**作者：**Zelin Liu, Xinggang Wang, Cheng Wang, Wenyu Liu, Xiang Bai

作者单位：

发布时间：2023

发布期刊/会议：Arxiv

出版商：

**论文全称：**SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth

论文地址：

SparseTrack: Multi-Object Tracking by Performing Scene...

论文代码：

https://github.com/hustvl/SparseTrack

地位：

个人理解

• **为什么：**尽管现有的跟踪方法已经取得了令人印象深刻的性能，但拥堵和频繁的遮挡仍然是多目标跟踪的难点
• 创新点：
  • 提出了一种从二维图像中获取目标相对深度的伪深度估计方法（preudo-depth estimation method）
  • 设计了一种深度级联匹配(DCM)算法，利用得到的深度信息将一个密集目标集转换成多个稀疏目标子集，并在这些稀疏目标子集上按远近顺序进行数据关联
  • 通过将伪深度方法和DCM策略集成到数据关联过程中，提出了一种新的跟踪器，称为SparseTrack。

一、摘要

Exploring robust and efficient association methods has always been an important issue in multiple-object tracking (MOT). Although existing tracking methods have achieved impressive performance, congestion and frequent occlusions still pose challenging problems in multi-object tracking. We reveal that performing sparse decomposition on dense scenes is a crucial step to enhance the performance of associating occluded targets. To this end, we propose a pseudo-depth estimation method for obtaining the relative depth of targets from 2D images. Secondly, we design a depth cascading matching (DCM) algorithm, which can use the obtained depth information to convert a dense target set into multiple sparse target subsets and perform data association on these sparse target subsets in order from near to far. By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack. SparseTrack provides a new perspective for solving the challenging crowded scene MOT problem. Only using IoU matching, SparseTrack achieves comparable performance with the state-of-the-art (SOTA) methods on the MOT17 and MOT20 benchmarks.

• 在密集场景上进行稀疏分解是提高被遮挡目标关联性能的关键步骤
• 对此：
  • 提出了一种从二维图像中获取目标相对深度的伪深度估计方法（preudo-depth estimation method）
  • 设计了一种深度级联匹配(DCM)算法，利用得到的深度信息将一个密集目标集转换成多个稀疏目标子集，并在这些稀疏目标子集上按远近顺序进行数据关联
• 通过将伪深度方法和DCM策略集成到数据关联过程中，提出了一种新的跟踪器，称为SparseTrack。