Research Article
A Multimodal Dataset for the Analysis of Movement Qualities in Karate Martial Art
@INPROCEEDINGS{10.4108/icst.intetain.2015.260039, author={Ksenia Kolykhalova and Antonio Camurri and Gualtiero Volpe and Marcello Sanguineti and Enrico Puppo and Radoslaw Niewiadomski}, title={A Multimodal Dataset for the Analysis of Movement Qualities in Karate Martial Art}, proceedings={7th International Conference on Intelligent Technologies for Interactive Entertainment}, publisher={EAI}, proceedings_a={INTETAIN}, year={2015}, month={8}, keywords={motion capture multimodal dataset karate movement features}, doi={10.4108/icst.intetain.2015.260039} }- Ksenia Kolykhalova
Antonio Camurri
Gualtiero Volpe
Marcello Sanguineti
Enrico Puppo
Radoslaw Niewiadomski
Year: 2015
A Multimodal Dataset for the Analysis of Movement Qualities in Karate Martial Art
INTETAIN
ICST
DOI: 10.4108/icst.intetain.2015.260039
Abstract
A multimodal dataset is presented, which has been collected for analyzing and measuring the quality of movement performed during sport activities. Martial arts (namely karate) are taken as test-beds for investigation. Karate encompasses predefined sequences of movements (“katas”) that can be carried out with different qualities, e.g., by performers at different skill levels (highly vs. poorly skilled).The experimental setup and method are described. The dataset is composed of motion capture (MoCap) data, synchronized with video and audio recordings, of several participants with different levels of experience. The raw MoCap data are independent of any particular post-processing algorithm and can be used for other research purposes. In the second part of the paper, a set of measures is proposed to evaluate a kata performance. They are based on the geometrical and kinematic features, such as posture correctness and synchronization between limbs. and were chosen according to karate experts’ opinion.
