Abstract To avoid the track coalescence of the Joint Integrated Probabilistic Data Association (JIPDA), a modified version of JIPDA is proposed by modelling targets as Random Finite Set (RFS). The JIPDA first generates the original Probability Density Function (PDF) and then makes an approximation of the PDF to estimate target states. To maximize the similarity between the state estimate PDF and the original PDF, the original PDF is optimized when target label is irrelevant. Using the KL divergence as a measure of the similarity, the cost function is developed. The experimental results show that the proposed method can effectively avoid the track coalescence.
CHANG K C and BAR-SHALOM Y. Joint probabilistic data association for multitarget tracking with possibly unresolved measurements and maneuvers[J]. IEEE Transactions on Automatic Control, 1984, 29(7): 585-594. doi: 10.1109/TAC. 1984.1103597.
[2]
MUŠICKI D and EVANS R. Joint integrated probabilistic data association-JIPDA[J]. IEEE Transactions on Aerospace and Electronic Systems, 2004, 40(3): 1093-1099. doi: 10.1109/ TAES.2004.1337482.
WU Ming, LI Linlin, WEI Zhenhua, et al. A robot multi- object tracking algorithm in unknown environments[J]. CAAI Transactions on Intelligent Systems, 2015, 10(3): 448-453. doi: 10.3969/j.issn.1673-4785.201405051.
[5]
CHEN Xin, PELLETIER M, KIRUBARAJAN T, et al. Integrated Bayesian clutter estimation with JIPDA/MHT trackers[J]. IEEE Transactions on Aerospace and Electronic Systems, 2013, 49(1): 395-414. doi: 10.1109/TAES.2013. 6404111.
[6]
BLOM H A P, BLOEM E A, and MUŠICKI D. JIPDA*: Automatic target tracking avoiding track coalescence[J]. IEEE Transactions on Aerospace and Electronic Systems, 2015, 51(2): 962-974. doi: 10.1109/TAES.2014.130327.
[7]
MAHLER R. Statistical Multisource Multitarget Information Fusion[M]. London, Artech House, 2007: 5-14.
[8]
WILLIAMS J L. Marginal multi-Bernoulli filters: RFS derivation of MHT, JIPDA and association-based MeMBer[J]. IEEE Transactions on Aerospace and Electronic Systems, 2015, 51(3): 1664-1687. doi: 10.1109/TAES.2015.130550.
YU Yan. Similarity measure method of Gaussian mixture model by integrating Kullback-Leibler divergence and earth mover's distance[J], Journal of Computer Applications, 2014, 34(3): 828-832. doi: 10.11772/j.issn.1001-9081.2014.03.0828.
[10]
BLAHUT R E. Principles and Practice of Information Theory[M]. MA: Addison-Wesley, 1987, Chapter 7.
[11]
SVENSSON L, SVENSSON D, and WILLETT P. Set JPDA algorithm for tracking unordered sets of targets[C]. 12th International Conference on Information Fusion, Seattle, WA, USA, 2009: 1187-1194.
[12]
SCHUHMACHER D, VO B T, and VO B N. A consistent metric for performance evaluation of multi-object filters[J]. IEEE Transactions on Signal Processing, 2008, 56(8): 3447-3457. doi: 10.1109/TSP.2008.920469.
[13]
MUŠICKI D and EVANS R. Clutter map information for data association and track initialization[J]. IEEE Transactions on Aerospace and Electronic Systems, 2004, 40(2): 387-398. doi: 10.1109/TAES.2004.1309992.
[14]
JING P L, XU S Y, LI X, et al. Coalescence-avoiding joint probabilistic data association based on bias removal[J]. EURASIP Journal on Advances in Signal Processing, 2015(1): 1-13. doi: 10.1186/s13634-015-0205-2.
[15]
PANAKKAL V P and VELMURUGAN R. Effective joint probabilistic data association using maximum a posteriori estimates of target states[C]. 16th International Conference on Information Fusion, Istanbul, Turkey, 2013: 781-788.