A Gesture-Based Control for Handheld Devices Using Accelerometer

The current paper presents how the signals from an accelerometer can be processed to accurately recognize user gestures after applying a small accelerometer to a handheld device. For gesture-based control to be effective in handheld devices, the overheads involved in recognizing gestures should be minimal and the gestures accurately recognized in real operational environments. Therefore, the signals detected from accelerometers were classified into acceleration and dynamic acceleration, then the signal patterns of the accelerometers in relation to simple gestures were analyzed. A device control module was created and its operating process compared to that of a normal control device to evaluate the usability of gesture recognition. As a result, gesture-based control was found to be easy to use, reduced the preparation process, a produced a rapid system reaction. Accordingly, gesture-based control would seem to be an effective user interface for handheld devices primarily used in mobile environments.

[1]  Matthieu Bray,et al.  Recognition of gestures in the context of speech , 2002, Object recognition supported by user interaction for service robots.

[2]  Kristofer S. J. Pister,et al.  Acceleration sensing glove (ASG) , 1999, Digest of Papers. Third International Symposium on Wearable Computers.

[3]  Tapio Seppänen,et al.  Hand gesture recognition of a mobile device user , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[4]  Eric Horvitz,et al.  Sensing techniques for mobile interaction , 2000, UIST '00.

[5]  Rüdiger Dillmann,et al.  Dynamic gestures as an input device for directing a mobile platform , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[6]  B. Milner Handwriting recognition using acceleration-based motion detection , 1999 .

[7]  J. F. Bartlett,et al.  Rock 'n' Scroll Is Here to Stay , 2000 .

[8]  Seiji Hata,et al.  Gesture recognition for human-friendly interface in designer-consumer cooperate design system , 1999, 8th IEEE International Workshop on Robot and Human Interaction. RO-MAN '99 (Cat. No.99TH8483).

[9]  J. Bartlett WRL Research Report 2000 / 3 Rock ’ n ’ Scroll is Here to Stay , 2000 .

[10]  C. Randell,et al.  Context awareness by analysing accelerometer data , 2000, Digest of Papers. Fourth International Symposium on Wearable Computers.