Remarks on human body posture estimation from silhouette image based on heuristic rules and Kalman filter

Kazuhiko Takahashi; Masahide Naemura

doi:10.1117/12.664696

2 May 2006 Remarks on human body posture estimation from silhouette image based on heuristic rules and Kalman filter

Kazuhiko Takahashi, Masahide Naemura

Proceedings Volume 6042, ICMIT 2005: Control Systems and Robotics; 604238 (2006) https://doi.org/10.1117/12.664696
Event: ICMIT 2005: Merchatronics, MEMS, and Smart Materials, 2005, Chongqing, China

Abstract

This paper proposes a human body posture estimation method based on analysis of human silhouette and Kalman filter. The proposed method is based on both the heuristically extraction method of estimating the significant points of human body and the contour analysis of the human silhouette. The 2D coordinates of the human body's significant points, such as top of the head, and tips of feet, are located by applying the heuristically extraction method to the human silhouette, those of tips of hands are obtained by using the result of the contour analysis, and the joints of elbows and knees are estimated by introducing some heuristic rules to the contour image of the human silhouette. The estimated results are optimized and tracked by using Kalman filter. The proposed estimation method is implemented on a personal computer and runs in real-time. Experimental results show both the feasibility and the effectiveness of the proposed method for estimating human body postures.

Citation Download Citation

Kazuhiko Takahashi and Masahide Naemura "Remarks on human body posture estimation from silhouette image based on heuristic rules and Kalman filter", Proc. SPIE 6042, ICMIT 2005: Control Systems and Robotics, 604238 (2 May 2006); https://doi.org/10.1117/12.664696

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