论文标题
Ensemlemot：迈向整体学习多个对象跟踪的一步
EnsembleMOT: A Step towards Ensemble Learning of Multiple Object Tracking
论文作者
论文摘要
近年来，多个对象跟踪（MOT）迅速发展。现有的作品倾向于设计单个跟踪算法以同时执行检测和关联。尽管在许多任务（即分类和对象检测）中利用了集合学习，但尚未在MOT任务中进行研究，这主要是由其复杂性和评估指标引起的。在本文中，我们为MOT提出了一种简单但有效的集合方法，称为Ensemlembot，该方法合并了具有时空约束的各种跟踪器的多个跟踪器。同时，应用了几种后处理程序来滤除异常结果。我们的方法是独立于模型的，不需要学习过程。更重要的是，它可以与其他算法（例如Tracklets插值）结合使用。 MOT17数据集的实验证明了该方法的有效性。代码可在https://github.com/dyhbupt/ensemblemot上找到。
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.
