Automated player identification and indexing using two-stage deep learning network.

Automated player identification and indexing using two-stage deep learning network.
复制标题

使用两阶段深度学习网络的自动球员识别和索引。

DOI:
10.1038/s41598-023-36657-5
复制
发表时间:
2023-06-20
期刊:
影响因子:
4.6
通讯作者:
--
中科院分区:
综合性期刊3区
文献类型:
--
作者:

文献摘要

参考文献

相似文献

美式橄榄球比赛每年都会吸引全世界的关注。从每场比赛的视频中识别球员对于球员参与的索引也至关重要。处理足球比赛视频面临着巨大的挑战,例如拥挤的环境、扭曲的对象以及用于识别球员(尤其是球衣号码)的不平衡数据。在这项工作中,我们提出了一种基于深度学习的球员跟踪系统,可以自动跟踪球员并索引他们在美式橄榄球比赛中的每次比赛参与情况。它是一个两阶段的网络设计,可以突出显示感兴趣的区域并高精度地识别球衣号码信息。首先,我们利用对象检测网络(检测变压器)来解决拥挤环境中的玩家检测问题。其次,我们使用球衣号码识别和辅助卷积神经网络来识别球员,然后将其与比赛时钟子系统同步。最后,系统在数据库中输出完整的日志以用于播放索引。我们通过分析足球视频的定性和定量结果来证明球员跟踪系统的有效性和可靠性。所提出的系统在足球广播视频的实施和分析方面显示出巨大的潜力。
American football games attract significant worldwide attention every year. Identifying players from videos in each play is also essential for the indexing of player participation. Processing football game video presents great challenges such as crowded settings, distorted objects, and imbalanced data for identifying players, especially jersey numbers. In this work, we propose a deep learning-based player tracking system to automatically track players and index their participation per play in American football games. It is a two-stage network design to highlight areas of interest and identify jersey number information with high accuracy. First, we utilize an object detection network, a detection transformer, to tackle the player detection problem in a crowded context. Second, we identify players using jersey number recognition with a secondary convolutional neural network, then synchronize it with a game clock subsystem. Finally, the system outputs a complete log in a database for play indexing. We demonstrate the effectiveness and reliability of player tracking system by analyzing the qualitative and quantitative results on football videos. The proposed system shows great potential for implementation in and analysis of football broadcast video.
DOI: 10.1016/j.future.2021.06.022
发表时间: 2021-07-01
影响因子: 7.5
作者:
Ning, Bai;Na, Liu
通讯作者: Na, Liu
DOI: 10.1038/s41598-022-05966-6
发表时间: 2022-02-03
期刊: Scientific reports
影响因子: 4.6
作者:
Moodley T;van der Haar D;Noorbhai H
通讯作者: Noorbhai H
DOI: 10.1016/j.future.2021.01.020
发表时间: 2021-02-08
影响因子: 7.5
作者:
Liu, Long
通讯作者: Liu, Long
DOI: 10.1186/s40537-018-0151-6
发表时间: 2018-11-01
影响因子: 8.1
作者:
Leevy, Joffrey L.;Khoshgoftaar, Taghi M.;Seliya, Naeem
通讯作者: Seliya, Naeem
DOI: 10.1049/iet-ipr.2018.5589
发表时间: 2019-03-28
影响因子: 2.3
作者:
Javed, Ali;Irtaza, Aun;Adnan, Syed
通讯作者: Adnan, Syed