Image super-resolution for outdoor digital forensics. Usability and legal aspects

Salvador Villena, Miguel Vega, Javier Mateos, Duska Rosenberg, Fionn Murtagh, Rafael Molina, Aggelos K. Katsaggelos

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Digital Forensics encompasses the recovery and investigation of data, images, and recordings found in digital devices in order to provide evidence in the court of law. This paper is devoted to the assessment of digital evidence which requires not only an understanding of the scientific technique that leads to improved quality of surveillance video recordings, but also of the legal principles behind it. Emphasis is given on the special treatment of image processing in terms of its handling and explanation that would be acceptable in a court of law. In this context, we propose a variational Bayesian approach to multiple-image super-resolution based on Super-Gaussian prior models that automatically enhances the quality of outdoor video recordings and estimates all the model parameters while preserving the authenticity, credibility and reliability of video data as digital evidence. The proposed methodology is validated both quantitatively and visually on synthetic videos generated from single images and real-life videos and applied to a real-life case of damages and stealing in a private property.
LanguageEnglish
Pages34-47
Number of pages14
JournalComputers in Industry
Volume98
Early online date8 Mar 2018
DOIs
Publication statusPublished - Jun 2018

Fingerprint

Video recording
Digital devices
Image processing
Recovery
Digital forensics

Cite this

Villena, Salvador ; Vega, Miguel ; Mateos, Javier ; Rosenberg, Duska ; Murtagh, Fionn ; Molina, Rafael ; Katsaggelos, Aggelos K. / Image super-resolution for outdoor digital forensics. Usability and legal aspects. In: Computers in Industry. 2018 ; Vol. 98. pp. 34-47.
@article{35f76e18880447b996d9b9c758086d89,
title = "Image super-resolution for outdoor digital forensics. Usability and legal aspects",
abstract = "Digital Forensics encompasses the recovery and investigation of data, images, and recordings found in digital devices in order to provide evidence in the court of law. This paper is devoted to the assessment of digital evidence which requires not only an understanding of the scientific technique that leads to improved quality of surveillance video recordings, but also of the legal principles behind it. Emphasis is given on the special treatment of image processing in terms of its handling and explanation that would be acceptable in a court of law. In this context, we propose a variational Bayesian approach to multiple-image super-resolution based on Super-Gaussian prior models that automatically enhances the quality of outdoor video recordings and estimates all the model parameters while preserving the authenticity, credibility and reliability of video data as digital evidence. The proposed methodology is validated both quantitatively and visually on synthetic videos generated from single images and real-life videos and applied to a real-life case of damages and stealing in a private property.",
keywords = "legal aspects, outdoor surveillance, super-resolution, usability",
author = "Salvador Villena and Miguel Vega and Javier Mateos and Duska Rosenberg and Fionn Murtagh and Rafael Molina and Katsaggelos, {Aggelos K.}",
year = "2018",
month = "6",
doi = "10.1016/j.compind.2018.02.004",
language = "English",
volume = "98",
pages = "34--47",
journal = "Computers in Industry",
issn = "0166-3615",
publisher = "Elsevier",

}

Villena, S, Vega, M, Mateos, J, Rosenberg, D, Murtagh, F, Molina, R & Katsaggelos, AK 2018, 'Image super-resolution for outdoor digital forensics. Usability and legal aspects', Computers in Industry, vol. 98, pp. 34-47. https://doi.org/10.1016/j.compind.2018.02.004

Image super-resolution for outdoor digital forensics. Usability and legal aspects. / Villena, Salvador; Vega, Miguel; Mateos, Javier; Rosenberg, Duska; Murtagh, Fionn; Molina, Rafael; Katsaggelos, Aggelos K.

In: Computers in Industry, Vol. 98, 06.2018, p. 34-47.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Image super-resolution for outdoor digital forensics. Usability and legal aspects

AU - Villena, Salvador

AU - Vega, Miguel

AU - Mateos, Javier

AU - Rosenberg, Duska

AU - Murtagh, Fionn

AU - Molina, Rafael

AU - Katsaggelos, Aggelos K.

PY - 2018/6

Y1 - 2018/6

N2 - Digital Forensics encompasses the recovery and investigation of data, images, and recordings found in digital devices in order to provide evidence in the court of law. This paper is devoted to the assessment of digital evidence which requires not only an understanding of the scientific technique that leads to improved quality of surveillance video recordings, but also of the legal principles behind it. Emphasis is given on the special treatment of image processing in terms of its handling and explanation that would be acceptable in a court of law. In this context, we propose a variational Bayesian approach to multiple-image super-resolution based on Super-Gaussian prior models that automatically enhances the quality of outdoor video recordings and estimates all the model parameters while preserving the authenticity, credibility and reliability of video data as digital evidence. The proposed methodology is validated both quantitatively and visually on synthetic videos generated from single images and real-life videos and applied to a real-life case of damages and stealing in a private property.

AB - Digital Forensics encompasses the recovery and investigation of data, images, and recordings found in digital devices in order to provide evidence in the court of law. This paper is devoted to the assessment of digital evidence which requires not only an understanding of the scientific technique that leads to improved quality of surveillance video recordings, but also of the legal principles behind it. Emphasis is given on the special treatment of image processing in terms of its handling and explanation that would be acceptable in a court of law. In this context, we propose a variational Bayesian approach to multiple-image super-resolution based on Super-Gaussian prior models that automatically enhances the quality of outdoor video recordings and estimates all the model parameters while preserving the authenticity, credibility and reliability of video data as digital evidence. The proposed methodology is validated both quantitatively and visually on synthetic videos generated from single images and real-life videos and applied to a real-life case of damages and stealing in a private property.

KW - legal aspects

KW - outdoor surveillance

KW - super-resolution

KW - usability

UR - http://www.scopus.com/inward/record.url?scp=85042911645&partnerID=8YFLogxK

U2 - 10.1016/j.compind.2018.02.004

DO - 10.1016/j.compind.2018.02.004

M3 - Article

VL - 98

SP - 34

EP - 47

JO - Computers in Industry

T2 - Computers in Industry

JF - Computers in Industry

SN - 0166-3615

ER -