Soccer match broadcast video analysis method based on detection and tracking

Author:

Li Hongyu1ORCID,Yang Meng12ORCID,Yang Chao1ORCID,Kang Jianglang1ORCID,Suo Xiang3ORCID,Meng Weiliang45ORCID,Li Zhen3,Mao Lijuan3,Sheng Bin6,Qi Jun7ORCID

Affiliation:

1. School of Information science and Technology Beijing Forestry University Beijing China

2. Engineering Research Center for Forestry‐Oriented Intelligent Information Processing National Forestry and Grassland Administration Beijing China

3. School of Athletic Performance Shanghai University of Sport Shanghai China

4. State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation, Chinese Academy of Sciences Beijing China

5. School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

6. Department of Computer Science and Engineering Shanghai Jiao Tong Univerity Shanghai China

7. Department of Computing Xi'an JiaoTong‐Liverpool University Suzhou China

Abstract

AbstractWe propose a comprehensive soccer match video analysis pipeline tailored for broadcast footage, which encompasses three pivotal stages: soccer field localization, player tracking, and soccer ball detection. Firstly, we introduce sports camera calibration to seamlessly map soccer field images from match videos onto a standardized two‐dimensional soccer field template. This addresses the challenge of consistent analysis across video frames amid continuous camera angle changes. Secondly, given challenges such as occlusions, high‐speed movements, and dynamic camera perspectives, obtaining accurate position data for players and the soccer ball is non‐trivial. To mitigate this, we curate a large‐scale, high‐precision soccer ball detection dataset and devise a robust detection model, which achieved the of 80.9%. Additionally, we develop a high‐speed, efficient, and lightweight tracking model to ensure precise player tracking. Through the integration of these modules, our pipeline focuses on real‐time analysis of the current camera lens content during matches, facilitating rapid and accurate computation and analysis while offering intuitive visualizations.

Funder

National Natural Science Foundation of China

Natural Science Foundation of Beijing Municipality

Beihang University

Publisher

Wiley

Reference38 articles.

1. A review of vision-based systems for soccer video analysis

2. Use of deep learning in soccer videos analysis: survey

3. ChenJ LittleJJ.Sports camera calibration via synthetic data. 2019 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW).20192497–2504.

4. HomayounfarN FidlerS UrtasunR.Sports field localization via deep structured models. Proceedings of the IEEE conference on computer vision and pattern recognition.20175212–5220.

5. SegFormer: simple and efficient design for semantic segmentation with transformers;Xie E;Adv Neural Inf Process Syst,2021

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3