Reconstruction of compressed-sensed video using compound regularization

Abstract

This paper introduces a novel reconstruction model with compound regularization to recover compressed-sensed video sequences. For a target frame, the compound regularization consists of total variation (TV) norm of the frame, l 1 norm of the frame in a certain transform domain, and TV norm of the residual between the frame and its prediction. The first two terms in the compound regularization are used to describe image characteristics, while the third term exploits inter-frame correlation within video sequences. To solve the minimization problem, a new splitting objective function is considered, and it is divided into sub-problems that are easy to solve. In addition, bivariate shrinkage method is integrated into the proposed algorithm so that high quality of reconstruction results can be guaranteed. Experimental results show that the proposed algorithms are substantially superior to state-ofthe-art reconstruction methods.

Research on Information Applied Technology with Video Compression Algorithms Based on the Optimal Multi-Band Haar Wavelet Transform

“…In recent years, the stereoscopic video compression scheme has attracted much more attention from all over the world [4]. Some European countries like Germany and France jointly developed DISTIMA project since 1992, on the basis of MPEG-2 coding standard, to implement a complete stereo video communication system [5]. Another European plan ATTEST proposed a novel stereo video compression scheme with one road transporting MPEG-2 video image with color information, the other transporting depth information through Depth Based Image Rendering technique to generate three-dimensional effect on the receiving end [6][7].…”