In order to solve the problem of robust track-to-track association in the presence of sensor biases and non-identical observation, an anti-bias track association algorithm based on t-distribution mixture model is proposed. The robust track-to-track association problem is turned into the non-rigid point matching problem. The tracks of non-common are regarded as outliers in the point matching for the effects of the track-to-track association caused by non-identical observation. The heavy-tailed t-distribution mixture model is established with better robustness to outliers. The closed-form solution of t-distribution mixture model is solved by Expectation Maximization (EM) algorithm. The conditional expectation function is added a regular item of point set, so that the points have a feature of Coherent Point Drift (CPD). Finally, the effectiveness of the proposed algorithm is verified by simulation experiments at the presence of sensor biases and missed detections.
QI Lin, CUI Yaqi, XIONG Wei, et al. Anti-bias association algorithm for automatic identification system and radar based on bias detection[J]. Journal of Electronics & Information Technology, 2015, 37(8): 1855-1861. doi: 10. 11999/JEIT141472.
[2]
ZHU Hao, Leung H, and Yuen K V. A joint data association, registration, and fusion approach for distributed tracking[J]. Information Sciences, 2015, 324(C): 186-196.
HE You, SONG Qiang, and XIONG Wei. A track registration-correlation algorithm based on fourier transform [J]. Acta Aeronautica et Astronautica Sinica, 2010, 31(2): 356-362.
[4]
ZHU Hongyan and HAN Suying. Track-to-track association based on structural similarity in the presence of sensor biases[J]. Journal of Applied Mathematics, 2014(1): 1-8. doi: 10.1155/2014/294657
ZHU Hongyan and WANG Chen. Joint track-to-track association and sensor registration at the track level[J]. Digital Signal Processing, 2015, 41: 48-59. doi 10.1016/j.dsp. 2015.03.012.[5]
DONG Kai, WANG Haipeng, and LIU Yu. Anti- bias track association algorithm based on topology statistical distance[J]. Journal of Electronics & Information Technology, 2015, 37(1): 50-55. doi: 10.11999/JEIT140244.
[7]
HUANG D, LEUNG H, and BOSSE E. A pseudo- measurement approach to simultaneous registration and track fusion[J]. IEEE Transactions on Aerospace & Electronic Systems, 2012, 48(3): 2315-2331. doi: 10.1109/TAES.2012. 6237594.
[8]
ZHU Hongyan and CHEN Shuo. Track fusion in the presence of sensor biases[J]. IET Signal Processing, 2014, 8(9): 958-967. doi: 10.1049/iet-spr.2013.0393.
[9]
ZHU Hongyan, WANG Wei, and WANG Chen. Robust track-to-track association in the presence of sensor biases and missed detections[J]. Information Fusion, 2016, 27: 33-40. doi: 10.1016/j.inffus.2015.05.002.
ZHU Hongyan, ZHANG Ying, and WANG Chen. Anti-biases track-to-track association based on relaxation labeling[J]. Control & Decision, 2015, 30(4): 593-598. doi: 10.13195/j. kzyjc.2014.0134.
[11]
LEE S X and MCLACHLAN G J. Finite mixtures of canonical fundamental skew t-distributions[J]. Statistics & Computing, 2016, 26(3): 573-589. doi: 10.1007/s11222-015- 9545-x
[12]
PEEL D and MCLACHLAN G J. Robust mixture modelling using the t distribution[J]. Statistics & Computing, 2000, 10(4): 339-348. doi: 10.1023/A:1008981510081.
[13]
WU C.F.J. On the convergence properties of the EM algorithm[J]. The Annals of Statistics, 1983, 11(1): 95-103.
[14]
LIU C and RUBIN D B. ML estimation of the t distribution using EM and its extensions, ECM and ECME[J]. Statistica Sinica, 1995, 5(1): 19-39.
[15]
MYRONENKO A and SONG X. Point set registration: Coherent point drift[J]. IEEE Transactions on Software Engineering, 2010, 32(12): 2262-2275. doi: 10.1109/TPAMI. 2010.46.
