English

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

Computer Vision and Pattern Recognition 2017-05-17 v2

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.

Keywords

Cite

@article{arxiv.1705.04608,
  title  = {Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters},
  author = {Lucas Beyer and Stefan Breuers and Vitaly Kurin and Bastian Leibe},
  journal= {arXiv preprint arXiv:1705.04608},
  year   = {2017}
}

Comments

First two authors have equal contribution. This is initial work into a new direction, not a benchmark-beating method. v2 only adds acknowledgements and fixes a typo in e-mail