A high performance reconfigurable Motion Estimation hardware architecture

Motion Estimation (ME) is the most computationally intensive part of video compression and video enhancement systems. For the recently available high definition frame sizes and high frame rates, the computational complexity of full search (FS) ME algorithm is prohibitively high, while the PSNR obtained by fast search ME algorithms is low. Therefore, in this paper, we propose a new ME algorithm and a high performance reconfigurable systolic ME hardware architecture for efficiently implementing this algorithm. The proposed ME algorithm performs up to three different granularity search iterations in different size search ranges based on the application requirements. Simulation results showed that the proposed ME algorithm performs very close to FS algorithm, even though it searches much fewer search locations than FS algorithm. It outperforms successful fast search ME algorithms by searching more search locations than these algorithms. The proposed reconfigurable ME hardware is implemented in VHDL and mapped to a low cost Xilinx XC3S1500-5 FPGA. It works at 130 MHz and is capable of processing high definition and high frame rate video formats in real time. Therefore, it can be used in flat panel displays for frame rate conversion and de-interlacing, and in video encoders.