On-line Evolutionary Head Pose Measurement by Feedforward Stereo Model Matching

Author

Song, Wei ; Minami, Mamoru ; Mae, Yasushi ; Aoyagi, Seiji

Author_Institution

Graduate Sch. of Eng., Fukui Univ.

fYear

2007

fDate

10-14 April 2007

Firstpage

4394

Lastpage

4400

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

Keywords

biomedical education; computer aided instruction; feedforward; genetic algorithms; image matching; image motion analysis; pose estimation; robot vision; stereo image processing; 3D pose estimation; evolutionary search; feedforward stereo model matching; fitness evaluation; genetic algorithm; hand-eye system; object motion; online evolutionary head pose measurement; stereo camera; Cameras; Convergence; Head; Image recognition; Medical robotics; Medical treatment; Robot sensing systems; Robot vision systems; Solid modeling; Target recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 2007 IEEE International Conference on

Conference_Location

Roma

ISSN

1050-4729

Print_ISBN

1-4244-0601-3

Electronic_ISBN

1050-4729

Type

conf

DOI

10.1109/ROBOT.2007.364156

Filename

4209774