Mostra el registre d'ítem simple
Physical based skeleton tracking
dc.contributor | Susín Sánchez, Antonio |
dc.contributor.author | López Gandía, Axel Javier |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
dc.date.accessioned | 2017-06-29T09:36:20Z |
dc.date.available | 2017-06-29T09:36:20Z |
dc.date.issued | 2016-07-04 |
dc.identifier.uri | http://hdl.handle.net/2117/105975 |
dc.description.abstract | Skeleton tracking has multiple applications such as games, virtual reality, motion capture and more. One of the main challenges of pose detection is to be able to obtain the best possible quality with a cheap and easy-to-use device. In this work we propose a physically based method to detect errors and tracking issues which appear when we use low cost tracking devices such as Kinect. Therefore, we can correct the animation in order to obtain a smoother movement. We have implemented the Newton-Euler Algorithm, which allow us to compute the internal forces involved in a skeleton. In a common movement, forces are usually smooth without sudden variations. When the tracking yields poor results or invalid poses the internal forces become very large with a lot of variation. This allow us to detect when the tracking system fails and the animation needs to be inferred through di erent methods. Finally, once the detection algorithm is set up, we propose the Hermite interpolation to infer the positions of the joints that the tracking system is not capable of properly determine. This interpolation method allows to take into account both position and velocity, producing a smooth transition from valid portions of the animation to the inferred parts. |
dc.language.iso | eng |
dc.publisher | Universitat Politècnica de Catalunya |
dc.subject | Àrees temàtiques de la UPC::Informàtica |
dc.subject.lcsh | Biomechanics |
dc.subject.lcsh | Pattern recognition systems |
dc.subject.other | seguiment d'esquelets |
dc.subject.other | captura de moviment |
dc.subject.other | física |
dc.subject.other | interpolació d'Hermite |
dc.subject.other | skeleton tracking |
dc.subject.other | motion capture |
dc.subject.other | physics |
dc.subject.other | Hermite interpolation |
dc.title | Physical based skeleton tracking |
dc.type | Master thesis |
dc.subject.lemac | Biomecànica |
dc.subject.lemac | Reconeixement de formes (Informàtica) |
dc.identifier.slug | 118238 |
dc.rights.access | Open Access |
dc.date.updated | 2016-07-06T06:27:09Z |
dc.audience.educationlevel | Màster |
dc.audience.mediator | Facultat d'Informàtica de Barcelona |
dc.audience.degree | MÀSTER UNIVERSITARI EN INNOVACIÓ I RECERCA EN INFORMÀTICA (Pla 2012) |