Research on the applications of the genetic algorithm to sensor registration

Sensor registration is a basis for well-organized sensor network, and a precondition for data fusion. In cases of constant registration errors, batch processing methods are always applied, where the registration is actually viewed as an optimization problem. Such methods are fast convergent, but sometimes they are not flexible in different cases and the optimal techniques used in batch processing methods may provide the suboptimum as solution. What's more, when dealing with a large number of sensors, the batch processing methods may come across numeric problems. To address the registration problem in some practical cases, the evolutionary algorithm based method can be explored. A method based on genetic algorithm, as well as the least squares method, are developed for sensor registration in different simulation scenarios and compared. Simulation results are analyzed to make clear the advantages and disadvantages of the methods.

[1]  I. T. Li,et al.  Multi-target multi-platform sensor registration in geodetic coordinates , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[2]  Alex Fukunaga,et al.  Genetic algorithm portfolios , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[3]  Yaakov Bar-Shalom,et al.  New assignment-based data association for tracking move-stop-move targets , 2004 .

[4]  T. R. Rice,et al.  Removal of alignment errors in an integrated system of two 3-D sensors , 1993 .

[5]  B. Ristic,et al.  Maximum likelihood registration for multiple dissimilar sensors , 2003 .

[6]  R. Bishop,et al.  Solution to a multisensor tracking problem with sensor registration errors , 1999 .

[7]  M. Farooq,et al.  Registration in a distributed multi-sensor environment , 1997, Proceedings of 40th Midwest Symposium on Circuits and Systems. Dedicated to the Memory of Professor Mac Van Valkenburg.

[8]  G. W. Pulford,et al.  Simultaneous registration and tracking for multiple radars with cluttered measurements , 1996, Proceedings of 8th Workshop on Statistical Signal and Array Processing.

[9]  Yaakov Bar-Shalom.  Airborne GMTI radar position bias estimation using static-rotator targets of opportunity , 2001 .

[10]  Yifeng Zhou,et al.  Sensor alignment with Earth-centered Earth-fixed (ECEF) coordinate system , 1999 .

[11]  W.D. Blair,et al.  Estimation of sensor bias in multisensor systems , 1992, Proceedings IEEE Southeastcon '92.

[12]  Henry Leung,et al.  An exact maximum likelihood registration algorithm for data fusion , 1997, IEEE Trans. Signal Process..

[13]  Yifeng Zhou,et al.  A Kalman filter based registration approach for asynchronous sensors in multiple sensor fusion applications , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.