Unsupervised Discovery of Activities and Their Temporal Behaviour

This paper addresses the problem of discovering activities and their temporal significance in surveillance videos in an unsupervised manner. We propose a generative model that can jointly capture the activities and their behaviour over time. We use multinomial distribution over local motion features to model activities and a mixture distribution over their time stamps to capture the multi-modal temporal distribution of these activities. We give a Gibbs sampling algorithm to infer the parameters of the model. We demonstrate the effectiveness of our approach on real life surveillance feed of outdoor scenes.

[1]  Jean-Marc Odobez,et al.  Extracting and locating temporal motifs in video scenes using a hierarchical non parametric Bayesian model , 2011, CVPR 2011.

[2]  Juan Carlos Niebles,et al.  Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words , 2008, International Journal of Computer Vision.

[3]  Vera M. Kettnaker.  Time-dependent HMMs for visual intrusion detection , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[4]  Feng Niu,et al.  HMM-Based Segmentation and Recognition of Human Activities from Video Sequences , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[5]  Jean-Marc Odobez,et al.  Probabilistic Latent Sequential Motifs: Discovering Temporal Activity Patterns in Video Scenes , 2010, BMVC.

[6]  Subhashis Banerjee,et al.  Time based Activity Inference using Latent Dirichlet Allocation , 2009, BMVC.

[7]  Zhenjiang Miao,et al.  Multi-person activity recognition through hierarchical and observation decomposed HMM , 2010, 2010 IEEE International Conference on Multimedia and Expo.

[8]  Juan Carlos Niebles,et al.  Unsupervised Learning of Human Action Categories , 2006 .

[9]  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.

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

[11]  W. Eric L. Grimson,et al.  Unsupervised Activity Perception by Hierarchical Bayesian Models , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Andrew McCallum,et al.  Topics over time: a non-Markov continuous-time model of topical trends , 2006, KDD '06.