Fusion of Head and Full-Body Detectors for Multi-Object Tracking
Abstract
In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach. Yet, relying solely on a single detector is also a major limitation, as useful image information might be ignored. Consequently, this work demonstrates how to fuse two detectors into a tracking system. To obtain the trajectories, we propose to formulate tracking as a weighted graph labeling problem, resulting in a binary quadratic program. As such problems are NP-hard, the solution can only be approximated. Based on the Frank-Wolfe algorithm, we present a new solver that is crucial to handle such difficult problems. Evaluation on pedestrian tracking is provided for multiple scenarios, showing superior results over single detector tracking and standard QP-solvers. Finally, our tracker ranks 2nd on the MOT16 benchmark and 1st on the new MOT17 benchmark, outperforming over 90 trackers.
Cite
Text
Henschel et al. "Fusion of Head and Full-Body Detectors for Multi-Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00192Markdown
[Henschel et al. "Fusion of Head and Full-Body Detectors for Multi-Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/henschel2018cvprw-fusion/) doi:10.1109/CVPRW.2018.00192BibTeX
@inproceedings{henschel2018cvprw-fusion,
title = {{Fusion of Head and Full-Body Detectors for Multi-Object Tracking}},
author = {Henschel, Roberto and Leal-Taixé, Laura and Cremers, Daniel and Rosenhahn, Bodo},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2018},
pages = {1428-1437},
doi = {10.1109/CVPRW.2018.00192},
url = {https://mlanthology.org/cvprw/2018/henschel2018cvprw-fusion/}
}