Change search
ReferencesLink to record
Permanent link

Direct link
Modelling the body language of a musical conductor using Gaussian Process Latent Variable Models
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
2015 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Modellering av en dirigents kroppsspråk användandes Gaussian Process Latent Variable Models (Swedish)
Abstract [en]

Motion capture data of a musical conductor's movements when conducting a string quartet is analysed in this work using the Gaussian Process Latent Variable Model (GP-LVM) framework. A dimensionality reduction on the high dimensional motion capture data to a two dimensional representation using a GP-LVM is performed, followed by classification of conduction movements belonging to different interpretations of the same musical piece. A dynamical prior is used for the GP-LVM, resulting in a representative latent space for the sequential conduction motion data. Classification results with great performance for some of the interpretations are obtained. The GP-LVM with dynamical prior distribution is shown to be a reasonable choice when wanting to model conduction data, opening up the possibility for creating for example a "conduct-your-own-orchestra" system in a principled mathematical way, in the future.

Place, publisher, year, edition, pages
2015. , 54 p.
Keyword [en]
Machine Learning, Gaussian Processes, Statistical Modelling, Classification, Motion Capture
National Category
Computer Science
URN: urn:nbn:se:kth:diva-176101OAI: diva2:866153
Educational program
Master of Science in Engineering -Engineering Physics
Available from: 2015-11-04 Created: 2015-11-01 Last updated: 2015-11-04Bibliographically approved

Open Access in DiVA

fulltext(6975 kB)40 downloads
File information
File name FULLTEXT01.pdfFile size 6975 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
Computer Vision and Active Perception, CVAP
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 40 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 93 hits
ReferencesLink to record
Permanent link

Direct link