A Programmable, Maximal Throughput Architecture for Neighborhood Image Processing
We propose a run-time re-configurable architecture for local neighborhood image processing. We discuss how the new architecture can offer improved flexibility to the developer. We show that for a satellite image feature extraction application, our architecture, implemented on Stratix II and Virtex 2 Field Programmable Gate Arrays, achieves similar performance, hardware resource utilization, and throughput as a fully pipelined systolic array architecture.
Citation:
Reid Porter, Jan Frigo, Maya Gokhale, Christophe Wolinski, Francois Charot, Charles Wagner, "A Programmable, Maximal Throughput Architecture for Neighborhood Image Processing," fccm,pp.279-280, 14th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM'06), 2006