Modified labeled particle probability hypothesis density filter for joint multi-target tracking and classification

Unification of the detection, tracking and classification for multiple targets is an object for random finite sets based filters developing. Introduction of target attribute information can improve tracking performance. Then, as the improved labeled particle probability hypothesis density (IL-P-PHD) filter is capable of joint detection and tracking, we will fuse obtained target attribute information into IL-P-PHD filter to propose a joint tracking and classification particle PHD (JTC-P-PHD) algorithm. We are in the expectation that the proposed JTC-P-PHD algorithm is capable of joint detection, tracking as well as classification of multiple targets. Numerical examples demonstrate that the proposed JTC-P-PHD algorithm behaves in a manner consistent with our expectations.

[1]  Ronald P. S. Mahler,et al.  “Statistics 102” for Multisource-Multitarget Detection and Tracking , 2013, IEEE Journal of Selected Topics in Signal Processing.

[2]  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.

[3]  Xiaofan He,et al.  Two-level automatic multiple target joint tracking and classification , 2010, Defense + Commercial Sensing.

[4]  Branko Ristic,et al.  A Metric for Performance Evaluation of Multi-Target Tracking Algorithms , 2011, IEEE Transactions on Signal Processing.

[5]  Xiang Li,et al.  Joint detection, tracking and classification of multiple maneuvering targets based on the linear Gaussian jump Markov probability hypothesis density filter , 2013 .

[6]  Wei Mei,et al.  Simultaneous tracking and classification: a modularized scheme , 2007, IEEE Transactions on Aerospace and Electronic Systems.

[7]  Fu Yaowen,et al.  Joint Detection, Tracking, and Classification of Multiple Targets in Clutter using the PHD Filter , 2012 .

[8]  Klaus C. J. Dietmayer,et al.  The Labeled Multi-Bernoulli Filter , 2014, IEEE Transactions on Signal Processing.

[9]  Ba-Ngu Vo,et al.  On performance evaluation of multi-object filters , 2008, 2008 11th International Conference on Information Fusion.

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

[11]  Ba Tuong Vo,et al.  Tracking, identification, and classification with random finite sets , 2013, Defense, Security, and Sensing.

[12]  Thiagalingam Kirubarajan,et al.  Tracking with classification-aided multiframe data association , 2005 .

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

[14]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[15]  Rui Hu,et al.  Joint multi-target filtering and track maintenance using improved labeled particle PHD filter , 2014, 2014 7th International Congress on Image and Signal Processing.

[16]  Peter Willett,et al.  Classification aided cardinalized probability hypothesis density filter , 2012, Defense + Commercial Sensing.

[17]  Xiang Li,et al.  Joint Detection, Tracking, and Classification of Multiple Targets in Clutter using the PHD Filter , 2012, IEEE Transactions on Aerospace and Electronic Systems.

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