Data association is a key step within the multi-object tracking pipeline that is notoriously challenging due to its combinatorial nature. A popular and general way to formulate data association is as the NP-hard multi-dimensional assignment problem. Over the past few years, data-driven approaches to assignment have become increasingly prevalent as these techniques have started to mature. We focus this survey solely on learning algorithms for the assignment step of multi-object tracking, and we attempt to unify various methods by highlighting their connections to linear assignment and to the multi-dimensional assignment problem. First, we review probabilistic and end-to-end optimization approaches to data association, followed by methods that learn association affinities from data. We then compare the performance of the methods presented in this survey and conclude by discussing future research directions.

中文翻译：

---

多目标跟踪中数据关联的机器学习方法

数据关联是多对象跟踪管道中的一个关键步骤，由于其组合性质，这是众所周知的具有挑战性的。制定数据关联的一种流行且通用的方法是 NP-hard 多维分配问题。在过去的几年里，随着这些技术开始成熟，数据驱动的分配方法变得越来越流行。我们只关注多目标跟踪分配步骤的学习算法，并试图通过突出它们与线性分配和多维分配问题的联系来统一各种方法。首先，我们回顾了数据关联的概率和端到端优化方法，然后是从数据中学习关联亲和力的方法。