Motion Capture of Modern Greek Verbs: Measuring aspects and relations among actions

In the context of human motion analysis and human-centered computational sensing, this work presents a methodology for the investigation of the relations among actions of a set of (Modern Greek) motion verbs. The actions denoted by these verbs fall in the motion categories of pushing, pulling, hitting, and beating. Motion data were collected with motion capture technology, and measures of correlation and distance are used to identify existing relations among actions. Finally, hierarchical clustering analysis was applied to identify groups of actions. The results are in line with a semantic categorization of the corresponding verbs. The overall experimental procedure and data analysis indicate that the employed methodology could be useful in promising applications of motion recognition or motion clustering, aiming at the identification of related captured actions.