Tracking of dynamic arm motion estimation and interaction with fuzzy control

• Main Authors: Badi, Haitham, Hamza, Alaa, Mohd Yunus, Mohd Amin
• Format: Article
• Language: English
• Published: IEEE 2016
• Subjects: QA76 Computer software; TK7885-7895 Computer engineering. Computer hardware
• Online Access: http://eprints.uthm.edu.my/5715/1/AJ%202017%20%28889%29.pdf; http://eprints.uthm.edu.my/5715/

Considerable effort has been put toward the development of intelligent and natural interfaces be- tween users and computer systems. In line with this endeavor, several modes of information (e.g., visual, au- dio, and pen) that are used either individually or in combination have been proposed. Multi-projector dis- play systems are gaining popularity for use in immersive virtual reality applications and scientific visualization. While recent work has addressed the issues of human interfaces to hide the distributed nature of those sys- tems, there has been relatively little work on natural interactive modalities. In this paper, based on the dis- crete characteristics of node distribution and the spatio- temporal coherence of the users movement, we propose a non-contact interactive solution for multi-projector display system. Utilizing a virtual three-dimensional interactive rectan- gular parallelepiped, we establish correspondence be- tween the virtual scene and the users arm position in- formation. For robustly tracking the users arm position, an arm motion estimation method is designed based on the fuzzy predictive control fuzzy Mamdani algorithm theory. To verify the efficiency and accuracy of the pro- posed method, we use a Kalman filter algorithm to test stabilize the output.