EnsembleMOT: A Step towards Ensemble Learning of Multiple Object Tracking

TL;DR

EnsembleMOT introduces a simple, model-independent ensemble approach for multiple object tracking that merges results from various trackers using spatio-temporal constraints, improving accuracy without additional learning.

Contribution

It is the first to apply ensemble learning to MOT, combining multiple trackers with post-processing for enhanced performance without requiring training.

Findings

Improves MOT accuracy on the MOT17 dataset

Compatible with existing tracking algorithms

Does not require additional training or learning procedures

Abstract

Multiple Object Tracking (MOT) has rapidly progressed in recent years. Existing works tend to design a single tracking algorithm to perform both detection and association. Though ensemble learning has been exploited in many tasks, i.e, classification and object detection, it hasn't been studied in the MOT task, which is mainly caused by its complexity and evaluation metrics. In this paper, we propose a simple but effective ensemble method for MOT, called EnsembleMOT, which merges multiple tracking results from various trackers with spatio-temporal constraints. Meanwhile, several post-processing procedures are applied to filter out abnormal results. Our method is model-independent and doesn't need the learning procedure. What's more, it can easily work in conjunction with other algorithms, e.g., tracklets interpolation. Experiments on the MOT17 dataset demonstrate the effectiveness of the proposed method. Codes are available at https://github.com/dyhBUPT/EnsembleMOT.