Compressive Video Sensing via Dictionary Learning and Forward Prediction

TL;DR

This paper introduces a compressive video sensing framework that leverages spatial and temporal redundancies by using adaptive dictionary learning for key frames and forward prediction for non-key frames, demonstrating improved reconstruction quality.

Contribution

It presents a novel CVS method combining adaptive dictionary learning for key frames and forward prediction for non-key frames, enhancing redundancy exploitation.

Findings

Achieves higher PSNR and SSIM compared to existing methods.

Effectively exploits spatial and temporal redundancies in video.

Investigates three dictionary learning algorithms for improved reconstruction.

Abstract

In this paper, we propose a new framework for compressive video sensing (CVS) that exploits the inherent spatial and temporal redundancies of a video sequence, effectively. The proposed method splits the video sequence into the key and non-key frames followed by dividing each frame into small non-overlapping blocks of equal sizes. At the decoder side, the key frames are reconstructed using adaptively learned sparsifying (ALS) basis via $\ell_0$ minimization, in order to exploit the spatial redundancy. Also, the effectiveness of three well-known dictionary learning algorithms is investigated in our method. For recovery of the non-key frames, a prediction of the current frame is initialized, by using the previous reconstructed frame, in order to exploit the temporal redundancy. The prediction is employed in a proper optimization problem to recover the current non-key frame. To compare our experimental results with the results of some other methods, we employ peak signal to noise ratio (PSNR) and structural similarity (SSIM) index as the quality assessor. The numerical results show the adequacy of our proposed method in CVS.