Abstract
Two variations of the joint probabilistic data association filter (JPDAF) are derived and simulated in various cases in this paper. First, an analytic solution for an optimal gain that minimizes posterior estimate uncertainty is derived, referred to as the minimum uncertainty JPDAF (M-JPDAF). Second, the coalescence-avoiding JPDAF (C-JPDAF) is derived, which removes coalescence by minimizing a weighted sum of the posterior uncertainty and a measure of similarity between estimated probability densities. Both novel algorithms are tested in much further depth than any prior work to show how the algorithms perform in various scenarios. In particular, the M-JPDAF more accurately tracks objects than the conventional JPDAF in all simulated cases. When coalescence degrades the estimates at too great of a level, and the C-JPDAF is often superior at removing coalescence when its parameters are properly tuned.
Similar content being viewed by others
References
Bar-Shalom, Y.: Multitarget-Multisensor Tracking. Artech House, Inc., Norwood (1990)
Bar-Shalom, Y., Daum, F., Huang, J.: The probabilistic data association filter. IEEE Control. Syst. Mag. 29, 82–100 (2009)
Bar-Shalom, Y., Fortmann, T.E.: Tracking and Data Association. Elsevier, Inc, San Diego (1988)
Bar-Shalom, Y., Li, X.R., Kirubarajan, T.: Estimation with Applications to Tracking and Navigation. A Wiley-Interscience Publication, New York (2001)
Blackman, S.S.: Multiple hypothesis tracking for multiple target tracking. IEEE Aerosp. Electron. Syst. Mag. 19(1), 5–18 (2004)
Bloem, E.A., Blom, H.A.: Joint probabilistic data association methods avoiding track coalescence. In: Proceedings of the IEEE Conference on Decision and Control (1995)
Blom, H.A., Bloem, E.A.: Combining IMM and JPDA for tracking multiple maneuvering targets in clutter. Tech. rep., National Aerospace Laboratory NLR (2002)
Blom, H.A.P., Bloem, E.: Probabilistic data association avoiding track coalescence. IEEE Trans. Autom. Control 45(17), 247–259 (2000)
Chen, S., Xu, Y.: A new joint probabilistic data association algorithm avoiding track coalescence. Int. J. Intell. Syst. Appl. 2, 45–51 (2011)
Fitzgerald, R.J.: Development of practical PDA logic for multitarget tracking by microprocessor. Tech. rep., Raytheon Company, Missile Systems Division (1986)
Gelb, A.: Applied Optimal Estimation. The Analytic Sciences Corporation, Cambridge (1974)
Habtemariam, B., Tharmarasa, R., Thayaparan, T., Mallick, M., Kirubarajan, T.: A multiple-detection joint probabilistic data association filter. IEEE J. Sel. Top. Sign. Process. 7(3), 461–471 (2013)
Kaufman, E., Lovell, T.A., Lee, T.: Optimal joint probabilistic data association filter avoiding coalescence in close proximity. In: Proceedings of the IEEE European Control Conference (2014)
Kaufman, E., Lovell, T.A., Lee, T.: Minimum uncertainty jpda filter and coalescence avoidance performance evaluations. In: Proceedings of the AAS-AIAA Spaceflight Mechanics Meeting (2015)
Kural, F., Arikan, F., Arikan, O., Efe, M.: Performance evaluation of track association and maintenance for a mfpar with doppler velocity measurements. Prog. Electromagn. Res. 108, 249–275 (2010)
Li, X.R., Bar-Shalom, Y.: Tracking in clutter with nearest neighbor filters: analysis and performance. IEEE Trans. Aerosp. Electron. Syst. 32(3), 995–1010 (1996)
Lin, L., Bar-Shalom, Y., Kirubarajan, T.: Track labeling and PHD filter for multitarget tracking. IEEE Trans. Aerosp. Electron. Syst. 42(3), 778–794 (2006)
