Extraction of hand and estimation of direction from multiple cameras for hand signed recognition

摘要

We have been researching human sensing technologies based on computer vision for the realization of the Percept-room as an intelligent environment. This room offers several services such as the control of electrical appliances by use of human's gestures. A more caring technology is strongly expected for providing more human-friendly interfaces. The control of electrical appliance by use of a gesture is one of the important contributions to the implementation of the Percept-room. The recognition of human motion in the Percept-room is important as a first priority. In this paper, we propose an estimation method of the human position in the Percept-room by integrating the silhouettes from multiple cameras. We then propose an extraction method of the hand by integrating the motions detected from subtractions during a gesture in the Percept-Room. We precisely describe the proposed methods and the experimental results obtained by use of a PC system implemented in the Percept-room.