An improved distributed compressed video sensing scheme in reconstruction algorithm

Zheng, Shuai; Chen, Jian; Kuo, Yan-Fu

doi:10.1007/s11042-017-4765-z

Cited by 7 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On basis of DCVS, well-known video CS algorithms are proposed, such as BCS-SP, and BCS-SPL, 21,22 BCS-SPL based on multiple hypothesis(MH-BCS-SPL) 23,24 and so on. Zheng et al 122 proposed an auxiliary iterative termination decision algorithm using a position intersection reduction algorithm to improve the reconstruction quality of non-reference frames, and the reconstruction was performed by a weight prediction algorithm to enable the effective recovery of key frames. Chen et al 25 proposed HSU and DRS to improve DCVS.…”

Section: Video Reconstruction Using Distributed Compressive Video Sen...mentioning

confidence: 99%

Survey on compressed sensing reconstruction method for3Ddata

Zhang

Xie

2022

Concurrency and Computation

View full text Add to dashboard Cite

The information society has higher and higher requirements for the collection, transmission and storage of digital signals, and signal utilization efficiency has become an increasingly important part of the digital signal processing process. The traditional digital signal processing needs to satisfy the Nyquist sampling theorem to ensure the restoration of the signal, while the digital signal processing method based on compressed sensing can sample and reconstruct the signal under the conditions that much lower than the Nyquist sampling theorem. Undoubtedly, the utilization efficiency of digital signals has been greatly accelerated. In this article, taking hyperspectral images and videos as examples, we review the basic theory, reconstruction model, and reconstruction algorithm of 3D data compressed sensing. We analyze, summarize, and discuss the existing literature. Finally, the research status of compressive sensing reconstruction methods for hyperspectral images and videos is compared, and several important research directions for compressive sensing reconstruction of 3D data in the future are proposed.

show abstract

Section: Video Reconstruction Using Distributed Compressive Video Sen...mentioning

confidence: 99%

Survey on compressed sensing reconstruction method for3Ddata

Zhang

Xie

2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…The core of DISCOS is multi-hypothesis prediction [10] and residual reconstruction [11], which ensures high reconstruction quality. Several adaptive derivatives based on DISCOS have been proposed [12][13][14][15]; however, these derivatives cannot meet the requirement of real-time video communication because of their high computational complexity. A state-of-the-art DCVS framework was proposed by Kang and Lu [16].…”

Section: Introductionmentioning

confidence: 99%

Perceptual hash algorithm‐based adaptive GOP selection algorithm for distributed compressive video sensing

Chen

Ding

Zhang

2018

IET Image Processing

View full text Add to dashboard Cite

“…In [1], Fowler proposed a single Tikhonov regularization which achieves acceptable performance and speeds up the reconstruction. Combing with the Tikhonov regularization, Chen [4] presented an elastic net-based scheme for DCVS which as- sumes the coefficient vector to be sparse. Moreover, instead of considering the sparsity of the coefficient vector, Azghani [6] incorporated the MH technique with the sparsity constraint on the frames and the Tikhonov regularization, and presented an iterative algorithm using ADMM technique.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, instead of considering the sparsity of the coefficient vector, Azghani [6] incorporated the MH technique with the sparsity constraint on the frames and the Tikhonov regularization, and presented an iterative algorithm using ADMM technique. Compared with the Tikhonov-based scheme [1], although these methods [4] and [6] achieve better reconstruction quality, they are at the cost of higher computational complexity. Furthermore, the prediction generated from this map can be likely inaccurate at a low sampling rate, which can lead to poor reconstruction performance, e.g., the value of pixels of the prediction can beyond a range of 0 to 255 through the linear combination of hypothesis set.…”

Section: Introductionmentioning

confidence: 99%

Resample-Based Hybrid Multi-Hypothesis Scheme for Distributed Compressive Video Sensing

Chen

Zhang

Liu

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYMulti-hypothesis prediction technique, which exploits inter-frame correlation efficiently, is widely used in block-based distributed compressive video sensing. To solve the problem of inaccurate prediction in multi-hypothesis prediction technique at a low sampling rate and enhance the reconstruction quality of non-key frames, we present a resamplebased hybrid multi-hypothesis scheme for block-based distributed compressive video sensing. The innovations in this paper include: (1) multihypothesis reconstruction based on measurements reorganization (MR-MH) which integrates side information into the original measurements; (2) hybrid multi-hypothesis (H-MH) reconstruction which mixes multiple multi-hypothesis reconstructions adaptively by resampling each reconstruction. Experimental results show that the proposed scheme outperforms the state-of-the-art technique at the same low sampling rate.

show abstract

An improved distributed compressed video sensing scheme in reconstruction algorithm

Cited by 7 publications

References 23 publications

Survey on compressed sensing reconstruction method for3Ddata

Survey on compressed sensing reconstruction method for3Ddata

Perceptual hash algorithm‐based adaptive GOP selection algorithm for distributed compressive video sensing

Resample-Based Hybrid Multi-Hypothesis Scheme for Distributed Compressive Video Sensing

Contact Info

Product

Resources

About