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

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 [Formula: see text] 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 ≈1:4, ≈1:6, and ≈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 [Formula: see text], [Formula: see text] crop, ≈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.