Parallel rate-distortion optimised fast motion estimation algorithm for H.264/AVC using GPU

Recently, the parallel processing capability of the Graphics Processing Unit (GPU) has been employed for accelerating motion estimation in H.264/AVC encoder implementations. However, while implementing parallel motion estimation on GPU, the bit rate cost of the motion vector is generally ignored. This is due to the unavailability of the spatially predicted motion vectors, which leads to rate-distortion performance degradation. This paper presents a fast parallel motion estimation algorithm implemented on GPU using OpenCL to tackle this problem. The predicted motion vectors are estimated from temporally predicted motion vectors and used for evaluating the bit rate cost of the motion vectors simultaneously. The experimental results show that the proposed scheme achieves significant speedup and has comparable rate-distortion performance with respect to sequential fast motion estimation algorithm.