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

Download the digital copy of the doc pdf document

Authors

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.