Abstract
This paper addresses the linear and log-linear fusion approaches to multitarget density fusion which yield arithmetic average (AA) and geometric average (GA), respectively. We reaffirm Abbas’s finding in 2009 that both AA and GA can be related to the minimization of the Kullback-Leibler divergence (KLD) between the fusing densities and the fused result, which differ from each other in the reference used to measure the KLD: the AA uses the fusing densities while the GA uses the fused density. We derive the explicit AA expressions for fusing some known multitarget densities and discuss the implementation issues. The results serve as the theoretical basis for designing distributed random finite set filters for distributed multitarget tracking.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Vo, B., Mallick, M., Barshalom, Y., Coraluppi, S., Osborne, R., Mahler, R., Vo, B.: Multitarget tracking. In: Webster, J.G. (ed.) Wiley Encyclopedia of Electrical and Electronics Engineering (2015)
Mahler, R.P.S.: Advances in Statistical Multisource-Multitarget Information Fusion. Artech House, Norwood (2014)
Li, T., Fan, H., Garcia, J., Corchado, J.M.: Second-order statistics analysis and comparison between arithmetic and geometric average fusion: application to multi-sensor target tracking. Inf. Fusion 51, 233–243 (2019)
Olfati-Saber, R., Fax, J.A., Murray, R.M.: Consensus and cooperation in networked multi-agent systems. Proc. IEEE 95(1), 215–233 (2007)
Xiao, L., Boyd, S., Kim, S.-J.: Distributed average consensus with least-mean-square deviation. J. Parallel Distrib. Comput. 67(1), 33–46 (2007)
Abbas, A.E.: A Kullback-Leibler view of linear and log-linear pools. Decis. Anal. 6(1), 25–37 (2009)
Li, T., Corchado, J.M., Sun, S.: Partial consensus and conservative fusion of Gaussian mixtures for distributed PHD fusion. IEEE Trans. Aerosp. Electron. Syst. (2018, in press). https://doi.org/10.1109/TAES.2018.2882960
Li, T., Hlawatsch, F., Djurić, P.M.: Cardinality-consensus-based PHD filtering for distributed multitarget tracking. IEEE Sig. Process. Lett. 26(1), 49–53 (2019)
Li, T., Hlawatsch, F.: A distributed SMC-PHD filter based on arithmetic average PHD fusion. arxiv: 1712.06128v2 (2018)
Gostar, A.K., Hoseinnezhad, R., Bab-Hadiashar, A.: Cauchy-Schwarz divergence-based distributed fusion with Poisson random finite sets. In: Proceedings of ICCAIS, Chiang Mai, Thailand, pp. 112–116 (2017)
Gao, L., Battistelli, G., Chisci, L.: Multiobject fusion with minimum information loss. arXiv:1903.04239, March 2019
Burnham, K.P., Anderson, D.R.: Model Selection and Multi-Model Inference: A Practical Information-Theoretic Approach, 2nd edn. Springer, New York (2002)
Battistelli, G., Chisci, L., Fantacci, C., Farina, A., Graziano, A.: Consensus CPHD filter for distributed multitarget tracking. IEEE J. Sel. Top. Sig. Proces. 7(3), 508–520 (2013)
Wang, Y., Li, X.R.: A fast and fault-tolerant convex combination fusion algorithm under unknown cross-correlation. In: Proceedings of Fusion, Seattle, WA, USA, pp. 6–9, July 2009
Nagappa, S., Clark, D.E., Mahler, R.: Incorporating track uncertainty into the OSPA metric. In: Proceedings of FUSION 2011, Chicago, IL, USA, July 2011
Clark, D., Julier, S., Mahler, R., Ristic, B.: Robust multi-object sensor fusion with unknown correlations. In: Proceedings of Sensor Signal Processing for Defence (SSPD 2010), London, September 2010
Ristic, B., Vo, B.T., Vo, B.N., Farina, A.: A tutorial on Bernoulli filters: theory, implementation and applications. IEEE Trans. Sig. Process. 61(13), 3406–3430 (2013)
Vo, B.T., Vo, B.-N., Cantoni, A.: Analytic implementations of the cardinalized probability hypothesis density filter. IEEE Trans. Sig. Process. 55(7), 3553–3567 (2007)
Williams, J.L.: Marginal multi-Bernoulli filters: RFS derivation of MHT, JIPDA, and association-based MeMBer. IEEE Trans. AES 51(3), 1664–1687 (2015)
Li, T., Corchado, J.M., Chen, H.: distributed flooding-then-clustering: a lazy networking approach for distributed multiple target tracking. In: Proceeding of FUSION 2018, Cambridge, UK, 10–13 July, pp. 2415–2422 (2018)
Li, S., Battistelli, G., Chisci, L., Yi, W., Wang, B., Kong, L.: Computationally efficient multi-agent multi-object tracking with labeled random finite sets. IEEE Trans. Sig. Process. 67(1), 260–275 (2019)
Acknowledgments
This work is supported by the Joint Fund of Equipment development and Aerospace Science and Technology under Grant no 6141B0624050101.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Da, K., Li, T., Zhu, Y., Fan, H., Fu, Q. (2020). Kullback-Leibler Averaging for Multitarget Density Fusion. In: Herrera, F., Matsui , K., Rodríguez-González, S. (eds) Distributed Computing and Artificial Intelligence, 16th International Conference. DCAI 2019. Advances in Intelligent Systems and Computing, vol 1003 . Springer, Cham. https://doi.org/10.1007/978-3-030-23887-2_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-23887-2_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-23886-5
Online ISBN: 978-3-030-23887-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)