
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
E.K.B. Lee, S. Haykin, "Parallel Implementation of the Extended SquareRoot Covariance Filter for Tracking Applications," IEEE Transactions on Parallel and Distributed Systems, vol. 4, no. 4, pp. 446457, April, 1993.  
BibTex  x  
@article{ 10.1109/71.219759, author = {E.K.B. Lee and S. Haykin}, title = {Parallel Implementation of the Extended SquareRoot Covariance Filter for Tracking Applications}, journal ={IEEE Transactions on Parallel and Distributed Systems}, volume = {4}, number = {4}, issn = {10459219}, year = {1993}, pages = {446457}, doi = {http://doi.ieeecomputersociety.org/10.1109/71.219759}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Parallel and Distributed Systems TI  Parallel Implementation of the Extended SquareRoot Covariance Filter for Tracking Applications IS  4 SN  10459219 SP446 EP457 EPD  446457 A1  E.K.B. Lee, A1  S. Haykin, PY  1993 KW  Index Termsextended squareroot covariance filter; tracking; tracking Kalman filter; computationalrequirements; parallelism; decoupling technique; Kalman gain; Kalman filters; parallelalgorithms VL  4 JA  IEEE Transactions on Parallel and Distributed Systems ER   
Parallel implementations of the extended squareroot covariance filter (ESRCF) for tracking applications are developed. The decoupling technique and special properties used in the tracking Kalman filter (KF) are employed to reduce computational requirements and to increase parallelism. The application of the decoupling technique to the ESRCF results in the time and measurement updates of m decoupled (n/m)dimensional matrices instead of one coupled ndimensional matrix, where m denotes the tracking dimension and n denotes the number of state elements. The updates of m decoupled matrices are found to require approximately m fewer processing elements and clock cycles than the updates of one coupled matrix. The transformation of the Kalman gain which accounts for the decoupling is found to be straightforward to implement. The sparse nature of the measurement matrix and the sparse, band nature of the transition matrix are explored to simplify matrix multiplications.
[1] B. D. O. Anderson and J. B. Moore,Optimal Filtering. Englewood Cliffs, NJ: PrenticeHall, 1979.
[2] R. S. Baheti, "Efficient approximation of Kalman filter for target tracking,"IEEE Trans. AES, vol. AES22, no. 1, pp. 814, 1986.
[3] R. S. Baheti, D. R. O'Hallaron, and H. R. Itzkowitz, "Mapping extended Kalman filters onto linear arrays,"IEEE Trans. Automat. Contr., 1990.
[4] R. S. Baheti and O. R. Halloran, "Efficient parallel implementation of target tracking Kalman filter," inProc. IEEE 27th Conf. Decision and Contr., 1988, pp. 376381.
[5] G. Bierman,Factorization Methods for Discrete Sequential Estimation. New York Academic, 1977.
[6] M. J. Chen and K. Yao, "On realization of leastsquares estimation and Kalman filtering," inProc. 1st. Int. Workshop Systolic Arrays, Oxford, 1986, pp. 161170.
[7] F. E. Daum and J. Fitzgerald, "Decoupled Kalman filters for phased array radar tracking,"IEEE Trans. Automat. Contr., vol. AC28, pp. 269283, 1983.
[8] J. L. Fisher, D. P. Casasent, and C. P. Neuman, "A factorized extended Kalman filter," inProc. SPIE 85, RealTime Signal Processing, 1985, pp. 119130.
[9] F. M. F. Gaston and G. W. Irwin, "VLSI architecture for square root covariance Kalman filtering," inProc. SPIE 89, RealTime Signal Processing, 1989, pp. 4455.
[10] W. M. Gentleman and H. T. Kung, "Matrix triangularization by systolic arrays," inProc. SPIE 81, RealTime Signal Processing, 1981, pp. 1926.
[11] G. H. Golub and C. F. Van Loan,Matrix Computations. Baltimore, MD: John Hopkins University Press, 1983.
[12] A. H. Jazwinski,Stochastic Processes and Filtering Theory. New York: Academic, 1970.
[13] J. M. Jover and T. Kailath, "A parallel architecture for Kalman filter measurement update," inProc. IFAC 84, Hungary, 1984, pp. 10051009.
[14] R. E. Kalman, "A new approach to linear filtering and prediction problems,"Trans. ASME, (J. Basic Eng.), vol. 82, pp. 3550, 1960.
[15] P. G. Kaminski, A. E. Bryson, and S. F. Schmidt, "Discrete square root filtering: A survey of current techniques,"IEEE Trans. Automat. Contr., vol. AC16, pp. 727735, 1971.
[16] R. T. Kee and G. W. Irwin, "Transputer implementation of tracking Kalman filters," inProc. IEEE Int. Conf. Contr., vol. 1, 1991, pp. 145150.
[17] S.Y. Kung,VLSI Array Processors, Prentice Hall, Englewood Cliffs, N.J. 1988.
[18] S. Y. Kung and J. N. Hwang, "An efficient triarray systolic design for realtime Kalman filtering," inProc. ICSASSP, 1988, pp. 20452048.
[19] E. K. B. Lee and S. Haykin, "Parallel implementation of the tracking Kalman filter," inProc. ICASSP 88, pp. 20922094.
[20] T. Ohmuro, "A decoupled Kalman tracker using LOS coordinates," inProc. 1984 Int. Symp. Noise and Clutter Rejection in Radars and Imaging Sensors, 1984, pp. 451455.
[21] R. A. Singer and K. W. Behnke, "Realtime tracking filter evaluation and selection for tracking applications,"IEEE Trans. AES, vol. AES7, no. 1, pp. 100110, 1971.
[22] T. Sung and Y. Hu, "Parallel VLSI implementation of the Kalman filter,"IEEE Trans. AES, vol. AES23, no. 2, pp. 215224, 1987.
[23] E. J. Volder, "The CORDIC trigonometric computing technique,"IRE Trans. Electron. Comput., pp. 330334, 1959.
[24] H. G. Yeh, "Systolic implementation of Kalman filtering,"IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP35, no. 9, pp. 15141517, Sept. 1987.