Activity Recognition using Dynamic Bayesian Networks with Automatic State Selection

Applying advanced video technology to understand activity and intent is becoming increasingly important for intelligent video surveillance. We present a general model of a d-level dynamic Bayesian network to perform complex event recognition. The levels of the network are constrained to enforce state hierarchy while the dth level models the duration of simplest event. Moreover, in this paper we propose to use the deterministic annealing clustering method to automatically discover the states for the observable levels. We used real world data sets to show the effectiveness of our proposed method.

[1]  Yoram Singer,et al.  The Hierarchical Hidden Markov Model: Analysis and Applications , 1998, Machine Learning.

[2]  David J. Spiegelhalter,et al.  Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[3]  Jake K. Aggarwal,et al.  Recognition of Composite Human Activities through Context-Free Grammar Based Representation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[4]  Nando de Freitas,et al.  Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks , 2000, UAI.

[5]  Pradeep Buddharaju,et al.  Activity Awareness: from Predefined Events to New Pattern Discovery , 2006, Fourth IEEE International Conference on Computer Vision Systems (ICVS'06).

[6]  Larry S. Davis,et al.  Multivalued Default Logic for Identity Maintenance in Visual Surveillance , 2006, ECCV.

[7]  Svetha Venkatesh,et al.  Activity recognition and abnormality detection with the switching hidden semi-Markov model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  François Brémond,et al.  Automatic Video Interpretation: A Recognition Algorithm for Temporal Scenarios Based on Pre-compiled Scenario Models , 2003, ICVS.

[9]  Keiji Kanazawa,et al.  A model for reasoning about persistence and causation , 1989 .

[10]  K. Rose.  Deterministic annealing for clustering, compression, classification, regression, and related optimization problems , 1998, Proc. IEEE.

[11]  Xavier Boyen,et al.  Tractable Inference for Complex Stochastic Processes , 1998, UAI.

[12]  Isaac Cohen,et al.  Multiple Hypothesis Target Tracking Using Merge and Split of Graph's Nodes , 2006, ISVC.

[13]  Fatih Murat Porikli,et al.  Event Detection by Eigenvector Decomposition Using Object and Frame Features , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[14]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .

[15]  Ramakant Nevatia,et al.  Bayesian framework for video surveillance application , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[17]  M. Thonnat,et al.  Video understanding for metro surveillance , 2004, IEEE International Conference on Networking, Sensing and Control, 2004.