Cardiopulmonary resuscitation, commonly known as CPR, is an emergency procedure that normally combines chest compression with artificial ventilation in an effort to preserve intact brain function manually until further measures can be taken to restore spontaneous blood circulation and breathing in a person who is in cardiac arrest. In this study, we evaluated the skills of CPR practitioners on the basis of kinematic data obtained from their body movements while performing CPR. In particular, we used a Microsoft Kinect sensor to evaluate CPR performance by new and more experienced practitioners and to analyze CPR skill-building techniques. Such measurement using the Kinect sensor enabled detailed information about motion at body joints to be displayed quickly and objectively, thus facilitating identification of any problems. However, we could not confirm gesture recognition and detailed motion analysis based on using a high-speed camera to capture three-dimensional (3-D) motion of the entire body, we determined the Kinect sensor to be an easily applied evaluation tool that can provide body-motion information quickly and thus serve as an objective index for evaluating CPR performance.