| Popis: |
In this paper, we propose a human-tracking robot that can be used in commercial establishments such as airports and factories. The human-tracking process involves three main steps. The first is robust person identification using QR code recognition, and is the most important step in human tracking. The second is location detection using shape-based pattern matching in order to determine the position of the QR code when the person being tracked moves far from the robot. Finally, the third step is robot control to maintain an appropriate distance for human tracking. In experiments measuring QR code recognition rates, it was shown that QR code recognition was 99.9% and that location detection is robust. In a robot-control experiment, tracking was shown to be accurate, and during tracking, the robot maintained an appropriate distance from the human |
