Head attitude tracking based on EKF

Kai Ma; Quanxin Ding; Quizhi Zhang; Jinfeng Zhang

doi:10.1117/12.978695

15 October 2012 Head attitude tracking based on EKF

Kai Ma, Quanxin Ding, Quizhi Zhang, Jinfeng Zhang

Proceedings Volume 8417, 6th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment; 84171P (2012) https://doi.org/10.1117/12.978695
Event: 6th International Symposium on Advanced Optical Manufacturing and Testing Technologies (AOMATT 2012), 2012, Xiamen, China

Abstract

As there exists a high mean-square error for the monocular vision PNP algorithms in solving the problem of continuous head attitude tracking especially at certain relative orientations, this paper presented a new refinement method based on Extended Kalman Filter. Firstly, three Euler angles of head pose were computed by P4P algorithm, and then continuous movement parameters of the head were estimated in the EKF framework through introducing the nonlinear model of head movements. Simulation results indicated that the proposed approach can further improve the precision of the head attitude tracking.

Citation Download Citation

Kai Ma, Quanxin Ding, Quizhi Zhang, and Jinfeng Zhang "Head attitude tracking based on EKF", Proc. SPIE 8417, 6th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment, 84171P (15 October 2012); https://doi.org/10.1117/12.978695

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available