Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jun 20;13(1):10036.
doi: 10.1038/s41598-023-36657-5.

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

Hongshan Liu  1 , Colin Adreon  2 , Noah Wagnon  2 , Abdul Latif Bamba  3 , Xueshen Li  1 , Huapu Liu  4 , Steven MacCall  4 , Yu Gan  5
Affiliations

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

Hongshan Liu et al. Sci Rep. .

Abstract

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.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
An example of the output of the proposed system: player detection, jersey number recognition, and game log.
Figure 2
Figure 2
Flowchart of the proposed work.
Figure 3
Figure 3
Image processed with one-stage YOLOv2, shows limited performance if a one-stage model is directly applied.
Figure 4
Figure 4
Example of data augmentation: (a) Original frame; (b) Original frame with motion-blurry effect.
Figure 5
Figure 5
Example of players’ proposals; example of digit on jersey.
Figure 6
Figure 6
Color filtering demonstration: (a) player wears red jersey, (b) histogram of center region of red jersey, (c) player wears white jersey; (d) histogram of center region of white jersey.
Figure 7
Figure 7
Representative testing results. (a–c) original frames; (d–f) Result from Faster R-CNN (g–i) Result from DETR.
Figure 8
Figure 8
(a) Digit counts grouped by jersey color. (b) Confusion matrix of digit recognition result, with IoU=0.55 and confidence = 0.97.
Figure 9
Figure 9
Part of the output game log, including the player detecting information, play number, quarter, start/end time, home/away team.
See this image and copyright information in PMC

References

    1. Sports Media Watch. Super bowl ratings history (1967-present) (2022).
    1. National Football League. NFL Guide for Statisticians (2022). https://www.nflgsis.com/gsis/documentation/stadiumguides/guide_for_stati... (2022).
    1. National Collegiate Athletic Association. The Official National Collegiate Athletic Association 2022 Football Statisticians’ Manual Including Special Interpretations and Approved Rulings Covering Unusual Situations (2022). http://fs.ncaa.org/Docs/stats/Stats_Manuals/Football/2022.pdf (2022).
    1. Nady, A. & Hemayed, E. E. Player identification in different sports. In VISIGRAPP (5: VISAPP), 653–660 (2021).
    1. Šari, M., Dujmi, H., Papi, V. & Roži, N. Player number localization and recognition in soccer video using HSV color space and internal contours. In The International Conference on Signal and Image Processing (ICSIP 2008) (Citeseer, 2008).