In this report, we propose a novel framework to explore the activity interactions and temporal dependencies between activities in complex video surveillance scenes. Under our framework, a low-level codebook is generated by an adaptive quantization with respect to the activeness criterion. The Hierarchical Dirichlet Processes (HDP) model is then applied to automatically cluster low-level features into atomic activities. Afterwards, the dynamic behaviors of the activities are represented as a multivariate point-process. The pair-wise relationships between activities are explicitly captured by the non-parametric Granger causality analysis, from which the activity interactions and temporal dependencies are discovered. Then, each video clip is labeled by one of the activity interactions. The results of the real-world traffic datasets show that the proposed method can achieve a high quality classification performance. Compared with traditional K-means clustering, a maximum improvement of 19.19% is achieved by using the proposed causal grouping method.
References
[1]
Wang, X.G.; Ma, X.X.; Grimson, W.E.L. Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models. IEEE Trans. Patt. Anal. Mach. Intell. 2008, 31, 539–555.
[2]
Xu, X.; Tang, J.; Zhang, X.; Liu, X.; Zhang, H.; Qiu, Y. Exploring techniques for vision based human activity recognition: Methods, systems, and evaluation. Sensors 2013, 13, 1635–1650.
[3]
Calavia, L.; Baladrn, C.; Aguiar, J.M.; Carro, B.; Snchez-Esguevillas, A. A semantic autonomous video surveillance system for dense camera networks in smart cities. Sensors 2012, 12, 10407–10429.
[4]
Lee, J.; Park, M. An adaptive background subtraction method based on kernel density estimation. Sensors 2012, 12, 12279–12300.
[5]
Hospedales, T.; Gong, S.G.; Xiang, T. A Markov Clustering Topic Model for Mining Behaviour in Video. Proceedings of the IEEE 12th International Conference on Computer Vision, Kyoto, Japan, 29 September–2 October 2009; pp. 1165–1172.
[6]
Kuettel, D.; Breitenstein, M.D.; van Gool, L.; Ferrari, V. What's going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes. Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 13–18 June 2010; pp. 1951–1958.
[7]
Varadarajan, J.; Emonet, R.; Odobez, J.M. Bridging the Past, Present and Future: Modeling Scene Activities from Event Relationships and Global Rules. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 16–21 June 2012; pp. 2096–2103.
[8]
Faruquie, T.A.; Banerjee, S.; Prem, K.K. Unsupervised Discovery of Activities and Their Temporal Behaviour. Proceedings of the 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, Beijing, China, 18–21 September 2012; pp. 100–105.
Granger, C.W.J. Investigating causal relations by econometric models and cross-spectral methods. Econometrica 1969, 37, 424–438.
[12]
Zhou, Y.; Yan, S.; Huang, T.S. Pair-activity Classification by Bi-trajectories Analysis. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA, 23-28 June 2008; pp. 1–8.
[13]
Prabhakar, K.; Sangmin, O.; Wang, P.; Abowd, G.D.; Rehg, J.M. Temporal Causality for the Analysis of Visual Events. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 13-18 June 2010; pp. 1967–1974.
[14]
Yi, S.; Pavlovic, V. Sparse Granger Causality Graphs for Human Action Classification. Proceedings of the 21st International Conference on Pattern Recognition, Tsukuba Science City, Japan, 11–15 November 2012.
[15]
Daley, D.J.; Vere-Jones, D. An Introduction to the Theory of Point Processes; Springer: New York, NY, USA, 2003.
[16]
Nedungadi, A.; Rangarajan, G.; Jain, N.; Ding, M. Analyzing multiple spike trains with nonparametric granger causality. J. Comput. Neurosci. 2008, 27, 55–64.
[17]
Kullback, S. Letter to the editor: The KullbackLeibler distance. Am. Stat. 1987, 41, 340–341.
[18]
Walden, A.T. A unified view of multitaper multivariate spectral estimation. Biometrika 2000, 87, 767–788.
[19]
Bartlett, M.S. The spectral analysis of point processes. J. R. Stat. Soc. 1963, 25, 264–296.
[20]
Geweke, J. Measurement of linear dependence and feedback between multiple time series. J.Am. Stat. Assoc. 1982, 77, 304–313.
[21]
Ding, M.Z.; Chen, Y.H.; Bressler, S.L. Granger causality: Basic Theory and Applications to Neuroscience; Wiley-VCH Verlage: Weinheim, Germany, 2006; pp. 437–460.
[22]
Kaminski, M.; Ding, M.; Truccolo, W.A.; Bressler, S.L. Evaulating causal relations in neural systems: Granger causality, directed transfer function and statistical assessment significance. Biol. Cybern. 2001, 85, 145–157.
