DocumentCode :
436397
Title :
Iterated model-based estimation of object pose using kalman filter with an active camera
Author :
Nakao, K. ; Kondo, K. ; Kobashi, S. ; Hata, Y. ; Yagi, T.
Author_Institution :
Graduate School of Engineering, Himeji Institute of Technology, Japan
Volume :
18
fYear :
2004
fDate :
June 28 2004-July 1 2004
Firstpage :
139
Lastpage :
144
Abstract :
In this paper, we propose the novel method for estimating the three dimensional position and pose of the object by using only one active camera. Our method estimates the depth length from the camera to the object by a Kalman filter. Kalman filter enables the depth distance estimation with high accuracy by using one camera and decreases the number of the iteration by estimating the accurate depth distance. Moreover, we iterate the estimation by updated input images. Although the distance from a camera to the object was about 600mm, the experimental results showed that the estimated error of the depth length was about 2.4mm.
Keywords :
Cameras; Production systems; Robot kinematics; Robot sensing systems; Robot vision systems; Robotics and automation; Sensor systems; Service robots; Servomechanisms; Target recognition; Kalman Filter; Model-Based Method; Visual Servo System; lterated Estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Automation Congress, 2004. Proceedings. World
Conference_Location :
Seville
Print_ISBN :
1-889335-21-5
Type :
conf
Filename :
1441032
Link To Document :
بازگشت