Stabilizing Motion Tracking Using Retrieved Motion Priors
Abstract
In this paper, we introduce a novel iterative motion tracking framework that combines 3D tracking techniques with motion retrieval for stabilizing markerless human motion capturing. The basic idea is to start human tracking without prior knowledge about the performed actions. The resulting 3D motion sequences, which may be corrupted due to tracking errors, are locally classified according to available motion categories. Depending on the classification result, a retrieval system supplies suitable motion priors, which are then used to regularize and stabilize the tracking in the next iteration step. Experiments with the HumanEVA-II benchmark show that tracking and classification are remarkably improved after few iterations. 1.
Cite
Text
Baak et al. "Stabilizing Motion Tracking Using Retrieved Motion Priors." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459291Markdown
[Baak et al. "Stabilizing Motion Tracking Using Retrieved Motion Priors." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/baak2009iccv-stabilizing/) doi:10.1109/ICCV.2009.5459291BibTeX
@inproceedings{baak2009iccv-stabilizing,
title = {{Stabilizing Motion Tracking Using Retrieved Motion Priors}},
author = {Baak, Andreas and Rosenhahn, Bodo and Müller, Meinard and Seidel, Hans-Peter},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2009},
pages = {1428-1435},
doi = {10.1109/ICCV.2009.5459291},
url = {https://mlanthology.org/iccv/2009/baak2009iccv-stabilizing/}
}