An Overview on Deep Learning Techniques for Video Compressive Sensing

Abstract

The use of compressive sensing in several applications has allowed to capture impressive results, especially in various applications such as image and video processing and it has become a promising direction of scientific research. It provides extensive application value in optimizing video surveillance networks. In this paper, we introduce recent state-of-the-art video compressive sensing methods based on neural networks and categorize them into different categories. We compare these approaches by analyzing the networks architectures. Then, we present their pros and cons. The general conclusion of the paper identify open research challenges and point out future research directions. The goal of this paper is to overview the current approaches in image and video compressive sensing and demonstrate their powerful impact in computer vision when using well designed compressive sensing algorithms.

An Enhanced Subsampling Technique in Compressive Sensing using Linear Interpolation and Random Measurement Matrix

“…In some papers, it is either the case that the relevance of the incoherence of a measurement matrix required for subsampling is watered down like in [6], or as observed in [5] the subsampling techniques largely proposed for signal reconstruction still have an implicit significant probability of coherence within the sensing matrix, with an insufficient theoretical framework to provide certainty of a successful CS method. In [4] and [12] The rest of the paper is organized as follows;…”

“…The underdetermined CS problem as stated in [4][5][6][7] and also explained earlier, was formulated in MATLAB as follows:…”

“…While sparsity refers to when a signal (matrix) has fewer non-zero entries than zero entries [3], incoherence has to do with the requirement that measurements of the original signal taken need to evenly represent random sections of the given signal. More precisely, as mathematically presented in the CS problem stated in [4][5][6][7], and subsequently in this paper, the measurement matrix, Φ, should not be parallel with the columns of the transform basis matrix, Ψ, such that it only subsamples signals from those columns at the expense of the other columns [3]. What incoherence aims at is to have randomness with measurements taken from a signal to increase the efficiency of its reconstruction.…”

A Compact Dual-dispersion Architecture for Snapshot Compressive Spectral Imaging

“…. , B, are independently generated as stationary first order Markov processes with transition probabilities described in (8). For x ∈ Q and y = B i=1 D i x i let x denote the solution of (6).…”

“…Various methods have been proposed in the literature for solving such inverse problems., e.g. see [8]- [12]. While SCI systems are under-MZ is with the Electrical and computer Engineering Department of Rutgers University.…”