Publication
3D human motion sequences synchronization using dense matching algorithm
Conference Article
Conference
Annual Symposium of the German Association for Pattern Recognition (DAGM)
Edition
28th
Pages
485-494
Doc link
http://dx.doi.org/10.1007/11861898_49
File
Authors
-
Mozerov, Mikhail
-
Rius, Ignasi
-
Roca i Marva, Francesc Xavier
-
Gonzàlez Sabaté, Jordi
Projects associated
Abstract
This work solves the problem of synchronizing pre-recorded human motion sequences, which show different speeds and accelerations, by using a novel dense matching algorithm. The approach is based on the dynamic programming principle that allows finding an optimal solution very fast. Additionally, an optimal sequence is automatically selected from the input data set to be a time scale pattern for all other sequences. The synchronized motion sequences are used to learn a model of human motion for action recognition and full-body tracking purposes.
Categories
computer vision.
Scientific reference
M. Mozerov, I. Rius, F. Xavier Roca and J. Gonzàlez. 3D human motion sequences synchronization using dense matching algorithm, 28th Annual Symposium of the German Association for Pattern Recognition, 2006, Berlin, Germany, in Pattern Recognition, Vol 4174 of Lecture Notes in Computer Science, pp. 485-494, 2006, Springer, Berlin, Alemanya.
Follow us!