This paper presents a study of two tracking algorithms (SORT~\cite{7533003}
and Tracktor++~\cite{2019}) that were ranked first positions on the MOT
Challenge leaderboard (The MOTChallenge web page: this https URL ).
The purpose of this study is to discover the techniques used and to provide
useful insights about these algorithms in the tracking pipeline that could
improve the performance of MOT tracking algorithms. To this end, we adopted the
popular tracking-by-detection approach. We trained our own Pedestrian Detection
model using the MOT17Det dataset (MOT17Det :
this https URL ). We also used a re-identification
model trained on MOT17 dataset (MOT17 : this https URL )
for Tracktor++ to reduce the false re-identification alarms. We then present
experimental results which shows that Tracktor++ is a better multi-person
tracking algorithm than SORT. We also performed ablation studies to discover
the contribution of re-identification(RE-ID) network and motion to the results
of Tracktor++. We finally conclude by providing some recommendations for future
research.

这篇论文研究了两种在 MOT 挑战排行榜上名列前茅的追踪算法（SORT 和 Tracktor++），目的在于发现这些算法在追踪流程中采用的技术，并提供有价值的见解以改进 MOT 追踪算法的性能。研究采用了常用的检测跟踪方法，并使用自己训练的行人检测模型和跟踪模型，经实验结果表明 Tracktor++ 是比 SORT 更好的多人追踪算法。此外，进行了消融研究以发现 Tracktor++ 结果中重识别网络和运动的贡献，并提供了一些建议供未来研究参考。

多人跟踪方法的比较研究

Comparative study of multi-person tracking methods

Simple Online and Realtime Tracking (SORT) is a pragmatic approach to
multiple object tracking with a focus on simple, effective algorithms. In this
paper, we integrate appearance information to improve the performance of SORT.
Due to this extension we are able to track objects through longer periods of
occlusions, effectively reducing the number of identity switches. In spirit of
the original framework we place much of the computational complexity into an
offline pre-training stage where we learn a deep association metric on a
large-scale person re-identification dataset. During online application, we
establish measurement-to-track associations using nearest neighbor queries in
visual appearance space. Experimental evaluation shows that our extensions
reduce the number of identity switches by 45%, achieving overall competitive
performance at high frame rates.

文中介绍了一个基于 SORT 方法的多目标跟踪算法，通过整合外观信息能有效地降低物体遮挡时的身份切换次数，并在利用最近邻查询视觉外观空间建立测量轨迹关联时表现出竞争性的性能。