Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections

TL;DR

This paper introduces LG-Track, a novel multi-object tracking framework that incorporates localization confidence into data association, improving tracking accuracy by considering appearance clarity and localization accuracy.

Contribution

It is the first to integrate localization confidence into MOT, designing a deep association mechanism that improves tracking performance over existing methods.

Findings

Outperforms state-of-the-art methods on MOT17 and MOT20 datasets.

Effectively combines classification and localization confidence for better data association.

Demonstrates significant improvements in tracking accuracy and robustness.

Abstract

In currently available literature, no tracking-by-detection (TBD) paradigm-based tracking method has considered the localization confidence of detection boxes. In most TBD-based methods, it is considered that objects of low detection confidence are highly occluded and thus it is a normal practice to directly disregard such objects or to reduce their priority in matching. In addition, appearance similarity is not a factor to consider for matching these objects. However, in terms of the detection confidence fusing classification and localization, objects of low detection confidence may have inaccurate localization but clear appearance; similarly, objects of high detection confidence may have inaccurate localization or unclear appearance; yet these objects are not further classified. In view of these issues, we propose Localization-Guided Track (LG-Track). Firstly, localization confidence is applied in MOT for the first time, with appearance clarity and localization accuracy of detection boxes taken into account, and an effective deep association mechanism is designed; secondly, based on the classification confidence and localization confidence, a more appropriate cost matrix can be selected and used; finally, extensive experiments have been conducted on MOT17 and MOT20 datasets. The results show that our proposed method outperforms the compared state-of-art tracking methods. For the benefit of the community, our code has been made publicly at https://github.com/mengting2023/LG-Track.