Classification of complex pedestrian activities from trajectories

We propose a method to classify human trajectories, modeled by a set of motion vector fields, each tailored to describe a specific motion regime. Trajectories are modeled as being composed of segments corresponding to different motion regimes, each generated by one of the underlying motion fields. Switching among the motion fields follows a probabilistic mechanism, described by a field of stochastic matrices. This yields a space-dependent motion model which can be estimated using an expectation-maximization (EM) algorithm. To address the model selection question (how many fields to use?), we adopt a discriminative criterion based on classification accuracy on a held out set. Experiments with real data (human trajectories in a shopping mall) illustrate the ability of the proposed approach to classify complex trajectories into high level classes (client versus non-client).

[1]  Tim J. Ellis,et al.  Automatic learning of an activity-based semantic scene model , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[2]  Alex Pentland,et al.  Pfinder: real-time tracking of the human body , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[3]  W. Eric L. Grimson,et al.  Learning Semantic Scene Models by Trajectory Analysis , 2006, ECCV.

[4]  Mubarak Shah,et al.  A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  A. Lanterman.  Schwarz, Wallace, and Rissanen: Intertwining Themes in Theories of Model Selection , 2001 .

[6]  W. Eric L. Grimson,et al.  Trajectory analysis and semantic region modeling using a nonparametric Bayesian model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Mubarak Shah,et al.  View-Invariant Representation and Recognition of Actions , 2002, International Journal of Computer Vision.

[8]  Eamonn J. Keogh,et al.  Scaling up dynamic time warping for datamining applications , 2000, KDD '00.

[9]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[10]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[11]  Tieniu Tan,et al.  Similarity based vehicle trajectory clustering and anomaly detection , 2005, IEEE International Conference on Image Processing 2005.

[12]  Dimitrios Gunopulos,et al.  Discovering similar multidimensional trajectories , 2002, Proceedings 18th International Conference on Data Engineering.

[13]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[14]  Bo Thiesson,et al.  Discriminative Model Selection for Density Models , 2003, AISTATS.

[15]  Mário A. T. Figueiredo,et al.  Trajectory analysis in natural images using mixtures of vector fields , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).