Design and optimization of a parallel architecture dedicated to image matching

The design and optimised (in time and space) implementation of a systolic circuit dedicated to aerial image matching is proposed. The final run time data adaptive architecture evaluation with Xilinx XC 4010 XL offers the equivalent processing speed-up of 2000 (compared to a sequential solution).

[1]  Jean Frédéric Myoupo.  Mapping dynamic programming onto modular linear systolic arrays , 2005, Distributed Computing.

[2]  Viktor K. Prasanna,et al.  Mapping dynamic programming onto a linear systolic array , 1990, J. VLSI Signal Process..

[3]  Edwige E. Pissaloux,et al.  Parallel method for matching of aerial images , 1996, Other Conferences.

[4]  G. M. Quenot.  The 'orthogonal algorithm' for optical flow detection using dynamic programming , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Henri Maître,et al.  Improving dynamic programming to solve image registration , 1987, Pattern Recognit..

[6]  Edwige Pissaloux,et al.  A parallel algorithm for a very fast 2D velocity field estimation , 1997, Proceedings of International Conference on Image Processing.

[7]  M. Lightner,et al.  A modular architecture for dynamic programming and maximum likelihood sequence estimation , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.