Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Efficient articulated trajectory reconstruction using dynamic programming and filters|
|Citation:||Lecture Notes in Artificial Intelligence, 2012 / Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (ed./s), vol.7572 LNCS, iss.PART 1, pp.72-85|
|Series/Report no.:||Lecture Notes in Computer Science; 7572|
|Conference Name:||European Conference on Computer Vision (ECCV) (7 Oct 2012 - 13 Oct 2012 : Florence, Italy)|
|Jack Valmadre, Yingying Zhu, Sridha Sridharan and Simon Lucey|
|Abstract:||This paper considers the problem of reconstructing the motion of a 3D articulated tree from 2D point correspondences subject to some temporal prior. Hitherto, smooth motion has been encouraged using a trajectory basis, yielding a hard combinatorial problem with time complexity growing exponentially in the number of frames. Branch and bound strategies have previously attempted to curb this complexity whilst maintaining global optimality. However, they provide no guarantee of being more efficient than exhaustive search. Inspired by recent work which reconstructs general trajectories using compact high-pass filters, we develop a dynamic programming approach which scales linearly in the number of frames, leveraging the intrinsically local nature of filter interactions. Extension to affine projection enables reconstruction without estimating cameras.|
|Rights:||© Springer-Verlag Berlin Heidelberg 2012|
|Appears in Collections:||Aurora harvest 4|
Computer Science publications
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.