Estimating the Pose of a Medical Manikin for Haptic Augmentation of a Virtual Patient in Mixed Reality Training

Abstract

Virtual medical emergency training provides complex while safe interactions with virtual patients. Haptically integrating a medical manikin into virtual training has the potential to improve the interaction with a virtual patient and the training experience. We present a system that estimates the 3D pose of a medical manikin in order to haptically augment a human model in a virtual reality training environment, allowing users to physically touch a virtual patient. The system uses an existing convolutional neural network-based (CNN) body keypoint detector to locate relevant 2D keypoints of the manikin in the images of the stereo camera built into a head-mounted display. The manikin's position, orientation and joint angles are found by non-linear optimization. A preliminary analysis reports an error of 4.3 cm. The system is not yet capable of real-time processing.