000187555 001__ 187555
000187555 005__ 20190416220718.0
000187555 022__ $$a1077-3142
000187555 037__ $$aARTICLE
000187555 245__ $$aTemporal Motion Models for Monocular and Multiview 3–D Human Body Tracking
000187555 269__ $$a2006
000187555 260__ $$bElsevier$$c2006
000187555 336__ $$aJournal Articles
000187555 520__ $$aWe explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differ- entiable criterion whose differential structure is rich enough for optimization to be accom- plished via hill-climbing. This avoids the computational expense of Monte Carlo methods, while yielding good results under challenging conditions. To demonstrate the generality of the approach we show that we can learn and track cyclic motions such as walking and running, as well as acyclic motions such as a golf swing. We also show results from both monocular and multi-camera tracking. Finally, we provide results with a motion model learned from multiple activities, and show how this models might be used for recognition.
000187555 6531_ $$aTracking
000187555 6531_ $$aMotion Models
000187555 6531_ $$aOptimization
000187555 700__ $$0241534$$g137775$$aUrtasun, Raquel
000187555 700__ $$aFleet, David
000187555 700__ $$aFua, Pascal$$g112366$$0240252
000187555 773__ $$j104$$tComputer Vision and Image Understanding$$k2-3
000187555 8564_ $$uhttps://infoscience.epfl.ch/record/187555/files/top.pdf$$zn/a$$s1711240$$yn/a
000187555 909C0 $$xU10659$$0252087$$pCVLAB
000187555 909CO $$ooai:infoscience.tind.io:187555$$qGLOBAL_SET$$pIC$$particle
000187555 917Z8 $$x112366
000187555 937__ $$aEPFL-ARTICLE-187555
000187555 973__ $$rNON-REVIEWED$$sPUBLISHED$$aEPFL
000187555 980__ $$aARTICLE