Face models from noisy 3D cameras

Martin Breidt, Heinrich Bulthoff, Cristobal Curio

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Affordable 3D vision is just about to enter the mass market for consumer products such as video game consoles or TV sets. Having depth information in this context is beneficial for segmentation as well as gaining robustness against illumination effects, both of which are hard problems when dealing with color camera data in typical living room situations. Several techniques compute 3D (or rather 2.5D) depth information from camera data such as realtime stereo, time-of-flight (TOF), or real-time structured light, but all produce noisy depth data at fairly low resolutions. Not surprisingly, most applications are currently limited to basic gesture recognition using the full body. In particular, TOF cameras are a relatively new and promising technology for compact, simple and fast 2.5D depth measurements. Due to the measurement principle of measuring the flight time of infrared light as it bounces off the subject, these devices have comparatively low image resolution (176 × 144 ⋯ 320 × 240 pixels) with a high level of noise present in the raw data.

Original languageEnglish
Title of host publicationACM SIGGRAPH ASIA 2010 Sketches, SA'10
DOIs
Publication statusPublished - 2010 Dec 1
EventACM SIGGRAPH ASIA 2010 Sketches, SA'10 - Seoul, Korea, Republic of
Duration: 2010 Dec 152010 Dec 18

Other

OtherACM SIGGRAPH ASIA 2010 Sketches, SA'10
CountryKorea, Republic of
CitySeoul
Period10/12/1510/12/18

Fingerprint

Cameras
Gesture recognition
Consumer products
Image resolution
Lighting
Pixels
Color
Infrared radiation

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Breidt, M., Bulthoff, H., & Curio, C. (2010). Face models from noisy 3D cameras. In ACM SIGGRAPH ASIA 2010 Sketches, SA'10 [12] https://doi.org/10.1145/1899950.1899962

Face models from noisy 3D cameras. / Breidt, Martin; Bulthoff, Heinrich; Curio, Cristobal.

ACM SIGGRAPH ASIA 2010 Sketches, SA'10. 2010. 12.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Breidt, M, Bulthoff, H & Curio, C 2010, Face models from noisy 3D cameras. in ACM SIGGRAPH ASIA 2010 Sketches, SA'10., 12, ACM SIGGRAPH ASIA 2010 Sketches, SA'10, Seoul, Korea, Republic of, 10/12/15. https://doi.org/10.1145/1899950.1899962
Breidt M, Bulthoff H, Curio C. Face models from noisy 3D cameras. In ACM SIGGRAPH ASIA 2010 Sketches, SA'10. 2010. 12 https://doi.org/10.1145/1899950.1899962
Breidt, Martin ; Bulthoff, Heinrich ; Curio, Cristobal. / Face models from noisy 3D cameras. ACM SIGGRAPH ASIA 2010 Sketches, SA'10. 2010.
@inproceedings{79f6d1c7f5464ce6a704620f7a9052e7,
title = "Face models from noisy 3D cameras",
abstract = "Affordable 3D vision is just about to enter the mass market for consumer products such as video game consoles or TV sets. Having depth information in this context is beneficial for segmentation as well as gaining robustness against illumination effects, both of which are hard problems when dealing with color camera data in typical living room situations. Several techniques compute 3D (or rather 2.5D) depth information from camera data such as realtime stereo, time-of-flight (TOF), or real-time structured light, but all produce noisy depth data at fairly low resolutions. Not surprisingly, most applications are currently limited to basic gesture recognition using the full body. In particular, TOF cameras are a relatively new and promising technology for compact, simple and fast 2.5D depth measurements. Due to the measurement principle of measuring the flight time of infrared light as it bounces off the subject, these devices have comparatively low image resolution (176 × 144 ⋯ 320 × 240 pixels) with a high level of noise present in the raw data.",
author = "Martin Breidt and Heinrich Bulthoff and Cristobal Curio",
year = "2010",
month = "12",
day = "1",
doi = "10.1145/1899950.1899962",
language = "English",
isbn = "9781450305235",
booktitle = "ACM SIGGRAPH ASIA 2010 Sketches, SA'10",

}

TY - GEN

T1 - Face models from noisy 3D cameras

AU - Breidt, Martin

AU - Bulthoff, Heinrich

AU - Curio, Cristobal

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Affordable 3D vision is just about to enter the mass market for consumer products such as video game consoles or TV sets. Having depth information in this context is beneficial for segmentation as well as gaining robustness against illumination effects, both of which are hard problems when dealing with color camera data in typical living room situations. Several techniques compute 3D (or rather 2.5D) depth information from camera data such as realtime stereo, time-of-flight (TOF), or real-time structured light, but all produce noisy depth data at fairly low resolutions. Not surprisingly, most applications are currently limited to basic gesture recognition using the full body. In particular, TOF cameras are a relatively new and promising technology for compact, simple and fast 2.5D depth measurements. Due to the measurement principle of measuring the flight time of infrared light as it bounces off the subject, these devices have comparatively low image resolution (176 × 144 ⋯ 320 × 240 pixels) with a high level of noise present in the raw data.

AB - Affordable 3D vision is just about to enter the mass market for consumer products such as video game consoles or TV sets. Having depth information in this context is beneficial for segmentation as well as gaining robustness against illumination effects, both of which are hard problems when dealing with color camera data in typical living room situations. Several techniques compute 3D (or rather 2.5D) depth information from camera data such as realtime stereo, time-of-flight (TOF), or real-time structured light, but all produce noisy depth data at fairly low resolutions. Not surprisingly, most applications are currently limited to basic gesture recognition using the full body. In particular, TOF cameras are a relatively new and promising technology for compact, simple and fast 2.5D depth measurements. Due to the measurement principle of measuring the flight time of infrared light as it bounces off the subject, these devices have comparatively low image resolution (176 × 144 ⋯ 320 × 240 pixels) with a high level of noise present in the raw data.

UR - http://www.scopus.com/inward/record.url?scp=79951878891&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951878891&partnerID=8YFLogxK

U2 - 10.1145/1899950.1899962

DO - 10.1145/1899950.1899962

M3 - Conference contribution

AN - SCOPUS:79951878891

SN - 9781450305235

BT - ACM SIGGRAPH ASIA 2010 Sketches, SA'10

ER -