Efficient and configurable full-search block-matching processors

Efficient VLSI architectures for motion estimation using the full-search block-matching algorithm are proposed in this paper. These structures are based on an improved and more efficient two-dimensional single-array architecture with minimum latency, maximum throughput, and full utilization of the hardware resources. This optimized architecture is extended to a class of fully parameterizable multiple array architectures that combine both pipelining and parallel processing techniques and provide the ability to configure the processors according to the setup parameters, the processing time and the circuit area specified limits. The development of a single-array processor in a single-chip based on a 0.25-μm CMOS technology process proves the practical interest of the proposed architecture for implementing real-time motion estimators.