Matusita, K.: Decision rules, based on the distance, for problems of fit, two samples, and estimation. Ann. Math. Stat. 26(4), 631–640 (1955)
Minami, M., Shimizu, K.: Estimation of similarity measure for multivariate normal distributions. Environ. Ecol. Stat. 45(6), 229–248 (1999)
Sidenbladh, H.: Development of practical PDA logic for multitarget tracking by microprocessor. In: Proceedings of the American Control Conference (1986)
Svensson, D., Ulmke, M., Danielson, L.: Joint probabilistic data association filter for partially unresolved target groups. In: 13th Conference on Information Fusion (FUSION) (2010)
Thacker, N.A., Aherne, F.J., Rockett, P.I.: The bhattacharyya metric as an absolute similarity measure for frequency coded data. Kybernetika 34(4), 363–368 (1997)
Vallado, D.A.: Fundamentals of Astrodynamics and Applications. Microcosm Press and Kluwer Academic Publishers, El Segundo (2001)
Vergez, P., Sauter, L., Dahlke, S.: An improved kalman filter for satellite orbit predictions. J. Astronaut. Sci. 52, 7 (2004)
Wei, X., Jing-Wei, Z., You, H.: Multisensor multitarget tracking methods based on particle filter. In: Proceedings of Autonomous Decentralized Systems (2010)
Acknowledgments
This research has been supported in part by NSF under the grants CMMI-1243000 (transferred from 1029551), CMMI-1335008, and CNS-1337722.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix: A: M-JPDAF Proofs
Note that all object-related variables refer to the i-th object, so this subscript is omitted from indexing the object. Any subsequent usage in Appendix A is when i refers to matrix rows.
-
From Eqs. 16 and 18 the uncertainty cost for any gain K for each estimate is given by
$$ J_{P}=\text{tr}[P^{-}-(1-\beta_{0})(KHP^{-}+P^{-}H^{T}K^{T})+KEK^{T}]. $$(41)It can be easily seen that the second derivative of J P is only a function of the third term
$$ \text{tr}[KEK^{T}]=\sum\limits_{i=1}^{n}{k_{i}^{T}}Ek_{i} $$(42)where k i corresponds to the i-th row of K. Taking derivatives with respect to k i ,
$$ {\frac{\partial ({k_{i}^{T}}Ek_{i})}{\partial k_{i}}}=2Ek_{i}, \quad \frac{\partial^{2}({k_{i}^{T}}Ek_{i})}{\partial {k_{i}^{2}}}=2E, $$(43)which is positive-definite from (ii). As the Hessian is positive-definite, the given optimal gain globally minimizes the cost. Using Eq. 21, the optimal cost is given by,
$$ J^{*}_{P} = \text{tr}[P^{-}-KEK^{T}]. $$(44) -
Suppose that an object is not measured. Let this portion of the innovation update be e 0=0 m×1 because no innovation exists where measurements are not available. The Total Probability Theorem holds true for object i:
$$ \sum\limits_{j=0}^{n_{r}}\beta_{j}=1. $$(45)Consider the positive-semidefinite matrix \({\Sigma }\in \mathbb {R}^{m\times m}\) from [4, Eq. 1.4.16-(1-10)],
$$ {\Sigma}=\sum\limits_{j=0}^{n_{r}}\beta_{j}(e_{j}-{\bar{e}})(e_{j}-{\bar{e}})^{T}, $$(46)which may be manipulated as follows,
$$ {\Sigma}=\sum\limits_{j=0}^{n_{r}}\beta_{j}e_{j}{e_{j}^{T}} -\sum\limits_{j=0}^{n_{r}}\beta_{j}e_{j}{\bar{e}}^{T} -{\bar{e}}\sum\limits_{j=0}^{n_{r}}\beta_{j}{e_{j}^{T}} +{\bar{e}}{\bar{e}}^{T} =\sum\limits_{j=1}^{n_{r}}\beta_{j}e_{j}{e_{j}^{T}}-{\bar{e}}{\bar{e}}^{T}, $$(47)because e 0≡0. From Eq. 17,
$$ E=(1-\beta_{0})S+{\Sigma}, $$(48)which yields a positive-definite E because S is positive-definite, Σ is positive-semidefinite, and 0≤β 0<1. Therefore, E is invertible.
