Objective: The aim of this study is to investigate the way to distinguish and use gestures by the quantification through the handheld device included an acceleration sensor and gyro sensor in order to use the gesture with ease and common. Background: People use the hands and hand gestures to express one’s emotion or intend to not only other people but the machine and computer. To offer the affordance and comfortability through the gestures, there have been many researches on the development of gesture-based interfaces. Method: We quantified the gestures by the handheld device looks like TV remote controller included the acceleration sensor and gyro sensor on arduino platform. (1) collecting the values of acceleration sensor and gyro sensor occurred by the gesture, (2) searching the patterns of the sensor values and the approximate cycle of each gesture through the collected data, (3) setting the representative value of sensors which could be used as the index for chi square test. (4) We made the gesture set including the 10 gestures and distinguish user’s one gesture from the category of gestures using chi square test. Results: We did the pilot test with 10 participants and drew the result. It was found that accuracy of distinguishment of gestures is about 90%. Conclusion: It was suggested that gesture could be quantified to certain values not the array of values by the acceleration sensor and gyro sensor and used as representative values of gestures. And it was the chi square test that distinguishes the gesture user made from the gesture set. Application: The study is expected to provide the easy and economical way to distinguish the gestures without the large data set.
[1]
Sung-Bae Cho,et al.
Wrist Motion Recognition based on Nonlinear Analysis of 3D-Acceleration and Dynamic Bayesian Networks for Mobile User Interface
,
2011
.
[2]
David Zeltzer,et al.
A survey of glove-based input
,
1994,
IEEE Computer Graphics and Applications.
[3]
Kamiar Aminian,et al.
Arm position during daily activity.
,
2008,
Gait & posture.
[4]
Ling Bao,et al.
Activity Recognition from User-Annotated Acceleration Data
,
2004,
Pervasive.
[5]
Mario Jino,et al.
Experimental Results from Application of Fault-Sensitive Testing Strategies
,
2005,
RITA.
[6]
한성호,et al.
모바일 어플리케이션의 사용성 평가 방법 비교 분석
,
2012
.
[7]
Dan Saffer.
Designing gestural interfaces
,
2009
.