Accelerating existing non-blind image deblurring techniques through a strap-on limited-memory switched Broyden method

Ichraf Lahouli; Robby Haelterman; Joris Degroote; Michal Shimoni; Geert De Cubber; Rabah Attia

doi:10.1587/transinf.2017MVP0022

Accelerating existing non-blind image deblurring techniques through a strap-on limited-memory switched Broyden method

Ichraf Lahouli, Robby Haelterman, Joris Degroote, Michal Shimoni, Geert De Cubber, Rabah Attia

Résultats de recherche: Contribution à un journal › Article › Revue par des pairs

Résumé

Video surveillance from airborne platforms can suffer from many sources of blur, like vibration, low-end optics, uneven lighting conditions, etc. Many different algorithms have been developed in the past that aim to recover the deblurred image but often incur substantial CPU-time, which is not always available on-board. This paper shows how a "strap-on" quasi-Newton method can accelerate the convergence of existing iterative methods with little extra overhead while keeping the performance of the original algorithm, thus paving the way for (near) real-time applications using on-board processing.

langue originale	Anglais
Pages (de - à)	1288-1295
Nombre de pages	8
journal	IEICE Transactions on Information and Systems
Volume	E101D
Numéro de publication	5
Les DOIs	https://doi.org/10.1587/transinf.2017MVP0022
état	Publié - mai 2018

Accès au document

10.1587/transinf.2017MVP0022

Autres fichiers et liens

Lien vers la publication dans Scopus

SafeShore: System for detection of Threat Agents in Maritime Border Environment
Rabet, L. (Promoteur), Basak, S. (Chercheur), De cubber, G. (Chercheur) & Doroftei, L. (Chercheur)
1/05/16 → 31/12/18
Projet: Recherche

Contient cette citation

@article{e918579bc7f1460bab242e5a9e72ba2e,

title = "Accelerating existing non-blind image deblurring techniques through a strap-on limited-memory switched Broyden method",

abstract = "Video surveillance from airborne platforms can suffer from many sources of blur, like vibration, low-end optics, uneven lighting conditions, etc. Many different algorithms have been developed in the past that aim to recover the deblurred image but often incur substantial CPU-time, which is not always available on-board. This paper shows how a {"}strap-on{"} quasi-Newton method can accelerate the convergence of existing iterative methods with little extra overhead while keeping the performance of the original algorithm, thus paving the way for (near) real-time applications using on-board processing.",

keywords = "Image deblurring, Limited-memory, Quasi-Newton, Switched Broyden method",

author = "Ichraf Lahouli and Robby Haelterman and Joris Degroote and Michal Shimoni and {De Cubber}, Geert and Rabah Attia",

note = "Publisher Copyright: {\textcopyright} 2018 The Institute of Electronics, Information and Communication Engineers.",

year = "2018",

month = may,

doi = "10.1587/transinf.2017MVP0022",

language = "English",

volume = "E101D",

pages = "1288--1295",

journal = "IEICE Transactions on Information and Systems",

issn = "0916-8532",

number = "5",

}

TY - JOUR

T1 - Accelerating existing non-blind image deblurring techniques through a strap-on limited-memory switched Broyden method

AU - Lahouli, Ichraf

AU - Haelterman, Robby

AU - Degroote, Joris

AU - Shimoni, Michal

AU - De Cubber, Geert

AU - Attia, Rabah

PY - 2018/5

Y1 - 2018/5

N2 - Video surveillance from airborne platforms can suffer from many sources of blur, like vibration, low-end optics, uneven lighting conditions, etc. Many different algorithms have been developed in the past that aim to recover the deblurred image but often incur substantial CPU-time, which is not always available on-board. This paper shows how a "strap-on" quasi-Newton method can accelerate the convergence of existing iterative methods with little extra overhead while keeping the performance of the original algorithm, thus paving the way for (near) real-time applications using on-board processing.

AB - Video surveillance from airborne platforms can suffer from many sources of blur, like vibration, low-end optics, uneven lighting conditions, etc. Many different algorithms have been developed in the past that aim to recover the deblurred image but often incur substantial CPU-time, which is not always available on-board. This paper shows how a "strap-on" quasi-Newton method can accelerate the convergence of existing iterative methods with little extra overhead while keeping the performance of the original algorithm, thus paving the way for (near) real-time applications using on-board processing.

KW - Image deblurring

KW - Limited-memory

KW - Quasi-Newton

KW - Switched Broyden method

UR - http://www.scopus.com/inward/record.url?scp=85046297387&partnerID=8YFLogxK

U2 - 10.1587/transinf.2017MVP0022

DO - 10.1587/transinf.2017MVP0022

M3 - Article

AN - SCOPUS:85046297387

SN - 0916-8532

VL - E101D

SP - 1288

EP - 1295

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

IS - 5

ER -

Accelerating existing non-blind image deblurring techniques through a strap-on limited-memory switched Broyden method

Résumé

Accès au document

Autres fichiers et liens

Empreinte digitale

Projets

SafeShore: System for detection of Threat Agents in Maritime Border Environment

Contient cette citation