Runalyzer – Bewertung der Bewegungseffizient durch die Analyse von Microsoft Kinect

Auf einen Blick

Projektleiter/in: Dr. Evangelos Matsinos

Projektteam: Michal Jerzy Malinowski, Stephan Roth

Projektbeginn: 01.03.2014

Kurzdarstellung

The project investigated the use of the Microsoft Kinect ('Kinect', for short) sensors (original and upgraded) in the analysis of human motion. The scientific output of the project has been reported in three preprints which may be found on the Preprint Archive (http://arxiv.org/). The first preprint (1412.2032) provided the theoretical background. Our methodology has been developed in such a way that its application be easily adaptable to comparative studies of systems used in capturing human-motion data. We subsequently compared the performance of the two Kinect sensors (1504.00221) and demonstrated that the two outputs differ in regard to the variation of the physical quantities involved in the modelling of the human motion. As the original sensor has been found unsuitable for applications requiring high precision, the observed differences in the output of the two sensors call for the validation of the upgraded sensor on the basis of a marker-based system. The third preprint (1505.00371) examined the output obtained from the two versions of this sensor in relation to the variability of the estimates of the lengths of eight bones belonging to the subject’s extremities: of the humerus (upper arm), ulna (lower arm, forearm), femur (upper leg), and tibia (lower leg, shank). Large systematic effects in the output of the two sensors have been observed.