Human-Oriented Tracking for Human-Robot Interaction

摘要

In order for human-robot interaction to be effective in real-world environments, it needs to be natural and transparent. To achieve this, we need to facilitate direct, proximal communication between humans and robots. Our approach is to use computer vision to enable robots to observe and react to human activity. In this paper, we describe the development of real-time, computationally efficient vision modules for human tracking, human identification, and static gesture recognition.