On-line evolutionary head pose measurement by feedforward stereo model matching

Wei Song; Mamoru Minami; Yasushi Mae; Seiji Aoyagi

doi:10.1109/ROBOT.2007.364156

On-line evolutionary head pose measurement by feedforward stereo model matching

Wei Song, Mamoru Minami, Yasushi Mae, Seiji Aoyagi

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

23 Citations (Scopus)

Abstract

This paper presents a method to estimate the 3D pose of a human's head using two images input from stereo cameras. The proposed method utilizes an evolutionary search technique of genetic algorithm (GA) and a fitness evaluation based on a stereo model matching. To improve the dynamics of recognition, a motion-feedforward method is proposed for the hand-eye system. The effectiveness of the method is confirmed by the experiments where the motion of the hand-eye camera compensated for the relative motion of the object in camera frame, resulting robust recognition against the hand-eye motion.

Original language	English
Title of host publication	2007 IEEE International Conference on Robotics and Automation, ICRA'07
Pages	4394-4400
Number of pages	7
DOIs	https://doi.org/10.1109/ROBOT.2007.364156
Publication status	Published - 2007
Externally published	Yes
Event	2007 IEEE International Conference on Robotics and Automation, ICRA'07 - Rome, Italy Duration: Apr 10 2007 → Apr 14 2007

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)	1050-4729

Other

Other	2007 IEEE International Conference on Robotics and Automation, ICRA'07
Country/Territory	Italy
City	Rome
Period	4/10/07 → 4/14/07

ASJC Scopus subject areas

Software
Control and Systems Engineering
Artificial Intelligence
Electrical and Electronic Engineering

Access to Document

10.1109/ROBOT.2007.364156

Cite this

On-line evolutionary head pose measurement by feedforward stereo model matching. / Song, Wei; Minami, Mamoru; Mae, Yasushi et al.

2007 IEEE International Conference on Robotics and Automation, ICRA'07. 2007. p. 4394-4400 4209774 (Proceedings - IEEE International Conference on Robotics and Automation).

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

Song, W, Minami, M, Mae, Y & Aoyagi, S 2007, On-line evolutionary head pose measurement by feedforward stereo model matching. in 2007 IEEE International Conference on Robotics and Automation, ICRA'07., 4209774, Proceedings - IEEE International Conference on Robotics and Automation, pp. 4394-4400, 2007 IEEE International Conference on Robotics and Automation, ICRA'07, Rome, Italy, 4/10/07. https://doi.org/10.1109/ROBOT.2007.364156

@inproceedings{0202052bee7c41c78dd0f2ec73d492d4,

title = "On-line evolutionary head pose measurement by feedforward stereo model matching",

abstract = "This paper presents a method to estimate the 3D pose of a human's head using two images input from stereo cameras. The proposed method utilizes an evolutionary search technique of genetic algorithm (GA) and a fitness evaluation based on a stereo model matching. To improve the dynamics of recognition, a motion-feedforward method is proposed for the hand-eye system. The effectiveness of the method is confirmed by the experiments where the motion of the hand-eye camera compensated for the relative motion of the object in camera frame, resulting robust recognition against the hand-eye motion.",

author = "Wei Song and Mamoru Minami and Yasushi Mae and Seiji Aoyagi",

year = "2007",

doi = "10.1109/ROBOT.2007.364156",

language = "English",

isbn = "1424406021",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

pages = "4394--4400",

booktitle = "2007 IEEE International Conference on Robotics and Automation, ICRA'07",

note = "2007 IEEE International Conference on Robotics and Automation, ICRA'07 ; Conference date: 10-04-2007 Through 14-04-2007",

}

TY - GEN

T1 - On-line evolutionary head pose measurement by feedforward stereo model matching

AU - Song, Wei

AU - Minami, Mamoru

AU - Mae, Yasushi

AU - Aoyagi, Seiji

PY - 2007

Y1 - 2007

N2 - This paper presents a method to estimate the 3D pose of a human's head using two images input from stereo cameras. The proposed method utilizes an evolutionary search technique of genetic algorithm (GA) and a fitness evaluation based on a stereo model matching. To improve the dynamics of recognition, a motion-feedforward method is proposed for the hand-eye system. The effectiveness of the method is confirmed by the experiments where the motion of the hand-eye camera compensated for the relative motion of the object in camera frame, resulting robust recognition against the hand-eye motion.

AB - This paper presents a method to estimate the 3D pose of a human's head using two images input from stereo cameras. The proposed method utilizes an evolutionary search technique of genetic algorithm (GA) and a fitness evaluation based on a stereo model matching. To improve the dynamics of recognition, a motion-feedforward method is proposed for the hand-eye system. The effectiveness of the method is confirmed by the experiments where the motion of the hand-eye camera compensated for the relative motion of the object in camera frame, resulting robust recognition against the hand-eye motion.

UR - http://www.scopus.com/inward/record.url?scp=36349029231&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36349029231&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.2007.364156

DO - 10.1109/ROBOT.2007.364156

M3 - Conference contribution

AN - SCOPUS:36349029231

SN - 1424406021

SN - 9781424406029

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 4394

EP - 4400

BT - 2007 IEEE International Conference on Robotics and Automation, ICRA'07

T2 - 2007 IEEE International Conference on Robotics and Automation, ICRA'07

Y2 - 10 April 2007 through 14 April 2007

ER -

On-line evolutionary head pose measurement by feedforward stereo model matching

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this