Adaptive Interacting Multiple Model Unscented Particle Filter Tracking Algorithm

Abstract:

In order to study the tracking problem of maneuvering image sequence target in complex environment with multi-sensor array, the adaptive interacting multiple model unscented particle filter algorithm based on measured residual is proposed. The motion array tracking system dynamic model is established, and initialized probability density function also is defined based on unscented transformation, after that, the measured covariance and state covariance are online adjusted by measured residual and adaptive factor, then the self-adapting capability of filter gain and the real-time capability of posterior probability density function are improved. Finally, the simulation results between different algorithms show the validity and superiority of the presented algorithm in tracking accuracy, stability and real-time capability.

• Periodical: Applied Mechanics and Materials (Volumes 190-191)
• Pages: 906-910
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.190-191.906
• Online since: July 2012
• Authors: Hong Jiang Liu
• Keywords: Adaptive Algorithm, Measured Residual, Target Tracking, Unscented Particle Filter

References

[1] Y.L Liu, X. H Gu, Current statistical model tracking algorithm based on improved auxiliary particle filter[J],Systems Engineering and Electronics. 2010, 32(6):1206:1209.

[2] Y. I Wu, K. T Wong, S Lau.The Acoustic Vector-Sensor's Near-Field Array-Manifold[J]. IEEE Trans.on Signal Processing. 2010,58(7):121-125.

DOI: 10.1109/tsp.2010.2047393

[3] H. A Blom, Y.B Shalom. The Interacting Multiple Model Algorithm for Systems with Markovian Switching Coefficient[J]. IEEE Trans on AC, 1998,33(8): 780-783.

DOI: 10.1109/9.1299

[4] F.M Sun,X. Q Wu. Adaptive tracking algorithm based on MCSM[J]. Systems Engineering and Electronics, 2007,9(9):1420-1423.

[5] F. Dufour, M. Mariton. Tracking a 3D Maneuvering Target withPassive Sensors [J]. IEEE Trans on AES, 1991,27(4):725-739.

DOI: 10.1109/7.85047

[6] S. Y Xu, Z. P Chen. Comparison of Nonlinear Filtering for Passive Bistatic Radar Target Tracking[J]. Journal of System Simulation, 2008,1(1):128-131.

[7] P. P Pan, X. X Feng, F. Li. Adaptive constant acceleration model and tracking algorithm based on strong tracking filter[J]. Systems Engineering Theory and Practise, 2008,5(5):136-141.

[8] Y. L Liu, B.J Lin. Swarm intelligence particle filtering based on niching technique [J], Control and Decision, 2010,32(6):1271-1276.

[9] A. Doucet, S. J, Godsilli C. Abdrueu. On sequential Monte Carlo sampling methods for Bayesian filtering[J]. Statistics and Computing, 2000,10(3): 197-208

[10] Z. J Yuan, N. N Zheng, X. C Jia. The Gauss Hermite particle filter[J]. Acta Electronica Sinica, 2003,31(7): 970-973.