Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN Model
The accurate detection of ice hockey players and teams during a game is crucial to the tracking of individual players on the rink and team tactical decision making and is therefore becoming an important task for coaches and other analysts. However, hockey is a fluid sport due to its complex situatio...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9239271/ |
| _version_ | 1819173427267764224 |
|---|---|
| author | Tianxiao Guo Kuan Tao Qingrui Hu Yanfei Shen |
| author_facet | Tianxiao Guo Kuan Tao Qingrui Hu Yanfei Shen |
| author_sort | Tianxiao Guo |
| collection | DOAJ |
| description | The accurate detection of ice hockey players and teams during a game is crucial to the tracking of individual players on the rink and team tactical decision making and is therefore becoming an important task for coaches and other analysts. However, hockey is a fluid sport due to its complex situation and the frequent substitutions by both teams, resulting in the players taking various postures during a game. Few player detection models from basketball and soccer take these characteristics into account, especially for team detection without prior annotations. Here, a two-phase cascaded convolutional neural network (CNN) model is designed for the detection of individual ice hockey players, and the jersey color of the detected players is extracted to further identify team affiliations. Our model filters most of the disturbing information, such as the audience and sideline advertising bars, in Phase I and refines the detection of the targeted players in Phase II, resulting in an accurate detection with a precision of 98.75% and a recall of 94.11% for individual players and an average accuracy of 93.05% for team classification with a self-built dataset of collected images from the 2018 Winter Olympics. The results for the regular season games of the 2019-2020 National Hockey League (NHL) covering all 31 teams are also presented to show the robustness of our model. Compared to state-of-the-art approaches, our player detection model achieves the highest accuracy with the self-built dataset. |
| first_indexed | 2024-12-22T20:22:54Z |
| format | Article |
| id | doaj.art-0162f5b975314d17ba37841f39cd9ccd |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T20:22:54Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0162f5b975314d17ba37841f39cd9ccd2022-12-21T18:13:47ZengIEEEIEEE Access2169-35362020-01-01819506219507310.1109/ACCESS.2020.30335809239271Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN ModelTianxiao Guo0https://orcid.org/0000-0003-0064-5338Kuan Tao1Qingrui Hu2Yanfei Shen3School of Sports Science, Beijing Sport University, Beijing, ChinaSchool of Sports Engineering, Beijing Sport University, Beijing, ChinaSchool of Sports Science, Beijing Sport University, Beijing, ChinaSchool of Sports Engineering, Beijing Sport University, Beijing, ChinaThe accurate detection of ice hockey players and teams during a game is crucial to the tracking of individual players on the rink and team tactical decision making and is therefore becoming an important task for coaches and other analysts. However, hockey is a fluid sport due to its complex situation and the frequent substitutions by both teams, resulting in the players taking various postures during a game. Few player detection models from basketball and soccer take these characteristics into account, especially for team detection without prior annotations. Here, a two-phase cascaded convolutional neural network (CNN) model is designed for the detection of individual ice hockey players, and the jersey color of the detected players is extracted to further identify team affiliations. Our model filters most of the disturbing information, such as the audience and sideline advertising bars, in Phase I and refines the detection of the targeted players in Phase II, resulting in an accurate detection with a precision of 98.75% and a recall of 94.11% for individual players and an average accuracy of 93.05% for team classification with a self-built dataset of collected images from the 2018 Winter Olympics. The results for the regular season games of the 2019-2020 National Hockey League (NHL) covering all 31 teams are also presented to show the robustness of our model. Compared to state-of-the-art approaches, our player detection model achieves the highest accuracy with the self-built dataset.https://ieeexplore.ieee.org/document/9239271/Player detectionteam detectionplayer tracking dataice hockey |
| spellingShingle | Tianxiao Guo Kuan Tao Qingrui Hu Yanfei Shen Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN Model IEEE Access Player detection team detection player tracking data ice hockey |
| title | Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN Model |
| title_full | Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN Model |
| title_fullStr | Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN Model |
| title_full_unstemmed | Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN Model |
| title_short | Detection of Ice Hockey Players and Teams via a Two-Phase Cascaded CNN Model |
| title_sort | detection of ice hockey players and teams via a two phase cascaded cnn model |
| topic | Player detection team detection player tracking data ice hockey |
| url | https://ieeexplore.ieee.org/document/9239271/ |
| work_keys_str_mv | AT tianxiaoguo detectionoficehockeyplayersandteamsviaatwophasecascadedcnnmodel AT kuantao detectionoficehockeyplayersandteamsviaatwophasecascadedcnnmodel AT qingruihu detectionoficehockeyplayersandteamsviaatwophasecascadedcnnmodel AT yanfeishen detectionoficehockeyplayersandteamsviaatwophasecascadedcnnmodel |