The Community for Technology Leaders
Green Image
Issue No. 07 - July (2010 vol. 32)
ISSN: 0162-8828
pp: 1165-1181
Andrea Fossati , Ecole Polytechnique Fédérale de Lausanne (EPLFL/IC/ISIM/CVLab), Lausanne
Miodrag Dimitrijevic , Ecole Polytechnique Fédérale de Lausanne (EPLFL/IC/ISIM/CVLab), Lausanne
Vincent Lepetit , Ecole Polytechnique Fédérale de Lausanne (EPLFL/IC/ISIM/CVLab), Lausanne
Pascal Fua , Ecole Polytechnique Fédérale de Lausanne (EPLFL/IC/ISIM/CVLab), Lausanne
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 our approach, although monocular, is both metrically accurate because it integrates information over many frames and robust because it can recover from a few misdetections.
Computer vision, motion, video analysis, 3D scene analysis, modeling and recovery of physical attributes, tracking.

A. Fossati, M. Dimitrijevic, V. Lepetit and P. Fua, "From Canonical Poses to 3D Motion Capture Using a Single Camera," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 32, no. , pp. 1165-1181, 2009.
92 ms
(Ver 3.3 (11022016))