A closely spaced target track maintenance algorithm based on Gaussian mixture probability hypothesis density

Abstract As one suboptimal but tractable alternative to the Bayes filter within the random finite set (RFS) framework, the probability hypothesis density (PHD) filter has attracted considerable attention because of its low computational load and ease of implementation. However, the standard PHD filter is unable to estimate the tracks of targets in clutter circumstances. Although some PHD-based trackers are proposed to estimate the tracks of targets, the track maintenance performances of these trackers suffer from significant declines in closely spaced target environments. In this paper, with the help of the track label and an association-update factor matrix, a closely spaced target track maintenance algorithm based on the Gaussian mixture PHD filter is proposed to identify and provide the trajectories of close targets over times. Numerical simulations demonstrate that the proposed algorithm is capable of correctly estimating the tracks of closely spaced targets in clutter environments, and is superior to the related multi-target trackers in terms of target states, computational load, and association accuracy of tracks.

[1]  Ye Tian,et al.  Improved Gaussian Mixture CPHD Tracker for Multitarget Tracking , 2013, IEEE Transactions on Aerospace and Electronic Systems.

[2]  Zong-xiang Liu,et al.  Multi-target Bayesian filter for propagating marginal distribution , 2014, Signal Process..

[3]  Karl Granström,et al.  Poisson Multi-Bernoulli Mapping Using Gibbs Sampling , 2017, IEEE Transactions on Signal Processing.

[4]  Nathanael L. Baisa,et al.  Multiple target, multiple type filtering in the RFS framework , 2017, Digit. Signal Process..

[5]  Nahum Shimkin,et al.  Cross Entropy Algorithms for Data Association in Multi-Target Tracking , 2011, IEEE Transactions on Aerospace and Electronic Systems.

[6]  Andrew M. Wallace,et al.  Development of a N-type GM-PHD Filter for Multiple Target, Multiple Type Visual Tracking , 2019, J. Vis. Commun. Image Represent..

[7]  Ba-Ngu Vo,et al.  A Consistent Metric for Performance Evaluation of Multi-Object Filters , 2008, IEEE Transactions on Signal Processing.

[8]  Daniel E. Clark,et al.  A Tractable Forward– Backward CPHD Smoother , 2017, IEEE Transactions on Aerospace and Electronic Systems.

[9]  Yi Jiang,et al.  Iterative RANSAC based adaptive birth intensity estimation in GM-PHD filter for multi-target tracking , 2017, Signal Process..

[10]  Thia Kirubarajan,et al.  Labeled Random Finite Sets With Moment Approximation , 2017, IEEE Transactions on Signal Processing.

[11]  Ba-Tuong Vo,et al.  Multi-Sensor Multi-Object Tracking With the Generalized Labeled Multi-Bernoulli Filter , 2017, IEEE Transactions on Signal Processing.

[12]  Jinlong Yang,et al.  Iterative update correction and multi-frame state extraction based probability hypothesis density filter , 2017 .

[13]  B. Vo,et al.  Data Association and Track Management for the Gaussian Mixture Probability Hypothesis Density Filter , 2009, IEEE Transactions on Aerospace and Electronic Systems.

[14]  Zohreh Azimifar,et al.  Adaptive visual target detection and tracking using weakly supervised incremental appearance learning and RGM-PHD tracker , 2016, J. Vis. Commun. Image Represent..

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

[16]  Lennart Svensson,et al.  Labeling uncertainty in multitarget tracking , 2016, IEEE Transactions on Aerospace and Electronic Systems.

[17]  Weihua Wu,et al.  Augmented state GM-PHD filter with registration errors for multi-target tracking by Doppler radars , 2016, Signal Process..

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

[19]  Linna Ji,et al.  Cubature Information Gaussian Mixture Probability Hypothesis Density Approach for Multi Extended Target Tracking , 2019, IEEE Access.

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

[21]  Alberto Broggi,et al.  PHD filter for vehicle tracking based on a monocular camera , 2018, Expert Syst. Appl..

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

[23]  Jonathon A. Chambers,et al.  Multi-Level Cooperative Fusion of GM-PHD Filters for Online Multiple Human Tracking , 2019, IEEE Transactions on Multimedia.

[24]  Sinan Gezici,et al.  Multiperson Tracking With a Network of Ultrawideband Radar Sensors Based on Gaussian Mixture PHD Filters , 2015, IEEE Sensors Journal.

[25]  Y. Bar-Shalom,et al.  Track labeling and PHD filter for multitarget tracking , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[26]  D. Clark,et al.  Multi-target state estimation and track continuity for the particle PHD filter , 2007, IEEE Transactions on Aerospace and Electronic Systems.

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

[28]  Hans Driessen,et al.  Mixed Labelling in Multitarget Particle Filtering , 2010, IEEE Transactions on Aerospace and Electronic Systems.

[29]  Ba-Ngu Vo,et al.  A Generalized Labeled Multi-Bernoulli Filter With Object Spawning , 2017, IEEE Transactions on Signal Processing.

[30]  Honghai Liu,et al.  Tracking Multiple Video Targets with an Improved GM-PHD Tracker , 2015, Sensors.

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

[32]  Lichuan Zhang,et al.  Cooperative Localization for Multi-AUVs Based on GM-PHD Filters and Information Entropy Theory , 2017, Sensors.

[33]  Jinlong Yang,et al.  A novel track maintenance algorithm for PHD/CPHD filter , 2012, Signal Process..