GTA: Global Tracklet Association for Multi-Object Tracking in Sports

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Jiacheng, Huang, Hsiang-Wei, Yang, Cheng-Yen, Jiang, Zhongyu, Hwang, Jenq-Neng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929589239939072
author Sun, Jiacheng
Huang, Hsiang-Wei
Yang, Cheng-Yen
Jiang, Zhongyu
Hwang, Jenq-Neng
author_facet Sun, Jiacheng
Huang, Hsiang-Wei
Yang, Cheng-Yen
Jiang, Zhongyu
Hwang, Jenq-Neng
contents Multi-object tracking in sports scenarios has become one of the focal points in computer vision, experiencing significant advancements through the integration of deep learning techniques. Despite these breakthroughs, challenges remain, such as accurately re-identifying players upon re-entry into the scene and minimizing ID switches. In this paper, we propose an appearance-based global tracklet association algorithm designed to enhance tracking performance by splitting tracklets containing multiple identities and connecting tracklets seemingly from the same identity. This method can serve as a plug-and-play refinement tool for any multi-object tracker to further boost their performance. The proposed method achieved a new state-of-the-art performance on the SportsMOT dataset with HOTA score of 81.04%. Similarly, on the SoccerNet dataset, our method enhanced multiple trackers' performance, consistently increasing the HOTA score from 79.41% to 83.11%. These significant and consistent improvements across different trackers and datasets underscore our proposed method's potential impact on the application of sports player tracking. We open-source our project codebase at https://github.com/sjc042/gta-link.git.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08216
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GTA: Global Tracklet Association for Multi-Object Tracking in Sports
Sun, Jiacheng
Huang, Hsiang-Wei
Yang, Cheng-Yen
Jiang, Zhongyu
Hwang, Jenq-Neng
Computer Vision and Pattern Recognition
Multi-object tracking in sports scenarios has become one of the focal points in computer vision, experiencing significant advancements through the integration of deep learning techniques. Despite these breakthroughs, challenges remain, such as accurately re-identifying players upon re-entry into the scene and minimizing ID switches. In this paper, we propose an appearance-based global tracklet association algorithm designed to enhance tracking performance by splitting tracklets containing multiple identities and connecting tracklets seemingly from the same identity. This method can serve as a plug-and-play refinement tool for any multi-object tracker to further boost their performance. The proposed method achieved a new state-of-the-art performance on the SportsMOT dataset with HOTA score of 81.04%. Similarly, on the SoccerNet dataset, our method enhanced multiple trackers' performance, consistently increasing the HOTA score from 79.41% to 83.11%. These significant and consistent improvements across different trackers and datasets underscore our proposed method's potential impact on the application of sports player tracking. We open-source our project codebase at https://github.com/sjc042/gta-link.git.
title GTA: Global Tracklet Association for Multi-Object Tracking in Sports
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.08216