This is a brief technical report of our proposed method for Multiple-Object Tracking (MOT) Challenge in Complex Environments. In this paper, we treat the MOT task as a two-stage task including human detection and trajectory matching. Specifically, we designed an improved human detector and associated most of detection to guarantee the integrity of the motion trajectory. We also propose a location-wise matching matrix to obtain more accurate trace matching. Without any model merging, our method achieves 66.672 HOTA and 93.971 MOTA on the DanceTrack challenge dataset.
@article{arxiv.2212.03586,
title = {Multiple Object Tracking Challenge Technical Report for Team MT_IoT},
author = {Feng Yan and Zhiheng Li and Weixin Luo and Zequn jie and Fan Liang and Xiaolin Wei and Lin Ma},
journal= {arXiv preprint arXiv:2212.03586},
year = {2022}
}
Comments
This is a brief technical report for Multiple Object Tracking Challenge of ECCV workshop 2022