Detecting start and end times of object-handlings on a table by fusion of camera and load sensors
Ryuta Yasuoka, Atsushi Hashimoto, Takuya Funatomi, Michihiko Minoh · 2013
We aim to extract object-handlings in real time for realizing a system supporting cooking activities. Traditional methods based solely on camera is principally poor at judging whether touched or just closed near objects, and those based on load sensing table cannot extract concurrent object-handlings separately. To extract object-handlings separately, we propose a sensor fusion framework of a camera and load sensor information. We applied our method to a simple cooking activity and confirmed that our method principally worked as expected.