Human Posture Recognition for Human-Robot Interaction

Human-Robot Interaction is an important topic in the field of artificial intelligence and robotics. In this study, we present a human body posture estimation method based on depth image analysis for human-robot interaction. The method uses a calibrated 3D camera to capture depth images of a human body, and recognize human body postures only by analyzing the depth images without 3D human model. Experiments show that, the proposed method can achieve continuous real-time posture recognition, and meets the requirements for making robot dance.(Abstract)