Multi-object particle filter tracking with automatic event analysis

The automatic video content analysis is an important step to provide the content-based video coding, indexing and retrieval. It is also a key issue to the event analysis in video surveillance. In this paper, an automatic event analysis approach is presented. It is based on our previous method of Multi-object Particle Filter Tracking with Dual Consistency Check. The multiple non-rigid objects are first tracked individually in parallel by multi-resolution technique and particle filter method. The events including object presence and occlusion identification are then detected and analyzed by measuring the Goodness-of-Fit Coefficient based on Schwartz's inequality and the Backward Projection. The method is then tested in different indoor and outdoor environments with cluttered background. The experimental results show the robustness and the effectiveness of the method.

[1]  Ramakant Nevatia,et al.  Event Detection and Analysis from Video Streams , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Larry S. Davis,et al.  Multi-resolution Tracking in Space and Time , 2008, 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing.

[3]  Jordi Gonzàlez,et al.  Robust Multiple-People Tracking Using Colour-Based Particle Filters , 2007, IbPRIA.

[4]  Jianping Fan,et al.  An automatic algorithm for semantic object generation and temporal tracking , 2002, Signal Process. Image Commun..

[5]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 2019, Texts in Computer Science.

[6]  Bhavani M. Thuraisingham,et al.  A framework for a video analysis tool for suspicious event detection , 2005, MDM@KDD.

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

[8]  Anastasios D. Doulamis,et al.  Dynamic tracking re-adjustment: a method for automatic tracking recovery in complex visual environments , 2010, Multimedia Tools and Applications.

[9]  Jenny Benois-Pineau,et al.  Multi-resolution tracking of a non-rigid target with particle filters for low and variable frame-rate videos , 2009, 2009 10th Workshop on Image Analysis for Multimedia Interactive Services.

[10]  Edward H. Adelson,et al.  PYRAMID METHODS IN IMAGE PROCESSING. , 1984 .

[11]  Jenny Benois-Pineau,et al.  A multi-resolution particle filter tracking with a dual consistency check for model update in a multi-camera environment , 2010, 11th International Workshop on Image Analysis for Multimedia Interactive Services WIAMIS 10.

[12]  J. Hernández-Andrés,et al.  Colorimetric and spectroradiometric characteristics of narrow-field-of-view clear skylight in Granada, Spain. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.

[13]  Dominique Barba,et al.  Tracking of Objects in Video Scenes with Time Varying Content , 2002, EURASIP J. Adv. Signal Process..

[14]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 1997, Texts in Computer Science.

[15]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[16]  H. Kritikos.  Optimal signal-to-noise ratio for linear arrays by the Schwartz inequality , 1963 .

[17]  Luc Van Gool,et al.  An adaptive color-based particle filter , 2003, Image Vis. Comput..