates. Proceedings of the IEEE International Conference on Cluster Computing, pp. 275–283
Yu J, Chen Q (2002) The range of optimal class number of fuzzy cluster [J]. Sci China Ser E 32(2):274–80
Zhu J, Wang H (2010) An improved K-means clustering algorithm
Acknowledgments
This work is supported by Natural Science Foundation of China (No. 61272437, 61472236), Innovation Program of Shanghai Municipal Education Commission (No. 14ZZ150), Project of Shanghai Science and Technology Committee (14110500800) and Natural Science Foundation of Hainan (No. 20156235).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lei, J., Jiang, T., Wu, K. et al. Robust K-means algorithm with automatically splitting and merging clusters and its applications for surveillance data. Multimed Tools Appl 75, 12043–12059 (2016). https://doi.org/10.1007/s11042-016-3322-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3322-5