Multi kinect people detection for intuitive and safe human robot cooperation in the operating room

Microsoft Kinect cameras are widely used in robotics. The cameras can be mounted either to the robot itself (in case of mobile robotics) or can be placed where they have a good view on robots and/or humans. The use of cameras in the surgical operating room adds additional complexity in placing the cameras and adds the necessity of coping with a highly uncontrolled environment with occlusions and unknown objects. In this paper we present an approach that accurately detects humans using multiple Kinect cameras. Experiments were performed to show that our approach is robust to interference, noise and occlusions. It provides a good detection and identification rate of the user which is crucial for safe human robot cooperation.