A Robust Tracking of 3D Motion
Abstract
The tracking of moving objects in the 3D space for long-term image sequences must be very robust with respect to noise and computational errors. Thus, for example autoregressive, and Newtonian models have been adopted mainly with least-square, Kalman filter, and other techniques. The parameters measured are predicted/corrected on the basis of the model adopted; which can be adaptive or not. In this paper, a new method for tracking objects in the 3D space belonging to the class of matching-based algorithms with an adaptive prediction/correction mechanism is presented. The prediction/correction is based on 2D and 3D motion estimations, and both these corrections are used for measuring the displacements on the image plane. The mechanism proposed is very robust with respect to the accumulation error and, thus, it is suitable for very long-term object tracking.
Cite
Text
Borri et al. "A Robust Tracking of 3D Motion." European Conference on Computer Vision, 1994. doi:10.1007/3-540-57956-7_21Markdown
[Borri et al. "A Robust Tracking of 3D Motion." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/borri1994eccv-robust/) doi:10.1007/3-540-57956-7_21BibTeX
@inproceedings{borri1994eccv-robust,
title = {{A Robust Tracking of 3D Motion}},
author = {Borri, A. and Bucci, Giacomo and Nesi, Paolo},
booktitle = {European Conference on Computer Vision},
year = {1994},
pages = {181-188},
doi = {10.1007/3-540-57956-7_21},
url = {https://mlanthology.org/eccv/1994/borri1994eccv-robust/}
}