Branch-and-Price Global Optimization for Multi-View Multi-Target Tracking
Abstract
We present a new algorithm to jointly track multiple objects in multi-view images. While this has been typically addressed separately in the past, we tackle the problem as a single global optimization. We formulate this assignment problem as a min-cost problem by defining a graph structure that captures both temporal correlations between objects as well as spatial correlations enforced by the configuration of the cameras. This leads to a complex combinatorial optimization problem that we solve using Dantzig-Wolfe decomposition and branching. Our formulation allows us to solve the problem of reconstruction and tracking in a single step by taking all available evidence into account. In several experiments on multiple people tracking and 3D human pose tracking, we show our method outperforms state-of-the-art approaches.
Cite
Text
Leal-Taixé et al. "Branch-and-Price Global Optimization for Multi-View Multi-Target Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247901Markdown
[Leal-Taixé et al. "Branch-and-Price Global Optimization for Multi-View Multi-Target Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/lealtaixe2012cvpr-branch/) doi:10.1109/CVPR.2012.6247901BibTeX
@inproceedings{lealtaixe2012cvpr-branch,
title = {{Branch-and-Price Global Optimization for Multi-View Multi-Target Tracking}},
author = {Leal-Taixé, Laura and Pons-Moll, Gerard and Rosenhahn, Bodo},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2012},
pages = {1987-1994},
doi = {10.1109/CVPR.2012.6247901},
url = {https://mlanthology.org/cvpr/2012/lealtaixe2012cvpr-branch/}
}