Bio-inspired Neural Networks for Block based Motion Estimation

In the multi-view video coding, both temporal and interview redundancies can be exploited by using standard block-based motion estimation technique. This paper describes a novel Bio-inspired neural networks model to enhance regions and extract contours of image for block-based motion estimation. We implements the optimized algorithm in the reference model of H. 264 compiled by VC6.0, and chooses six typical video sequences for simulation comparison. Experiments performed show the good visual results which can reduces the computational complexity in a certain degree and enhances encoding efficiency with few changes in the reconstructed image quality and bit rate.