MOTCOM: The Multi-Object Tracking Dataset Complexity Metric
Abstract
There exists no comprehensive metric for describing the complexity of Multi-Object Tracking (MOT) sequences. This lack of metrics decreases explainability, complicates comparison of datasets, and reduces the conversation on tracker performance to a matter of leader board position. As a remedy, we present the novel MOT dataset complexity metric (MOTCOM), which is a combination of three sub-metrics inspired by key problems in MOT: occlusion, erratic motion, and visual similarity. The insights of MOTCOM can open nuanced discussions on tracker performance and may lead to a wider acknowledgement of novel contributions developed for either less known datasets or those aimed at solving sub-problems. We evaluate MOTCOM on the comprehensive MOT17, MOT20, and MOTSynth datasets and show that MOTCOM is far better at describing the complexity of MOT sequences compared to the conventional density and number of tracks. Project page at https://vap.aau.dk/motcom.
Cite
Text
Pedersen et al. "MOTCOM: The Multi-Object Tracking Dataset Complexity Metric." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-20074-8_2Markdown
[Pedersen et al. "MOTCOM: The Multi-Object Tracking Dataset Complexity Metric." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/pedersen2022eccv-motcom/) doi:10.1007/978-3-031-20074-8_2BibTeX
@inproceedings{pedersen2022eccv-motcom,
title = {{MOTCOM: The Multi-Object Tracking Dataset Complexity Metric}},
author = {Pedersen, Malte and Haurum, Joakim Bruslund and Dendorfer, Patrick and Moeslund, Thomas B.},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2022},
doi = {10.1007/978-3-031-20074-8_2},
url = {https://mlanthology.org/eccv/2022/pedersen2022eccv-motcom/}
}