AA fusion
Theory and approaches of the Arithmetic Average (AA) Fusion can be found in the subpage @P/P Consensus- AA Fusion
Below are some MATLAB codes. If any file is missing, please write to t.c.li@nwpu.edu.cn for it!
1 - Partial Consensus --- Many Could be Better than All
T.Li, S. Sun and J.M. Corchado, Partial Consensus and Conservative Fusion of Gaussian Mixtures for Distributed PHD Fusion, IEEE Trans. Aeros. Electr. Syst., vol.55, no.5, 2150-2163, 2019. PrePrint is available @ IEEE Xplore
We propose a novel consensus notion, called "partial consensus", for distributed Gaussian mixture probability hypothesis density fusion based on a decentralized sensor network, in which only highly-weighted Gaussian components (GCs) are exchanged and fused in terms of AA fusion across neighbor sensors. It is shown that this does not only gain high efficiency in both network communication and fusion computation but also significantly compensates the effects of clutter and missed detections.
M codes are available @Distributed AA-fusion GM-PHD filter
2 - Parallel Consensus -- parallelization of filtering and communication/fusion operations
T. Li, F. Hlawatsch, A distributed particle-PHD filter using arithmetic-average fusion of Gaussian mixture parameters, Information Fusion,73: 111-124, 2021. Preprint arXiv:1712.06128v2 [cs.SY]
We propose a particle-based distributed PHD filter for tracking an unknown, time-varying number of targets. To reduce communication, the local PHD filters at neighboring sensors communicate Gaussian mixture (GM) parameters. In contrast to most existing distributed PHD filters, our filter employs an `arithmetic average' fusion. For particles--GM conversion, we use a method that avoids particle clustering and enables a significance-based pruning of the GM components. For GM--particles conversion, we develop an importance sampling based method that enables a parallelization of filtering and dissemination/fusion operations. The proposed distributed particle-PHD filter is able to integrate GM-based local PHD filters. Simulations demonstrate the excellent performance and small communication and computation requirements of our filter.
M codes are available @Distributed AA-fusion SMC-PHD filter
3 - Cardinality-consensus based PHD Filter
T. Li, F. Hlawatsch, P. Djuric, Cardinality-consensus-based PHD filtering for distributed multi-target tracking, IEEE Signal Process. Lett. vol.26, no.1, 2019, pp.49-53. @ IEEE Xplore The communicationally cheapest solution among all distributed RFS filters
M codes are available @Cardinality-consensus based PHD Filter
4 - Distributed AA-fusion based Bernoulli Filter
T. Li, et al, Distributed Bernoulli Filtering for Target Detection and Tracking Based on Arithmetic Average Fusion, IEEE Signal Processing Letters. Vol.26, no.12, pp. 1812-1816, 2019. IEEE Xplore; the backbone for developing many other AA-fusion-based Bernoulli-mixture filters such as AA-MB, AA-PMBM, AA-PMB, AA-MBM, AA-GLMB, AA-LMB and so on...
M codes are available @Distributed AA-fusion Bernoulli filter
5 - Distributed AA-fusion based MB Filter
T.Li, X. Wang, Y. Liang and Q. Pan, On Arithmetic Average Fusion and Its Application for Distributed Multi-Bernoulli Multitarget Tracking, IEEE Transactions on Signal Processing, 68(1):2883-2896, 2020, IEEE eXplore
M codes are available @Distributed AA-fusion Multi-Bernoulli filter
6 - Distributed AA-fusion based Bayesian Filter
F. Yang, L. Zheng, T. Li*, and L. Shi, A computationally efficient distributed Bayesian filter with random finite set observations, Signal Processing, Volume 194, May 2022, 108454. Sciencedirect
M codes are available @Distributed AA-fusion Bayesian filter
7 - Distributed AA-fusion based multi-sensor Kalman Filter
T. Li, et al, Some Statistic and Information-theoretic Results on Arithmetic Average Density Fusion , [2110.01440] (arxiv.org)
M codes are available @Multi-sensor Kalman Filter