Compensation Tracker: Reprocessing Lost Object for Multi-Object Tracking

TL;DR

This paper introduces a simple, efficient compensation tracker that re-allocates lost objects in real-time multi-object tracking, significantly improving accuracy without additional training or network complexity.

Contribution

It proposes a novel, lightweight compensation tracker with motion and object selection modules that enhances existing real-time trackers by recovering lost objects.

Findings

Improves MOTA to 66% on MOT2020

Reduces identity switches significantly

Does not require re-training or extra networks

Abstract

Tracking by detection paradigm is one of the most popular object tracking methods. However, it is very dependent on the performance of the detector. When the detector has a behavior of missing detection, the tracking result will be directly affected. In this paper, we analyze the phenomenon of the lost tracking object in real-time tracking model on MOT2020 dataset. Based on simple and traditional methods, we propose a compensation tracker to further alleviate the lost tracking problem caused by missing detection. It consists of a motion compensation module and an object selection module. The proposed method not only can re-track missing tracking objects from lost objects, but also does not require additional networks so as to maintain speed-accuracy trade-off of the real-time model. Our method only needs to be embedded into the tracker to work without re-training the network. Experiments show that the compensation tracker can efficaciously improve the performance of the model and reduce identity switches. With limited costs, the compensation tracker successfully enhances the baseline tracking performance by a large margin and reaches 66% of MOTA and 67% of IDF1 on MOT2020 dataset.