Towards 3D Facial Reconstruction from Uncalibrated CCTV Footage

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

19 Downloads (Pure)

Abstract

Facial comparison in 2D is an accepted method in law enforcement and forensic investigation, but pose variations, varying light conditions and low resolution video data can reduce the evidential value of the comparison. Some of these problems might be solved by comparing 3D face models: a face model derived from CCTV camera footage and a reference face model acquired from a suspect. In our case we will assume uncalibrated CCTV footage, because the original camera setup may be destroyed or replaced after the incident, so precise camera information is no longer available. In contrast to other statistical methods, like Morphable Models, we would like to use no additional statistical information at all. Our method is based on a projective reconstruction of landmarks on the face and an auto-calibration step to obtain a 3D face model in a Euclidean space. In our experiment the effect of the number of frames and noise on the landmarks is explored for 3D face reconstruction based on landmarks. An estimation of the 3D face shape can already be obtained using 25 points in 30 frames.
Original languageEnglish
Title of host publication33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux
Place of PublicationEnschede
PublisherWerkgemeenschap voor Informatie- en Communicatietheorie (WIC)
Pages228-234
Number of pages7
ISBN (Print)978-90-365-3383-6
Publication statusPublished - May 2012
Event33rd WIC Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux 2012 - Boekelo, Netherlands
Duration: 24 May 201225 May 2012
Conference number: 33

Conference

Conference33rd WIC Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux 2012
CountryNetherlands
CityBoekelo
Period24/05/1225/05/12

Fingerprint

Closed circuit television systems
Cameras
Law enforcement
Statistical methods
Calibration
Experiments

Keywords

  • METIS-287895
  • 3D Facial Reconstruction
  • CCTV
  • EWI-21975
  • Landmarks
  • SCS-Safety
  • IR-80666

Cite this

van Dam, C., Veldhuis, R., & Spreeuwers, L. (2012). Towards 3D Facial Reconstruction from Uncalibrated CCTV Footage. In 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux (pp. 228-234). Enschede: Werkgemeenschap voor Informatie- en Communicatietheorie (WIC).
van Dam, Chris ; Veldhuis, Raymond ; Spreeuwers, Luuk. / Towards 3D Facial Reconstruction from Uncalibrated CCTV Footage. 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux. Enschede : Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), 2012. pp. 228-234
@inproceedings{926677491ca04d069853856559803db1,
title = "Towards 3D Facial Reconstruction from Uncalibrated CCTV Footage",
abstract = "Facial comparison in 2D is an accepted method in law enforcement and forensic investigation, but pose variations, varying light conditions and low resolution video data can reduce the evidential value of the comparison. Some of these problems might be solved by comparing 3D face models: a face model derived from CCTV camera footage and a reference face model acquired from a suspect. In our case we will assume uncalibrated CCTV footage, because the original camera setup may be destroyed or replaced after the incident, so precise camera information is no longer available. In contrast to other statistical methods, like Morphable Models, we would like to use no additional statistical information at all. Our method is based on a projective reconstruction of landmarks on the face and an auto-calibration step to obtain a 3D face model in a Euclidean space. In our experiment the effect of the number of frames and noise on the landmarks is explored for 3D face reconstruction based on landmarks. An estimation of the 3D face shape can already be obtained using 25 points in 30 frames.",
keywords = "METIS-287895, 3D Facial Reconstruction, CCTV, EWI-21975, Landmarks, SCS-Safety, IR-80666",
author = "{van Dam}, Chris and Raymond Veldhuis and Luuk Spreeuwers",
year = "2012",
month = "5",
language = "English",
isbn = "978-90-365-3383-6",
pages = "228--234",
booktitle = "33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux",
publisher = "Werkgemeenschap voor Informatie- en Communicatietheorie (WIC)",
address = "Netherlands",

}

van Dam, C, Veldhuis, R & Spreeuwers, L 2012, Towards 3D Facial Reconstruction from Uncalibrated CCTV Footage. in 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux. Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), Enschede, pp. 228-234, 33rd WIC Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux 2012, Boekelo, Netherlands, 24/05/12.

Towards 3D Facial Reconstruction from Uncalibrated CCTV Footage. / van Dam, Chris; Veldhuis, Raymond; Spreeuwers, Luuk.

33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux. Enschede : Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), 2012. p. 228-234.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Towards 3D Facial Reconstruction from Uncalibrated CCTV Footage

AU - van Dam, Chris

AU - Veldhuis, Raymond

AU - Spreeuwers, Luuk

PY - 2012/5

Y1 - 2012/5

N2 - Facial comparison in 2D is an accepted method in law enforcement and forensic investigation, but pose variations, varying light conditions and low resolution video data can reduce the evidential value of the comparison. Some of these problems might be solved by comparing 3D face models: a face model derived from CCTV camera footage and a reference face model acquired from a suspect. In our case we will assume uncalibrated CCTV footage, because the original camera setup may be destroyed or replaced after the incident, so precise camera information is no longer available. In contrast to other statistical methods, like Morphable Models, we would like to use no additional statistical information at all. Our method is based on a projective reconstruction of landmarks on the face and an auto-calibration step to obtain a 3D face model in a Euclidean space. In our experiment the effect of the number of frames and noise on the landmarks is explored for 3D face reconstruction based on landmarks. An estimation of the 3D face shape can already be obtained using 25 points in 30 frames.

AB - Facial comparison in 2D is an accepted method in law enforcement and forensic investigation, but pose variations, varying light conditions and low resolution video data can reduce the evidential value of the comparison. Some of these problems might be solved by comparing 3D face models: a face model derived from CCTV camera footage and a reference face model acquired from a suspect. In our case we will assume uncalibrated CCTV footage, because the original camera setup may be destroyed or replaced after the incident, so precise camera information is no longer available. In contrast to other statistical methods, like Morphable Models, we would like to use no additional statistical information at all. Our method is based on a projective reconstruction of landmarks on the face and an auto-calibration step to obtain a 3D face model in a Euclidean space. In our experiment the effect of the number of frames and noise on the landmarks is explored for 3D face reconstruction based on landmarks. An estimation of the 3D face shape can already be obtained using 25 points in 30 frames.

KW - METIS-287895

KW - 3D Facial Reconstruction

KW - CCTV

KW - EWI-21975

KW - Landmarks

KW - SCS-Safety

KW - IR-80666

M3 - Conference contribution

SN - 978-90-365-3383-6

SP - 228

EP - 234

BT - 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux

PB - Werkgemeenschap voor Informatie- en Communicatietheorie (WIC)

CY - Enschede

ER -

van Dam C, Veldhuis R, Spreeuwers L. Towards 3D Facial Reconstruction from Uncalibrated CCTV Footage. In 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux. Enschede: Werkgemeenschap voor Informatie- en Communicatietheorie (WIC). 2012. p. 228-234