Tracking by Cluster Analysis of Feature Points and Multiple Particle Filters

A moving target produces a coherent cluster of feature points in the image plane. This motivates our novel method of tracking multiple targets by cluster analysis of feature points and multiple particle filters. First, feature points are detected by a Harris corner detector and tracked by a Lucas-Kanade tracker. Clusters of moving targets are then initialized by grouping spatially co-located points with similar motion using the EM algorithm. Due to the non-Gaussian distribution of the points in a cluster and the multi-modality resulting from multiple targets, multiple particle filters are applied to track all the clusters simultaneously: one particle filter is started for one cluster. The proposed method is well suited for the typical video surveillance configuration where the cameras are still and targets of interest appear relatively small in the image. We demonstrate the effectiveness of our method on different PETS datasets.

[1]  Thomas Manfred Rupp,et al.  Determination and exchange of supply information for co-operation in complex production networks , 2004, Robotics Auton. Syst..

[2]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[3]  Jiří Matas,et al.  Computer Vision - ECCV 2004 , 2004, Lecture Notes in Computer Science.

[4]  Sebastian Thrun,et al.  Learning Activity-Based Ground Models from a Moving Helicopter Platform , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[5]  Mubarak Shah,et al.  A noniterative greedy algorithm for multiframe point correspondence , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[7]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[8]  Arthur E. C. Pece,et al.  Generative-model-based tracking by cluster analysis of image differences , 2002, Robotics Auton. Syst..

[9]  Nando de Freitas,et al.  Sequential Monte Carlo Methods in Practice , 2001, Statistics for Engineering and Information Science.

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

[11]  Patrick Pérez,et al.  Maintaining multimodality through mixture tracking , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[12]  Gérard G. Medioni,et al.  Inference of Integrated Surface, Curve, and Junction Descriptions From Sparse 3D Data , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Etienne Mémin,et al.  A robust stochastic filter for point tracking in image sequences , 2004 .

[14]  J. Crowley,et al.  Multi-Modal Tracking of Interacting Targets Using Gaussian Approximations , 2001 .

[15]  James J. Little,et al.  A Boosted Particle Filter: Multitarget Detection and Tracking , 2004, ECCV.