Information Processing and Signal Analysis, Image Processing, Human Interface, Measurement, Physically Handicapped People, Matching Pursuit, Line-of-Sight
その他のタイトル
Non-Contact Eye-Gazing Point Detection during Driving a Wheelchair Simulator
The purpose of this study is to detect the eye-gazing points during driving a wheelchair simulator through the image sequence analysis of video frames. The performances can be measured without restrictions of specific devices such as any accessories and sensors, which were put on a body. Images obtained with two video cameras allow the algorithm with two-dimensional matching pursuit through wavelet analysis to extract boundaries of right and left irises. Their three-dimensional positions and directions were estimated through the Direct Linear Transformation technique. The eye-gazing point was evaluated through the relationship between the vertical vectors of iris and line-of-sight. Consequently, some preliminary results were presented to illustrate the difference in variations with the eye-gazing point, which have relationship to the experience of wheelchair.