Video Sensor-Based Complex Scene Analysis with

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.

[1]  Daryl J. Daley,et al.  An Introduction to the Theory of Point Processes , 2013 .

[2]  James M. Rehg,et al.  Temporal causality for the analysis of visual events , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  A. Walden.  A unified view of multitaper multivariate spectral estimation , 2000 .

[4]  Shaogang Gong,et al.  A Markov Clustering Topic Model for mining behaviour in video , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[6]  Vladimir Pavlovic,et al.  Sparse Granger causality graphs for human action classification , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[7]  Antonio Sánchez-Esguevillas,et al.  A Semantic Autonomous Video Surveillance System for Dense Camera Networks in Smart Cities , 2012, Sensors.

[8]  Mingzhou Ding,et al.  Evaluating causal relations in neural systems: Granger causality, directed transfer function and statistical assessment of significance , 2001, Biological Cybernetics.

[9]  C. Granger.  Investigating Causal Relations by Econometric Models and Cross-Spectral Methods , 1969 .

[10]  S Kullback,et al.  LETTER TO THE EDITOR: THE KULLBACK-LEIBLER DISTANCE , 1987 .

[11]  W. Eric L. Grimson,et al.  Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Mignon Park,et al.  An Adaptive Background Subtraction Method Based on Kernel Density Estimation , 2012, Sensors.

[13]  Jean-Marc Odobez,et al.  Bridging the past, present and future: Modeling scene activities from event relationships and global rules , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  M. Bartlett.  The Spectral Analysis of Point Processes , 1963 .

[15]  Hong Zhang,et al.  Exploring Techniques for Vision Based Human Activity Recognition: Methods, Systems, and Evaluation , 2013, Sensors.

[16]  Shuicheng Yan,et al.  Pair-activity classification by bi-trajectories analysis , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Subhashis Banerjee,et al.  Unsupervised Discovery of Activities and Their Temporal Behaviour , 2012, 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance.

[18]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[19]  Luc Van Gool,et al.  What's going on? Discovering spatio-temporal dependencies in dynamic scenes , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[20]  J. Geweke,et al.  Measurement of Linear Dependence and Feedback between Multiple Time Series , 1982 .

[21]  Mingzhou Ding,et al.  Analyzing multiple spike trains with nonparametric granger causality , 2009, Journal of Computational Neuroscience.