000147969 001__ 147969
000147969 005__ 20190509132323.0
000147969 0247_ $$2doi$$a10.5075/epfl-thesis-4699
000147969 02470 $$2urn$$aurn:nbn:ch:bel-epfl-thesis4699-3
000147969 02471 $$2nebis$$a6016687
000147969 037__ $$aTHESIS
000147969 041__ $$aeng
000147969 088__ $$a4699
000147969 245__ $$aBridging the Gap between Detection and Tracking for 3D Human Motion Recovery
000147969 269__ $$a2010
000147969 260__ $$bEPFL$$c2010$$aLausanne
000147969 300__ $$a146
000147969 336__ $$aTheses
000147969 520__ $$aThe aim of this thesis is to build a system able to automatically and robustly track human motion in 3–D starting from monocular input. To this end two approaches are introduced, which tackle two different types of motion: The first is useful to analyze activities for which a characteristic pose, or key-pose, can be detected, as for example in the walking case. On the other hand the second can be used for cases in which such pose is not defined but there is a clear relation between some easily measurable image quantities and the body configuration, as for example in the skating case where the trajectory followed by a subject is highly correlated to how the subject articulates. In the first proposed technique we combine detection and tracking techniques to achieve robust 3D motion recovery of people seen from arbitrary viewpoints by a single and potentially moving camera. We rely on detecting key postures, which can be done reliably, using a motion model to infer 3D poses between consecutive detections, and finally refining them over the whole sequence using a generative model. We demonstrate our approach in the cases of golf motions filmed using a static camera and walking motions acquired using a potentially moving one. We will show that this approach, although monocular, is both metrically accurate because it integrates information over many frames and robust because it can recover from a few misdetections. The second approach is based on the fact that the articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. The true range of motion can therefore be represented by latent variables that span a low-dimensional space. This has often been used to make motion tracking easier. However, learning the latent space in a problem independent way makes it non trivial to initialize the tracking process by picking appropriate initial values for the latent variables, and thus for the pose. In this thesis, it will be shown that by directly using observable quantities as latent variables, this issue can be eliminated.
000147969 6531_ $$aHuman Body Detection and Tracking
000147969 6531_ $$aMotion Models
000147969 6531_ $$aLow-Dimensional Embedding
000147969 700__ $$aFossati, Andrea
000147969 720_2 $$aFua, Pascal$$edir.$$g112366$$0240252
000147969 8564_ $$uhttps://infoscience.epfl.ch/record/147969/files/EPFL_TH4699.pdf$$zTexte intégral / Full text$$s41080806$$yTexte intégral / Full text
000147969 909C0 $$xU10659$$0252087$$pCVLAB
000147969 909CO $$pthesis-bn2018$$pDOI$$pIC$$ooai:infoscience.tind.io:147969$$qDOI2$$qGLOBAL_SET$$pthesis
000147969 918__ $$dEDIC2005-2015$$cISIM$$aIC
000147969 919__ $$aCVLAB
000147969 920__ $$b2010
000147969 970__ $$a4699/THESES
000147969 973__ $$sPUBLISHED$$aEPFL
000147969 980__ $$aTHESIS