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

Abstract

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

Time-of-flight-assisted Kinect camera-based people detection for intuitive human robot cooperation in the surgical operating room

“…As described in [2] and [27], which are expanded through this work, a Kinect camera acquires 3-channel RGB images with a resolution of 8 bit per channel (dimensions: 640 × 480) as well as a 11 Bit depth map (dimensions: 640 × 480). The capturing frequency is 30 Hz, which results in a data rate of around 40 MB/s to be transferred between the Kinect and its host computer via USB.…”

“…A kernel on the NVIDIA Geforce GTX Titan computes Eq. (2) d( p, q) 2 = ||q − p|| 2 (2) which is the squared distance between points p and q. Using a brute force approach, which was fast enough for the point cloud sizes used in the experiments, we employ this kernel to compute all squared distances between the source (user) and target cloud (robot).…”

“…The marker-based tracking system ARTtrack2 (ART, Germany) is used for calibration purposes and accurate tracking of marker equipped objects. Our supervision system is developed in the context of OP:Sense [18,21], which is mainly dedicated to safe and intuitive workflow controlled human robot interaction in the operating room [2] as well as exploring new applications for the operation. OP:Sense is based on ROS [24].…”

Utilisation of Kinect Sensors for the Design of a Human-Robot Collaborative Workcell

“…Extrinsic parameters represent the location of a camera in the real scene. Matrix of extrinsic parameters consists of rotation matrix R and translation vector t. They are expressed by relation (2). Interdependence between intrinsic and extrinsic parameters is expressed by relation (3).…”

“…Kinect devices for its low start-up costs are often used in numerous research projects [7,13,16,20]. Their utilisation for solving the problem of a human-worker capturing within the monitored space of the collaborative workcell are described in [2,29].…”