物体移動操作の観察による物体の見えの逐次獲得と物体認識への応用

抄録

The paper describes a method for automatic acquisition of object appearances and grasping regions of everyday objects by observing human-object interaction from first person point of view. Human grasps and manipulates objects in everyday life. Home service robots and robotic environmental systems may extract and obtain object appearances by observing such human activity. However, the resolution of the acquired appearances may be low for object recognition. Our proposed method obtain object appearances and grasping regions by observing human-object interaction using first person point of view with head mount camera. The acquired appearances are integrated by matching feature points and used for object recognition.