Video compressed sensing using iterative self-similarity modeling and residual reconstruction

Yookyung Kim, Han Oh, Ali Bilgin

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Compressed sensing (CS) has great potential for use in video data acquisition and storage because it makes it unnecessary to collect an enormous amount of data and to perform the computationally demanding compression process. We propose an effective CS algorithm for video that consists of two iterative stages. In the first stage, frames containing the dominant structure are estimated. These frames are obtained by thresholding the coefficients of similar blocks. In the second stage, refined residual frames are reconstructed from the original measurements and the measurements corresponding to the frames estimated in the first stage. These two stages are iterated until convergence. The proposed algorithm exhibits superior subjective image quality and significantly improves the peak-signalto- noise ratio and the structural similarity index measure compared to other state-of-the-art CS algorithms.

Original languageEnglish (US)
Article number021005
JournalJournal of Electronic Imaging
Volume22
Issue number2
DOIs
StatePublished - 2013

Fingerprint

video compression
Compressed sensing
video data
Image quality
Data acquisition
data storage
data acquisition
coefficients

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Atomic and Molecular Physics, and Optics

Cite this

Video compressed sensing using iterative self-similarity modeling and residual reconstruction. / Kim, Yookyung; Oh, Han; Bilgin, Ali.

In: Journal of Electronic Imaging, Vol. 22, No. 2, 021005, 2013.

Research output: Contribution to journalArticle

@article{b7a0d524c07549f9819497d3c4f4ef38,
title = "Video compressed sensing using iterative self-similarity modeling and residual reconstruction",
abstract = "Compressed sensing (CS) has great potential for use in video data acquisition and storage because it makes it unnecessary to collect an enormous amount of data and to perform the computationally demanding compression process. We propose an effective CS algorithm for video that consists of two iterative stages. In the first stage, frames containing the dominant structure are estimated. These frames are obtained by thresholding the coefficients of similar blocks. In the second stage, refined residual frames are reconstructed from the original measurements and the measurements corresponding to the frames estimated in the first stage. These two stages are iterated until convergence. The proposed algorithm exhibits superior subjective image quality and significantly improves the peak-signalto- noise ratio and the structural similarity index measure compared to other state-of-the-art CS algorithms.",
author = "Yookyung Kim and Han Oh and Ali Bilgin",
year = "2013",
doi = "10.1117/1.JEI.22.2.021005",
language = "English (US)",
volume = "22",
journal = "Journal of Electronic Imaging",
issn = "1017-9909",
publisher = "SPIE",
number = "2",

}

TY - JOUR

T1 - Video compressed sensing using iterative self-similarity modeling and residual reconstruction

AU - Kim, Yookyung

AU - Oh, Han

AU - Bilgin, Ali

PY - 2013

Y1 - 2013

N2 - Compressed sensing (CS) has great potential for use in video data acquisition and storage because it makes it unnecessary to collect an enormous amount of data and to perform the computationally demanding compression process. We propose an effective CS algorithm for video that consists of two iterative stages. In the first stage, frames containing the dominant structure are estimated. These frames are obtained by thresholding the coefficients of similar blocks. In the second stage, refined residual frames are reconstructed from the original measurements and the measurements corresponding to the frames estimated in the first stage. These two stages are iterated until convergence. The proposed algorithm exhibits superior subjective image quality and significantly improves the peak-signalto- noise ratio and the structural similarity index measure compared to other state-of-the-art CS algorithms.

AB - Compressed sensing (CS) has great potential for use in video data acquisition and storage because it makes it unnecessary to collect an enormous amount of data and to perform the computationally demanding compression process. We propose an effective CS algorithm for video that consists of two iterative stages. In the first stage, frames containing the dominant structure are estimated. These frames are obtained by thresholding the coefficients of similar blocks. In the second stage, refined residual frames are reconstructed from the original measurements and the measurements corresponding to the frames estimated in the first stage. These two stages are iterated until convergence. The proposed algorithm exhibits superior subjective image quality and significantly improves the peak-signalto- noise ratio and the structural similarity index measure compared to other state-of-the-art CS algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84879657318&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879657318&partnerID=8YFLogxK

U2 - 10.1117/1.JEI.22.2.021005

DO - 10.1117/1.JEI.22.2.021005

M3 - Article

VL - 22

JO - Journal of Electronic Imaging

JF - Journal of Electronic Imaging

SN - 1017-9909

IS - 2

M1 - 021005

ER -