Comparative study of multi-person tracking methods

TL;DR

This study compares two top-ranked multi-person tracking algorithms, SORT and Tracktor++, analyzing their techniques and contributions to improve MOT tracking performance, with experimental results favoring Tracktor++ and insights for future research.

Contribution

It provides a detailed comparison of SORT and Tracktor++, including ablation studies on re-identification and motion, offering insights to enhance multi-person tracking methods.

Findings

Tracktor++ outperforms SORT in accuracy.

Re-identification network significantly improves tracking.

Ablation studies highlight the importance of motion and RE-ID.

Abstract

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: https://motchallenge.net ). 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 : https://motchallenge.net/data/MOT17Det/ ). We also used a re-identification model trained on MOT17 dataset (MOT17 : https://motchallenge.net/data/MOT17/ ) 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.