상세정보
학술대회
Bimanual Hand Tracking
- 발행일
- 200605
- 출처
- International Conference on Computational Science and Its Applications (ICCSA) 2006 (LNCS 3980), v.3980, pp.955-963
- 협약과제
- 06MI1200, URC를 위한 내장형 컴포넌트 기술개발 및 표준화, 조영조
- 초록
- This paper proposes a novel real-time hand tracking algorithm in the presence of occlusion. For this purpose, we construct a limb model and maintain the model obtained from ARKLT methods with respect to second-order auto-regression model and Kanade-LucasTomasi(KLT) features, respectively. Furthermore, this method do not require to categorize types of superimposed hand motion based on directivity obtained by the slope's direction of KLT regression. Thus, we can develop a method of hand tracking for gesture and activity recognition techniques frequently used in conjunction with Human-Robot Interaction (HRI) components. © Springer-Verlag Berlin Heidelberg 2006.
- KSP 제안 키워드
- Activity Recognition, Auto-regression model, Human-Robot Interaction(HRI), Real-time hand tracking, Tracking algorithm, hand motion, second-order