-
Let \(K_{K}=P^{-}H^{T}S^{-1}\in \mathbb {R}^{n\times m}\) [3]. Suppose that these gains are identical, i.e., K = K K . Multiplying both sides by E and using Eq. 17,
$$\begin{array}{@{}rcl@{}} KE&=&K_{K}E \\ (1-\beta_{0})P^{-}H^{T}&=& (1-\beta_{0})P^{-}H^{T}+K_{K}{\Sigma}. \end{array} $$(49)Therefore if Eq. 49 is true, then K K Σ=0, which may only occur if the probabilities that each measurement belongs to an object are exactly 0 or 1 or K K ⊥Σ. None of these conditions are satisfied in general, so it follows that the Kalman gain is different in general from the optimal gain proposed in this paper.
-
From Eq. 41, the uncertainty cost with the Kalman gain \(J_{P_{K}}\in \mathbb {R}\) can be written as
$$\begin{array}{@{}rcl@{}} J_{P_{K}} &=& \text{tr}[P^{-}-2(1-\beta_{0})P^{-}H^{T}S^{-1}HP^{-}+P^{-}H^{T}S^{-1}ES^{-1}HP^{-1}] \\ &=& \text{tr}\left[P^{-}-(1-\beta_{0})^{2}P^{-}H^{T}\left( \frac{2}{1-\beta_{0}}S^{-1}-\frac{1}{(1-\beta_{0})^{2}}S^{-1}ES^{-1}\right)HP^{-}\right].\\ \end{array} $$(50)Similarly, the optimal cost \(J^{*}_{P}\) may be rewritten as
$$ J^{*}_{P} = \text{tr}[P^{-}-(1-\beta_{0})^{2}P^{-}H^{T}E^{-1}HP^{-}]. $$(51)From Eqs. 50 and 51 and using variations of the definition of E from Eq. 17 repeatedly, the difference \(J_{P_{K}}-J^{*}_{P}\)can be written as
$$\begin{array}{@{}rcl@{}} J_{P_{K}}-J^{*}_{P} &=& (1-\beta_{0})^{2}\text{tr}\left[P^{-}H^{T}\left( E^{-1}-\frac{2}{1-\beta_{0}}S^{-1}\right.\right.\\ &&\quad\quad\quad\quad\quad\quad\quad\quad\quad\quad+\left.\left.\frac{1}{(1-\beta_{0})^{2}}S^{-1}ES^{-1}\right)HP^{-}\right] \\ &=& \text{tr}\left[P^{-}H^{T}S^{-1}{\Sigma} E^{-1}{\Sigma} S^{-1}HP^{-}\right] \\ &= &\text{tr}\left[K_{K}{\Sigma} E^{-1}{\Sigma} {K_{K}^{T}}\right] =\sum\limits_{i=1}^{n}{\nu_{i}^{T}}E^{-1}\nu_{i}\geq0, \end{array} $$(52)where ν i corresponds to the i-th row of K K Σ and E −1 is positive-definite because E is positive-definite from (ii). This implies the inequality \(J_{P_{K}}\geq J^{*}_{P}\). The only times when K K becomes optimal are if there exists no measurement origin uncertainty, i.e., Σ=0, or K K ⊥Σ, and neither scenario is satisfied in general. These results are consistent with those obtained from Eq. 49.
Appendix: B: Derivatives to Obtain the C-JPDAF
The derivative of the similarity cost is obtained as follows. Let \({\mathbf {1}_{bd}}\in \mathbb {R}^{n\times m}\) be defined such that its (b,d)-th element is one and other elements are zero, and let \([K_{p}]_{bd}\in \mathbb {R}\) be the (b,d)-th element of K p . Then we have
where \({\frac {\partial P^{+}_{p}}{\partial [K_{p}]_{bd}}}\in \mathbb {R}^{n\times n}\) is
From Eqs. 33 and 55, \({\frac {\partial u_{pq}}{\partial [K_{p}]_{bd}}}\in \mathbb {R}\) is obtained as
Then from Eqs. 32 and 56, we obtain \({\frac {\partial J_{S}}{\partial [K_{p}]_{bd}}}\in \mathbb {R}\) as
Rights and permissions
About this article
Cite this article
Kaufman, E., Lovell, T.A. & Lee, T. Minimum Uncertainty JPDA Filters and Coalescence Avoidance for Multiple Object Tracking. J of Astronaut Sci 63, 308–334 (2016). https://doi.org/10.1007/s40295-016-0092-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40295-016-0092-2