“ Shape Activities ” : Dynamic Stochastic Models for Moving / Deforming Shapes with Application to Abnormal Activity Detection

The changing configuration of a group of moving landmarks can be modeled as a moving/deforming shape. The landmarks could be moving objects (people/vehicles/robots) or rigid parts of an articulated shape like the human body. The deformation of a moving/deforming shape can be split into rigid motion of an average shape and its non-rigid deformations. We use the term “shape activity” to denote a particular stochastic model for shape deformation. We propose dynamical models for non-rigid shape deformation and for motion. Noise in the observed landmark locations makes the system partially observed and the mapping between observation and shape space makes it non-linear. The partially observed shape activity model is used to represent an activity performed by a group of moving objects. An abnormal activity is then defined as a change in the shape activity model with change parameters being unknown. We propose a change detection strategy using particle filters which can detect both slow and drastic changes in partially observed nonlinear systems. Results are shown on a real abnormal activity detection problem involving multiple moving objects (treated as point objects).

[1]  J. Kent.  The Complex Bingham Distribution and Shape Analysis , 1994 .

[2]  I. Miller.  Probability, Random Variables, and Stochastic Processes , 1966 .

[3]  Sudhir P. Mudur,et al.  Mathematical Elements for Computer Graphics , 1985, Advances in Computer Graphics.

[4]  F. Gland,et al.  STABILITY AND UNIFORM APPROXIMATION OF NONLINEAR FILTERS USING THE HILBERT METRIC AND APPLICATION TO PARTICLE FILTERS1 , 2004 .

[5]  Anuj Srivastava,et al.  Statistical Shape Analysis , 2014, Computer Vision, A Reference Guide.

[6]  Rama Chellappa,et al.  Activity recognition using the dynamics of the configuration of interacting objects , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[7]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[8]  M. Alex O. Vasilescu,et al.  Recognizing action events from multiple viewpoints , 2001, Proceedings IEEE Workshop on Detection and Recognition of Events in Video.

[9]  Rama Chellappa,et al.  Probabilistic Human Recognition from Video , 2002, ECCV.

[10]  Andrew Blake,et al.  A probabilistic contour discriminant for object localisation , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[11]  Lorenzo Torresani,et al.  Space-Time Tracking , 2002, ECCV.

[12]  Wolfram Burgard,et al.  Tracking multiple moving targets with a mobile robot using particle filters and statistical data association , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[13]  B. Azimi-Sadjadi,et al.  Change detection for nonlinear systems; a particle filtering approach , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[14]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[15]  Ramakant Nevatia,et al.  Description and tracking of moving articulated objects , 1994, Systems and Computers in Japan.

[16]  A. Doucet,et al.  A survey of convergence results on particle ltering for practitioners , 2002 .

[17]  Rama Chellappa,et al.  Statistical shape theory for activity modeling , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[18]  W. Eric L. Grimson,et al.  Using adaptive tracking to classify and monitor activities in a site , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[19]  Jitendra Malik,et al.  Automatic Symbolic Traffic Scene Analysis Using Belief Networks , 1994, AAAI.

[20]  Ralph Roskies,et al.  Fourier Descriptors for Plane Closed Curves , 1972, IEEE Transactions on Computers.

[21]  Lihi Zelnik-Manor,et al.  Event-based analysis of video , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[22]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[23]  Timothy F. Cootes,et al.  Training Models of Shape from Sets of Examples , 1992, BMVC.

[24]  Thad Starner,et al.  Visual Recognition of American Sign Language Using Hidden Markov Models. , 1995 .

[25]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[26]  Stefano Soatto,et al.  DEFORMOTION: Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images , 2002, ECCV.

[27]  Yi Zhou,et al.  Bayesian tangent shape model: estimating shape and pose parameters via Bayesian inference , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[28]  Aaron F. Bobick,et al.  Action recognition using probabilistic parsing , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[29]  T. K. Carne,et al.  Shape and Shape Theory , 1999 .

[30]  Timothy J. Robinson,et al.  Sequential Monte Carlo Methods in Practice , 2003 .

[31]  Stefano Soatto,et al.  Monte Carlo filtering on Lie groups , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[32]  Christoph Bregler,et al.  Learning and recognizing human dynamics in video sequences , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.