Real-time stereo facial feature tracking: Mimicking human mouth movement on a humanoid robot head

Sabri Gurbuz; Toshihiro Shimizu; Gordon Cheng

doi:10.1109/ICHR.2005.1573594

Real-time stereo facial feature tracking: Mimicking human mouth movement on a humanoid robot head

Sabri Gurbuz, Toshihiro Shimizu, Gordon Cheng

ATR Computational Neuroscience Laboratory

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

4 Scopus citations

Abstract

In this paper, we describe a novel real-time stereo facial feature tracking algorithm in presence of geometry and illumination changes. The algorithm is applied to real-time humanhumanoid interactions. First, facial feature tracking algorithm locates the facial landmarks such as eyes with the left camera. Then, matching the between the eye pattern on stereo images, the horopter of the head location is estimated for fast stereo disparity processing. Thus, as a result, knowing the disparity and calibration parameters of stereo cameras, not only make it possible to track features in 3D, but also makes tracking more robust. We demonstrate the developed stereo tracking system through a human to humanoid robot mouth mimicking task.

Original language	English
Title of host publication	Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots
Pages	363-368
Number of pages	6
DOIs	https://doi.org/10.1109/ICHR.2005.1573594
State	Published - 2005
Externally published	Yes
Event	2005 5th IEEE-RAS International Conference on Humanoid Robots - Tsukuba, Japan Duration: 5 Dec 2005 → 7 Dec 2005

Publication series

Name	Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots
Volume	2005

Conference

Conference	2005 5th IEEE-RAS International Conference on Humanoid Robots
Country/Territory	Japan
City	Tsukuba
Period	5/12/05 → 7/12/05

Keywords

Mimicking human mouth movement on a humanoid robot
Stereo facial feature tracking

Access to Document

10.1109/ICHR.2005.1573594

Cite this

Gurbuz, S., Shimizu, T., & Cheng, G. (2005). Real-time stereo facial feature tracking: Mimicking human mouth movement on a humanoid robot head. In Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots (pp. 363-368). Article 1573594 (Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots; Vol. 2005). https://doi.org/10.1109/ICHR.2005.1573594

@inproceedings{92a992d9ef6a427a8befc94ccb7b04ae,

title = "Real-time stereo facial feature tracking: Mimicking human mouth movement on a humanoid robot head",

abstract = "In this paper, we describe a novel real-time stereo facial feature tracking algorithm in presence of geometry and illumination changes. The algorithm is applied to real-time humanhumanoid interactions. First, facial feature tracking algorithm locates the facial landmarks such as eyes with the left camera. Then, matching the between the eye pattern on stereo images, the horopter of the head location is estimated for fast stereo disparity processing. Thus, as a result, knowing the disparity and calibration parameters of stereo cameras, not only make it possible to track features in 3D, but also makes tracking more robust. We demonstrate the developed stereo tracking system through a human to humanoid robot mouth mimicking task.",

keywords = "Mimicking human mouth movement on a humanoid robot, Stereo facial feature tracking",

author = "Sabri Gurbuz and Toshihiro Shimizu and Gordon Cheng",

year = "2005",

doi = "10.1109/ICHR.2005.1573594",

language = "English",

isbn = "0780393201",

series = "Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots",

pages = "363--368",

booktitle = "Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots",

note = "2005 5th IEEE-RAS International Conference on Humanoid Robots ; Conference date: 05-12-2005 Through 07-12-2005",

}

Gurbuz, S, Shimizu, T & Cheng, G 2005, Real-time stereo facial feature tracking: Mimicking human mouth movement on a humanoid robot head. in Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots., 1573594, Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots, vol. 2005, pp. 363-368, 2005 5th IEEE-RAS International Conference on Humanoid Robots, Tsukuba, Japan, 5/12/05. https://doi.org/10.1109/ICHR.2005.1573594

Real-time stereo facial feature tracking: Mimicking human mouth movement on a humanoid robot head. / Gurbuz, Sabri; Shimizu, Toshihiro; Cheng, Gordon.
Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots. 2005. p. 363-368 1573594 (Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots; Vol. 2005).

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

TY - GEN

T1 - Real-time stereo facial feature tracking

T2 - 2005 5th IEEE-RAS International Conference on Humanoid Robots

AU - Gurbuz, Sabri

AU - Shimizu, Toshihiro

AU - Cheng, Gordon

PY - 2005

Y1 - 2005

N2 - In this paper, we describe a novel real-time stereo facial feature tracking algorithm in presence of geometry and illumination changes. The algorithm is applied to real-time humanhumanoid interactions. First, facial feature tracking algorithm locates the facial landmarks such as eyes with the left camera. Then, matching the between the eye pattern on stereo images, the horopter of the head location is estimated for fast stereo disparity processing. Thus, as a result, knowing the disparity and calibration parameters of stereo cameras, not only make it possible to track features in 3D, but also makes tracking more robust. We demonstrate the developed stereo tracking system through a human to humanoid robot mouth mimicking task.

AB - In this paper, we describe a novel real-time stereo facial feature tracking algorithm in presence of geometry and illumination changes. The algorithm is applied to real-time humanhumanoid interactions. First, facial feature tracking algorithm locates the facial landmarks such as eyes with the left camera. Then, matching the between the eye pattern on stereo images, the horopter of the head location is estimated for fast stereo disparity processing. Thus, as a result, knowing the disparity and calibration parameters of stereo cameras, not only make it possible to track features in 3D, but also makes tracking more robust. We demonstrate the developed stereo tracking system through a human to humanoid robot mouth mimicking task.

KW - Mimicking human mouth movement on a humanoid robot

KW - Stereo facial feature tracking

UR - http://www.scopus.com/inward/record.url?scp=33846584063&partnerID=8YFLogxK

U2 - 10.1109/ICHR.2005.1573594

DO - 10.1109/ICHR.2005.1573594

M3 - Conference contribution

AN - SCOPUS:33846584063

SN - 0780393201

SN - 9780780393202

T3 - Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots

SP - 363

EP - 368

BT - Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots

Y2 - 5 December 2005 through 7 December 2005

ER -

Real-time stereo facial feature tracking: Mimicking human mouth movement on a humanoid robot head

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this