<p>Youth ice hockey lacks scalable, automated tools to quantify collision exposure and efficiently identify candidate head-impact events from routine game video. This study presents a player-centric, video-based pipeline for detecting physical contact events in single-view full-game footage and demonstrates its utility as a pre-filter to accelerate head-impact dataset creation and support injury surveillance. For training and validation, we constructed labeled player-centric clips around manually annotated contact events; for full-game testing, we applied the same pipeline to continuous game footage. In both settings, the unit of analysis is a fixed-duration (1 s) player-centric clip, and the model outputs one binary label (contact vs. non-contact) per clip. Players were detected using a youth-tuned You Only Look Once (YOLO)v8 model and tracked using StrongSORT with an intersection over union (IoU)-assisted matching cost to improve identity continuity under temporary occlusions. Contact events were manually annotated in 20 youth games (Under-11, Under-13, and Under-15). For each event, annotators recorded the event frame and marked the impacted player (head/body location), which was used to associate the event with the corresponding tracklet (point-in-box). A 60-frame clip spanning a <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\pm 0.5\)</EquationSource> </InlineEquation> s window around the event (60 fps) was extracted and uniformly subsampled to 30 frames for classification. Non-contact clips were sampled from tracklet windows that did not overlap annotated events, yielding contact: non-contact ratios of <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\approx\)</EquationSource> </InlineEquation>1:4, <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\approx\)</EquationSource> </InlineEquation>1:6, and <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(\approx\)</EquationSource> </InlineEquation>1:9. A Temporal Shift Module (TSM) classifier processed each player-centric clip, and we evaluated the effects of crop scale and class imbalance on contact detection performance. The best configuration (15 segments, shift division <InlineEquation ID="IEq5"> <EquationSource Format="TEX">\(=4\)</EquationSource> </InlineEquation>, <InlineEquation ID="IEq6"> <EquationSource Format="TEX">\(1.5\times\)</EquationSource> </InlineEquation> crop, <InlineEquation ID="IEq7"> <EquationSource Format="TEX">\(\approx\)</EquationSource> </InlineEquation>1:9 training ratio) achieved strong contact detection under evaluation conditions. The final model was then applied to two unseen full-length Under-13 games by partitioning each game into non-overlapping 1 s segments (60 frames at 60 fps), detecting and tracking players, post-processing tracklets, and classifying a player-centric clip for every tracked player. This full-game evaluation performed substantially above a random baseline and provides a practical operating point under realistic class imbalance. As a downstream demonstration, the contact detector served as an effective pre-filter for head-impact review: At the default decision threshold (0.5), 19 of 22 manually identified head impacts occurred in player-centric clips predicted as contact (86.4% head-impact recall), reducing manual review from over three hours to under 30 minutes per game. Overall, the proposed pipeline enables scalable contact-event monitoring in youth hockey and substantially reduces the burden of curating head-impact datasets from full-game video footage.</p>

Automated detection of physical contact events in youth ice hockey: a player-centric deep learning approach

期刊论文
出版模式：

开放获取
发表日期：

2026年3月25日

查看全文

Amir Azadi,
Parisa Dehghan,
Rowan Mohamed Amin Hefny Hussein,
Clara Karton,
Maia Fraser,
Robert Laganière,
Ryan B. Graham,
T. Blaine Hoshizaki

摘要

Youth ice hockey lacks scalable, automated tools to quantify collision exposure and efficiently identify candidate head-impact events from routine game video. This study presents a player-centric, video-based pipeline for detecting physical contact events in single-view full-game footage and demonstrates its utility as a pre-filter to accelerate head-impact dataset creation and support injury surveillance. For training and validation, we constructed labeled player-centric clips around manually annotated contact events; for full-game testing, we applied the same pipeline to continuous game footage. In both settings, the unit of analysis is a fixed-duration (1 s) player-centric clip, and the model outputs one binary label (contact vs. non-contact) per clip. Players were detected using a youth-tuned You Only Look Once (YOLO)v8 model and tracked using StrongSORT with an intersection over union (IoU)-assisted matching cost to improve identity continuity under temporary occlusions. Contact events were manually annotated in 20 youth games (Under-11, Under-13, and Under-15). For each event, annotators recorded the event frame and marked the impacted player (head/body location), which was used to associate the event with the corresponding tracklet (point-in-box). A 60-frame clip spanning a \(\pm 0.5\) s window around the event (60 fps) was extracted and uniformly subsampled to 30 frames for classification. Non-contact clips were sampled from tracklet windows that did not overlap annotated events, yielding contact: non-contact ratios of \(\approx\) 1:4, \(\approx\) 1:6, and \(\approx\) 1:9. A Temporal Shift Module (TSM) classifier processed each player-centric clip, and we evaluated the effects of crop scale and class imbalance on contact detection performance. The best configuration (15 segments, shift division \(=4\) , \(1.5\times\) crop, \(\approx\) 1:9 training ratio) achieved strong contact detection under evaluation conditions. The final model was then applied to two unseen full-length Under-13 games by partitioning each game into non-overlapping 1 s segments (60 frames at 60 fps), detecting and tracking players, post-processing tracklets, and classifying a player-centric clip for every tracked player. This full-game evaluation performed substantially above a random baseline and provides a practical operating point under realistic class imbalance. As a downstream demonstration, the contact detector served as an effective pre-filter for head-impact review: At the default decision threshold (0.5), 19 of 22 manually identified head impacts occurred in player-centric clips predicted as contact (86.4% head-impact recall), reducing manual review from over three hours to under 30 minutes per game. Overall, the proposed pipeline enables scalable contact-event monitoring in youth hockey and substantially reduces the burden of curating head-impact datasets from full-game video footage.