Towards a Principled Integration of Multi-Camera Re-Identification and Tracking Through Optimal Bayes Filters
Abstract
With the rise of end-to-end learning through deep learning, person detectors and re-identification (ReID) models have recently become very strong. Multi-target multicamera (MTMC) tracking has not fully gone through this transformation yet. We intend to take another step in this direction by presenting a theoretically principled way of integrating ReID with tracking formulated as an optimal Bayes filter. This conveniently side-steps the need for dataassociation and opens up a direct path from full images to the core of the tracker. While the results are still sub-par, we believe that this new, tight integration opens many interesting research opportunities and leads the way towards full end-to-end tracking from raw pixels. Code and models for all experiments are publicly available.
Cite
Text
Beyer et al. "Towards a Principled Integration of Multi-Camera Re-Identification and Tracking Through Optimal Bayes Filters." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.187Markdown
[Beyer et al. "Towards a Principled Integration of Multi-Camera Re-Identification and Tracking Through Optimal Bayes Filters." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/beyer2017cvprw-principled/) doi:10.1109/CVPRW.2017.187BibTeX
@inproceedings{beyer2017cvprw-principled,
title = {{Towards a Principled Integration of Multi-Camera Re-Identification and Tracking Through Optimal Bayes Filters}},
author = {Beyer, Lucas and Breuers, Stefan and Kurin, Vitaly and Leibe, Bastian},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2017},
pages = {1444-1453},
doi = {10.1109/CVPRW.2017.187},
url = {https://mlanthology.org/cvprw/2017/beyer2017cvprw-principled/}
}