Audio-Visual Feedback for Self-monitoring Posture in Ballet Training

Esben Winther Knudsen, Malte Lindholm Hølledig, Sebastian Siem Bach-Nielsen, Rikke Katrine Petersen, Bogdan-Constantin Zanescu, Mads Juel Nielsen, Kim Helweg, Daniel Overholt, Hendrik Purwins

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

252 Downloads (Pure)


An application for ballet training is presented that monitors the posture position (straightness of the spine and rotation of the pelvis) deviation from the ideal position in real-time. The human skeletal data is acquired through a Microsoft Kinect v2. The movement of the student is mirrored through an abstract skeletal figure and instructions are provided through a virtual teacher. Posture deviation is measured as torso misalignment, via comparing hip center joint, shoulder center joint and neck joint position with an ideal posture position retrieved through initial calibration, and pelvis deviation, expressed as the xz-rotation of the hipcenter joint. The posture deviation is sonified via a varying cut-off frequency of a high-pass filter applied to floating water sound. The posture deviation is visualized via a curve and a rigged skeleton in which the misaligned torso parts are color-coded. In an experiment with 9-12 year-old dance students from a ballet school, comparing the audio-visual feedback modality with no feedback leads to an increase in posture accuracy (p < 0.001, Cohen’s d = 1.047). Reaction card feedback and expert interviews indicate that the feedback is considered fun and useful for training independently from the teacher.
TitelNIME 2017 Papers and Posters Proceedings
ForlagNew Interfaces for Musical Expression
Publikationsdato15 maj 2017
StatusUdgivet - 15 maj 2017
BegivenhedNew Interfaces for Musical Expression 2017 - AAU Sydhavn, Copenhagen, Danmark
Varighed: 14 maj 201718 maj 2017


KonferenceNew Interfaces for Musical Expression 2017
LokationAAU Sydhavn
NavnNIME Proceedings


Dyk ned i forskningsemnerne om 'Audio-Visual Feedback for Self-monitoring Posture in Ballet Training'. Sammen danner de et unikt fingeraftryk.