Using Richer Models for Articulated Pose Estimation of Footballers
2012 (English)In: Proceedings British Machine Vision Conference 2012., 2012, 6.1-6.10 p.Conference paper (Refereed)
We present a fully automatic procedure for reconstructing the pose of a person in 3Dfrom images taken from multiple views. We demonstrate a novel approach for learningmore complex models using SVM-Rank, to reorder a set of high scoring conﬁgurations.The new model in many cases can resolve the problem of double counting of limbswhich happens often in the pictorial structure based models. We address the problemof ﬂipping ambiguity to ﬁnd the correct correspondences of 2D predictions across allviews. We obtain improvements for 2D prediction over the state of art methods on ourdataset. We show that the results in many cases are good enough for a fully automatic3D reconstruction with uncalibrated cameras.
Place, publisher, year, edition, pages
2012. 6.1-6.10 p.
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-104558DOI: 10.5244/C.26.6ISI: 000346356200003ScopusID: 2-s2.0-84898491407ISBN: 1-901725-46-4OAI: oai:DiVA.org:kth-104558DiVA: diva2:565039
British Machine Vision Conference, Surrey,3-7 September 2012
QC 201211142012-11-142012-11-052015-10-06Bibliographically approved