作者：Wenhan Luo，Junliang Xing，Anton Milan，Xiaoqin Zhang，Wei Liu，Tae-Kyun Kim

**作者单位：**Tencent AI Lab，Imperial College London，Institute of Automation, Chinese Academy of Sciences，Amazon Research and Development Center，Wenzhou University

发布时间：2022

发布期刊/会议：Arxiv

论文全称：Multiple Object Tracking: A Literature Review

论文地址：https://arxiv.org/abs/1409.7618

论文代码：

地位：多目标跟踪综述，每年都会更新，这是2022年的

个人理解

• **创新点：**目前最全面、最新的多目标跟踪论文综述。即向计算机视觉界提供关于MOT问题的第一个全面综述。
• **为什么：**为了处理所有这些问题（MOT的挑战，如跟踪对象尺寸的变化（scale changes）、平面外旋转（out-of-plane rotations）、光照变化（illumination variations），频繁的遮挡、轨迹的初始化和终止、相似的外观、多个物体之间的相互作用等），在过去几十年里提出了各种广泛的解决方案。这些解决方案集中于MOT系统的不同方面，这使得MOT研究人员，特别是新来者，很难获得对MOT的全面理解。
• **怎么做：**作者提供了一个综述来讨论多目标跟踪问题的各个方面。

一、摘要

Multiple Object Tracking (MOT) has gained increasing attention due to its academic and commercial potential. Although different approaches have been proposed to tackle this problem, it still remains challenging due to factors like abrupt appearance changes and severe object occlusions. In this work, we contribute the first comprehensive and most recent review on this problem. We inspect the recent advances in various aspects and propose some interesting directions for future research. To the best of our knowledge, there has not been any extensive review on this topic in the community. We endeavor to provide a thorough review on the development of this problem in recent decades. The main contributions of this review are fourfold: 1) Key aspects in an MOT system, including formulation, categorization, key principles, evaluation of MOT are discussed; 2) Instead of enumerating individual works, we discuss existing approaches according to various aspects, in each of which methods are divided into different groups and each group is discussed in detail for the principles, advances and drawbacks; 3) We examine experiments of existing publications and summarize results on popular datasets to provide quantitative and comprehensive comparisons. By analyzing the results from different perspectives, we have verified some basic agreements in the field; and 4) We provide a discussion about issues of MOT research, as well as some interesting directions which will become potential research effort in the future.

• 本论文基本每年都会更新，努力对近几十年来对MOT问题的发展情况进行彻底的调查。
• 本文主要有以下四个方面的贡献：

  • 讨论了MOT系统的关键方面，包括MOT的制定、分类、关键原则、评价。

    Key aspects in an MOT system, including formulation, categorization, key principles, evaluation of MOT are discussed

  • 根据不同的方面讨论现有的MOT方法，每个方法被分到不同的组，并详细讨论每个组的原则、进展和缺点；

    Instead of enumerating individual works, we discuss existing approaches according to various aspects, in each of which methods are divided into different groups and each group is discussed in detail for the principles, advances and drawbacks

  • 仔细检查现有公开模型的实验，并总结在流行的数据集上的结果，以提供定量和全面的比较。通过从不同的角度分析结果，验证了MOT的一些基本一致性

    We examine experiments of existing publications and summarize results on popular datasets to provide quantitative and comprehensive comparisons. By analyzing the results from different perspectives, we have verified some basic agreements in the field

  • 提供了一个关于MOT研究问题的讨论，以及一些有趣的方向，这将成为未来潜在的研究努力方向

    We provide a discussion about issues of MOT research, as well as some interesting directions which will become potential research effort in the future

二、Introduction