Real-time input of 3D pose and gestures of a user´s hand and its applications for HCI

Author

Sato, Yoichi ; Saito, Makiko ; Koike, Hideki

Author_Institution

Inst. of Ind. Sci., Tokyo Univ., Japan

fYear

2001

fDate

17-17 March 2001

Firstpage

79

Lastpage

86

Abstract

Introduces a method for tracking a user´s hand in 3D and recognizing the hand´s gesture in real time without the use of any invasive devices attached to the hand. Our method uses multiple cameras for determining the position and orientation of a user´s hand moving freely in a 3D space. In addition, the method identifies pre-determined gestures in a fast and robust manner by using a neural network which has been properly trained beforehand. This paper also describes results of user study of our proposed method and several types of applications, including 3D object handling for a desktop system and a 3D walkthrough for a large immersive display system.

Keywords

cameras; gesture recognition; interactive systems; neural nets; real-time systems; tracking; 3D object handling; 3D pose; 3D walkthrough; cameras; desktop system; human-computer interaction; immersive display system; orientation determination; position determination; pre-determined gesture identification; real-time input; trained neural network; user hand gestures; user hand tracking; user study; Application software; Cameras; Computer displays; Graphical user interfaces; Human computer interaction; Mice; Neural networks; Real time systems; Robustness; Three dimensional displays;

fLanguage

English

Publisher

ieee

Conference_Titel

Virtual Reality, 2001. Proceedings. IEEE

Conference_Location

Yokohama, Japan

Print_ISBN

0-7695-0948-7

Type

conf

DOI

10.1109/VR.2001.913773

Filename

913773