Scalable Saliency-Aware Distributed Compressive Video Sensing

Jin Xu; Soufiene Djahel; Yuansong Qiao

doi:10.1109/ISM.2015.54

Scalable Saliency-Aware Distributed Compressive Video Sensing

Jin Xu, Soufiene Djahel, Yuansong Qiao

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Distributed compressive video sensing (DCVS) is an emerging low-complexity video coding framework which integrates the merits of distributed video coding (DVC) and compressive sensing (CS). Because the human visual system (HVS) is the ultimate receiver of visual signals, we aim to improve the perceptual rate-distortion performance of DCVS by designing a novel scalable saliency-aware DCVS codec. Firstly, we perform saliency estimation in the the side information (SI) frame generated at the decoder side and adaptively control the size of region-of-interest (ROI) according to the measurements budget by applying a saliency guided foveation model. Subsequently, based on online estimation of the correlation noise between a non-key frame and its SI, we develop a saliency-aware block compressive sensing scheme to more accurately reconstruct the ROI of each non-key frame. The obtained experimental results reveal that our DCVS codec outperforms the legacy DCVS codecs in terms of the perceptual rate-distortion performance.

Original language	English
Title of host publication	Proceedings - 2015 IEEE International Symposium on Multimedia, ISM 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	327-330
Number of pages	4
ISBN (Electronic)	9781509003792, 9781509003785
DOIs	https://doi.org/10.1109/ISM.2015.54
Publication status	Published - 28 Mar 2016
Externally published	Yes
Event	17th IEEE International Symposium on Multimedia - Miami, United States Duration: 14 Dec 2015 → 16 Dec 2015 Conference number: 17

Conference

Conference	17th IEEE International Symposium on Multimedia
Abbreviated title	ISM 2015
Country/Territory	United States
City	Miami
Period	14/12/15 → 16/12/15

Access to Document

10.1109/ISM.2015.54Licence: Unspecified

Cite this

@inproceedings{170816a18a15443b9949d81ffcbb64b4,

title = "Scalable Saliency-Aware Distributed Compressive Video Sensing",

abstract = "Distributed compressive video sensing (DCVS) is an emerging low-complexity video coding framework which integrates the merits of distributed video coding (DVC) and compressive sensing (CS). Because the human visual system (HVS) is the ultimate receiver of visual signals, we aim to improve the perceptual rate-distortion performance of DCVS by designing a novel scalable saliency-aware DCVS codec. Firstly, we perform saliency estimation in the the side information (SI) frame generated at the decoder side and adaptively control the size of region-of-interest (ROI) according to the measurements budget by applying a saliency guided foveation model. Subsequently, based on online estimation of the correlation noise between a non-key frame and its SI, we develop a saliency-aware block compressive sensing scheme to more accurately reconstruct the ROI of each non-key frame. The obtained experimental results reveal that our DCVS codec outperforms the legacy DCVS codecs in terms of the perceptual rate-distortion performance.",

keywords = "Distributed compressive video sensing, human visual system, perceptual coding, scalable region-of-interest",

author = "Jin Xu and Soufiene Djahel and Yuansong Qiao",

note = "Funding Information: This work was supported in part by the scholarship from China Scholarship Council (No.201308515002) and and Science Foundation Ireland Grant (10/CE/I1855, 13/RC/2094). Publisher Copyright: {\textcopyright} 2015 IEEE.; 17th IEEE International Symposium on Multimedia, ISM 2015 ; Conference date: 14-12-2015 Through 16-12-2015",

year = "2016",

month = mar,

day = "28",

doi = "10.1109/ISM.2015.54",

language = "English",

pages = "327--330",

booktitle = "Proceedings - 2015 IEEE International Symposium on Multimedia, ISM 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Xu, J, Djahel, S & Qiao, Y 2016, Scalable Saliency-Aware Distributed Compressive Video Sensing. in Proceedings - 2015 IEEE International Symposium on Multimedia, ISM 2015., 7442351, Institute of Electrical and Electronics Engineers Inc., pp. 327-330, 17th IEEE International Symposium on Multimedia, Miami, Florida, United States, 14/12/15. https://doi.org/10.1109/ISM.2015.54

TY - GEN

T1 - Scalable Saliency-Aware Distributed Compressive Video Sensing

AU - Xu, Jin

AU - Djahel, Soufiene

AU - Qiao, Yuansong

N1 - Conference code: 17

PY - 2016/3/28

Y1 - 2016/3/28

N2 - Distributed compressive video sensing (DCVS) is an emerging low-complexity video coding framework which integrates the merits of distributed video coding (DVC) and compressive sensing (CS). Because the human visual system (HVS) is the ultimate receiver of visual signals, we aim to improve the perceptual rate-distortion performance of DCVS by designing a novel scalable saliency-aware DCVS codec. Firstly, we perform saliency estimation in the the side information (SI) frame generated at the decoder side and adaptively control the size of region-of-interest (ROI) according to the measurements budget by applying a saliency guided foveation model. Subsequently, based on online estimation of the correlation noise between a non-key frame and its SI, we develop a saliency-aware block compressive sensing scheme to more accurately reconstruct the ROI of each non-key frame. The obtained experimental results reveal that our DCVS codec outperforms the legacy DCVS codecs in terms of the perceptual rate-distortion performance.

AB - Distributed compressive video sensing (DCVS) is an emerging low-complexity video coding framework which integrates the merits of distributed video coding (DVC) and compressive sensing (CS). Because the human visual system (HVS) is the ultimate receiver of visual signals, we aim to improve the perceptual rate-distortion performance of DCVS by designing a novel scalable saliency-aware DCVS codec. Firstly, we perform saliency estimation in the the side information (SI) frame generated at the decoder side and adaptively control the size of region-of-interest (ROI) according to the measurements budget by applying a saliency guided foveation model. Subsequently, based on online estimation of the correlation noise between a non-key frame and its SI, we develop a saliency-aware block compressive sensing scheme to more accurately reconstruct the ROI of each non-key frame. The obtained experimental results reveal that our DCVS codec outperforms the legacy DCVS codecs in terms of the perceptual rate-distortion performance.

KW - Distributed compressive video sensing

KW - human visual system

KW - perceptual coding

KW - scalable region-of-interest

UR - http://www.scopus.com/inward/record.url?scp=84969677359&partnerID=8YFLogxK

U2 - 10.1109/ISM.2015.54

DO - 10.1109/ISM.2015.54

M3 - Conference contribution

AN - SCOPUS:84969677359

SP - 327

EP - 330

BT - Proceedings - 2015 IEEE International Symposium on Multimedia, ISM 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE International Symposium on Multimedia

Y2 - 14 December 2015 through 16 December 2015

ER -

Scalable Saliency-Aware Distributed Compressive Video Sensing

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this