Performance enhanced spatial video compression using global affine frame reconstruction

Abstract

The modern era of information technology suffers a serious loss due to the lack of a cutting edge methodology for storing mega sized videos. It is at this juncture, video compression makes a mark for its necessity. There have been several research outcomes where almost all researchers have followed a particular methodology of adopting GoP (Group of pictures) for video compression, focusing on I (Intra), B (Bi-directional) & P (Predicted) frame determination. These frames remain fixed throughout the process of GoP regardless of the camera motion. Moreover, it also leads to buffering of memory within the past and future thereby consuming more computational time for B-frames. These vital issues are handled by an adaptive framework of determining frames based on a matching criteria rather than utilizing fixed GoP pattern. NSEW affine translation (NAT) is introduced for replacing B-frames with either I or P frame. The framework involves VCAME (Video Compression using Affine Motion Estimation) & VDAW (Video Decompression using Affine Warping) methodologies for compressing and decompressing a video sequence, based on the resulted I & P frames. The methodology was investigated over four vital parameters, the file size, computational time, SSIM (Structural Similarity Index) & PSNR (Peak Signal to Noise ratio), which proved the superiority of the proposed technique. Further, the methodology was also investigated with optimizing the affine motion parameters (AMP) using nonlinear least squares, BFGS (Broyden–Fletcher–Goldfarb–Shanno) and Limited-memory BFGS which yet again proved to be far more superior than conventional techniques yielding an average PSNR gain of 2.52dB.