Abstract
A perceptual-based compressed sensing (CS), which focuses the measurements and the recovery on the visually important low-frequency coefficients, is applied for multi-view image signals. High correlation among different views is exploited to generate signal prediction using disparity estimation and compensation techniques. A residual-based recovery is utilised as a joint recovery for the nonreference images to enhance the reconstruction performance. The proposed framework shows remarkable performance improvement over the conventional CS with joint recovery as well as the perceptualbased CS with independent recovery.
| Original language | English |
|---|---|
| Pages (from-to) | 821-823 |
| Number of pages | 3 |
| Journal | Electronics Letters |
| Volume | 52 |
| Issue number | 10 |
| DOIs | |
| Publication status | Published - May 12 2016 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering
Cite this
Distributed perceptual compressed sensing framework for multiview images. / Elsayed, S.; Elsabrouty, M.; Muta, Osamu; Furukawa, Hiroshi.
In: Electronics Letters, Vol. 52, No. 10, 12.05.2016, p. 821-823.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Distributed perceptual compressed sensing framework for multiview images
AU - Elsayed, S.
AU - Elsabrouty, M.
AU - Muta, Osamu
AU - Furukawa, Hiroshi
PY - 2016/5/12
Y1 - 2016/5/12
N2 - A perceptual-based compressed sensing (CS), which focuses the measurements and the recovery on the visually important low-frequency coefficients, is applied for multi-view image signals. High correlation among different views is exploited to generate signal prediction using disparity estimation and compensation techniques. A residual-based recovery is utilised as a joint recovery for the nonreference images to enhance the reconstruction performance. The proposed framework shows remarkable performance improvement over the conventional CS with joint recovery as well as the perceptualbased CS with independent recovery.
AB - A perceptual-based compressed sensing (CS), which focuses the measurements and the recovery on the visually important low-frequency coefficients, is applied for multi-view image signals. High correlation among different views is exploited to generate signal prediction using disparity estimation and compensation techniques. A residual-based recovery is utilised as a joint recovery for the nonreference images to enhance the reconstruction performance. The proposed framework shows remarkable performance improvement over the conventional CS with joint recovery as well as the perceptualbased CS with independent recovery.
UR - http://www.scopus.com/inward/record.url?scp=84969542813&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84969542813&partnerID=8YFLogxK
U2 - 10.1049/el.2016.0477
DO - 10.1049/el.2016.0477
M3 - Article
AN - SCOPUS:84969542813
VL - 52
SP - 821
EP - 823
JO - Electronics Letters
JF - Electronics Letters
SN - 0013-5194
IS - 10
ER -