| Summary: | How much information with regard to identity and further individual participant<br />characteristics are revealed by relatively short spatio-temporal motion trajectories of a person?<br />We study this question by selecting a set of individual participant characteristics and analysing<br />motion captured trajectories of an exemplary class of familiar movements, namely handover of an<br />object to another person. The experiment is performed with different participants under different,<br />predefined conditions. A selection of participant characteristics, such as the Big Five personality<br />traits, gender, weight, or sportiness, are assessed and we analyse the impact of the three factor groups<br />“participant identity”, “participant characteristics”, and “experimental conditions” on the observed<br />hand trajectories. The participants’ movements are recorded via optical marker-based hand motion<br />capture. One participant, the giver, hands over an object to the receiver. The resulting time courses of<br />three-dimensional positions of markers are analysed. Multidimensional scaling is used to project<br />trajectories to points in a dimension-reduced feature space. Supervised learning is also applied.<br />We find that “participant identity” seems to have the highest correlation with the trajectories, with<br />factor group “experimental conditions” ranking second. On the other hand, it is not possible to find a<br />correlation between the “participant characteristics” and the hand trajectory features.
|
|---|
