作者：Nir Aharon, Roy Orfaig, Ben-Zion Bobrovsky

作者单位：School of Electrical Engineering, Tel-Aviv University

发布时间：2022

发布期刊/会议：Arxiv

出版商：

**论文全称：**BoT-SORT: Robust Associations Multi-Pedestrian Tracking

论文地址：

论文代码：

https://github.com/niraharon/bot-sort

PaddleDetection/configs/mot at develop · PaddlePaddle/PaddleDetection

地位：

个人理解

• 创新点：对基于多目标跟踪的检测跟踪方法进行了三个主要的修改和改进。通过将这些集成到ByteTrack中
  • 修改卡尔曼滤波器，原先卡尔曼滤波器的状态向量由七个元素表示，本文改进为八个元素表示
  • 遵循OpenCV[7]中使用的全局运动补偿(GMC)技术实现仿射变换的视频稳定模块(背景运动)，从而进行图像运动校正
  • 提出使用 IOU+ReID 融合机制的策略来进行匹配

一、摘要

The goal of multi-object tracking (MOT) is detecting and tracking all the objects in a scene, while keeping a unique identifier for each object. In this paper, we present a new robust state-of-the-art tracker, which can combine the advantages of motion and appearance information, along with camera-motion compensation, and a more accurate Kalman filter state vector. Our new trackers BoT-SORT, and BoT-SORT-ReID rank first in the datasets of MOTChallenge [29, 11] on both MOT17 and MOT20 test sets, in terms of all the main MOT metrics: MOTA, IDF1, and HOTA. F or MOT17: 80.5 MOTA, 80.2 IDF1, and 65.0 HOTA are achieved.