An Overview on Deep Learning Techniques for Video Compressive Sensing

Applied Sciences

卷:12

Wael Saideni¹  Jean-Pierre Cances¹  Fabien Courreges²  David Helbert³ 

[1] XLIM Research Institute, UMR CNRS 7252, ENSIL-ENSCI, 16 Atlantis Street, 87280 Limoges, France;

[2] XLIM Research Institute, UMR CNRS 7252, University Campus, 16 Jules Vallès Street, 19100 Brive-la-Gaillarde, France;

[3] XLIM Research Institute, UMR CNRS 7252, University of Poitiers, 15 Hotel Dieu Street, 86073 Poitiers, France;

关键词: video compressive sensing;    deep learning;    optimization;    loss function;    computer vision;    image and video reconstruction;   

DOI  :  10.3390/app12052734

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown