Multiple target tracking in video data using labeled random finite set

This paper demonstrates how the δ-Generalized Labeled Multi-Bernoulli (δ-GLMB) filter can be applied to track moving targets on videos. The tracking is performed directly on the original images which are not preprocessed into point measurements and estimates the number of targets on frame along with their states. In that sense this concept bears resemblance to the track before detect (TBD) approach employed under low signal to noise ratio conditions. Image sequences from the CAVIAR1 dataset are used in simulations to prove the aptitude of this method.

[1]  Ronald P. S. Mahler,et al.  Advances in Statistical Multisource-Multitarget Information Fusion , 2014 .

[2]  Samuel S. Blackman,et al.  Multiple-Target Tracking with Radar Applications , 1986 .

[3]  Ba-Ngu Vo,et al.  Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking , 2013, 2013 International Conference on Control, Automation and Information Sciences (ICCAIS).

[4]  R. Mahler.  PHD filters of higher order in target number , 2007 .

[5]  Sergio A. Velastin,et al.  Intelligent distributed surveillance systems: a review , 2005 .

[6]  Ba-Ngu Vo,et al.  A Random-Finite-Set Approach to Bayesian SLAM , 2011, IEEE Transactions on Robotics.

[7]  Ba-Ngu Vo,et al.  A Multiple Model Probability Hypothesis Density Tracker for Time-Lapse Cell Microscopy Sequences , 2013, IPMI.

[8]  Andre Levchenko,et al.  Tracking cell motion using GM-PHD , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[9]  Ba-Ngu Vo,et al.  Visual Tracking in Background Subtracted Image Sequences via Multi-Bernoulli Filtering , 2013, IEEE Transactions on Signal Processing.

[10]  R. Mahler.  Multitarget Bayes filtering via first-order multitarget moments , 2003 .

[11]  Evangeline Pollard,et al.  GM-PHD filters for multi-object tracking in uncalibrated aerial videos , 2009, 2009 12th International Conference on Information Fusion.

[12]  Ashraf A. Kassim,et al.  Gaussian mixture probability hypothesis density for visual people racking , 2007, 2007 10th International Conference on Information Fusion.

[13]  Ba-Ngu Vo,et al.  Labeled Random Finite Sets and the Bayes Multi-Target Tracking Filter , 2013, IEEE Transactions on Signal Processing.

[14]  Klaus C. J. Dietmayer,et al.  Real-Time Multi-Object Tracking using Random Finite Sets , 2013, IEEE Transactions on Aerospace and Electronic Systems.

[15]  Bohyung Han,et al.  Sequential Kernel Density Approximation and Its Application to Real-Time Visual Tracking , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Ba-Ngu Vo,et al.  The Gaussian Mixture Probability Hypothesis Density Filter , 2006, IEEE Transactions on Signal Processing.

[17]  Fredrik Gustafsson,et al.  Road Intensity Based Mapping Using Radar Measurements With a Probability Hypothesis Density Filter , 2011, IEEE Transactions on Signal Processing.

[18]  Dario Tarchi,et al.  Bernoulli Filter for Track-Before-Detect using MIMO Radar , 2014, IEEE Signal Processing Letters.

[19]  Joaquim Salvi,et al.  SLAM With Dynamic Targets via Single-Cluster PHD Filtering , 2013, IEEE Journal of Selected Topics in Signal Processing.

[20]  P. Willett,et al.  The GM-CPHD Tracker Applied to Real and Realistic Multistatic Sonar Data Sets , 2012, IEEE Journal of Oceanic Engineering.

[21]  Ba-Ngu Vo,et al.  The Cardinality Balanced Multi-Target Multi-Bernoulli Filter and Its Implementations , 2009, IEEE Transactions on Signal Processing.

[22]  Ronald P. S. Mahler,et al.  Statistical Multisource-Multitarget Information Fusion , 2007 .

[23]  Ba-Ngu Vo,et al.  SLAM Gets a PHD: New Concepts in Map Estimation , 2014, IEEE Robotics & Automation Magazine.

[24]  Y. Bar-Shalom.  Tracking and data association , 1988 .

[25]  Ba-Ngu Vo,et al.  Labeled Random Finite Sets and Multi-Object Conjugate Priors , 2013, IEEE Transactions on Signal Processing.

[26]  Aaron D. Lanterman,et al.  Probability hypothesis density-based multitarget tracking with bistatic range and Doppler observations , 2005 .

[27]  R. Mahler,et al.  PHD filters of higher order in target number , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[28]  Ba-Ngu Vo,et al.  Multi-Bernoulli based track-before-detect with road constraints , 2012, 2012 15th International Conference on Information Fusion.

[29]  Emilio Maggio,et al.  Efficient Multitarget Visual Tracking Using Random Finite Sets , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[30]  A. Doucet,et al.  Sequential Monte Carlo methods for multitarget filtering with random finite sets , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[31]  Ba-Ngu Vo,et al.  Bernoulli Forward-Backward Smoothing for Joint Target Detection and Tracking , 2011, IEEE Transactions on Signal Processing.

[32]  Ba-Ngu Vo,et al.  Multi-target Track-Before-Detect using labeled random finite set , 2013, 2013 International Conference on Control, Automation and Information Sciences (ICCAIS).

[33]  Sim Heng Ong,et al.  Probability Hypothesis Density Approach for Multi-camera Multi-object Tracking , 2007, ACCV.

[34]  David Suter,et al.  Joint Detection and Estimation of Multiple Objects From Image Observations , 2010, IEEE Transactions on Signal Processing.

[35]  David Suter,et al.  Visual tracking of numerous targets via multi-Bernoulli filtering of image data , 2012, Pattern Recognit..

[36]  Daniel E. Clark,et al.  Bayesian multiple target tracking in forward scan sonar images using the PHD filter , 2005 .

[37]  Daniel E. Clark,et al.  Particle PHD filter multiple target tracking in sonar image , 2007, IEEE Transactions on Aerospace and Electronic Systems.

[38]  Ba-Ngu Vo,et al.  Analytic Implementations of the Cardinalized Probability Hypothesis Density Filter , 2007, IEEE Transactions on Signal Processing.

[39]  Lauri Parkkonen,et al.  Dynamical MEG source modeling with multi‐target Bayesian filtering , 2009, Human brain mapping.

[40]  Klaus C. J. Dietmayer,et al.  Multi-object tracking at intersections using the cardinalized probability hypothesis density filter , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[41]  Ba-Tuong Vo,et al.  Bernoulli Forward-Backward Smoothing for Track-Before-Detect , 2014, IEEE Signal Processing Letters.

[42]  Klaus C. J. Dietmayer,et al.  A random finite set approach to multiple lane detection , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.