Towards a Principled Integration of Multi-Camera Re-Identification and Tracking Through Optimal Bayes Filters

Lucas Beyer, Stefan Breuers, Vitaly Kurin, Bastian Leibe; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 29-38

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-camera multi-target (MCMT) 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 data-association 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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Beyer_2017_CVPR_Workshops,
author = {Beyer, Lucas and Breuers, Stefan and Kurin, Vitaly and Leibe, Bastian},
title = {Towards a Principled Integration of Multi-Camera Re-Identification and Tracking Through Optimal Bayes Filters},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}