A vision-based pet robot interaction

摘要

We developed a Vision-based Pet Robot Interaction System that reacts to human gestures interactively. This Pet Robot system has special features with its vision part. The features are followings: (1) "Motion Processor TM (MP)", (2) Detecting the "Region Of Interest (ROI)", (3) Gesture recognition with the ROI. The MP is a new image input device. It can exclude background part and capture only the object's shape, motion and depth information in real time. The ROI is a concept in order to distinguish objects in a captured image. The proposed method use depth information of he captured image and offered a fast and robust searching method. It enables the MP to sense a variety of object's shapes, motions, positions and so on. And to use our gesture recognition technology with ROI, it is easy to recognition object's motions as effective computer eyes.