| Summary: | Current player tracking methods using multiple fixed stadium-based cameras and wearable sensors have limitations. To address this, a new computer vision system using aerial drone imagery has been developed to track football players. This approach is less expensive, has a wider field of view, and captures data not accessible through sensors. However, the visual performance has not been extensively evaluated. In this study, we aimed to determine the system's tracking performance using an F-measure score, which is calculated based on the number of true positives, false positives, and false negatives identified during the tracking process. We also investigated the tracking reliability by comparing the intra-operator performance using the ICC for distance, speed, and time metrics by repeating the measurements five times. The aerial-imagery data were taken from a test match recorded using a drone that was hovered away from the touchline. Four players were tracked and measured simultaneously. The system demonstrates accuracy by performing admirably with average F-measure scores of 0.80, 0.80, 0.89, and 0.84 for player A0, player A1, player B0, and player B1, respectively. Meanwhile, the intra-operator reliability for distance and speed was deemed good to moderate with %MD < 10%. The findings suggest that the system is a capable and reliable computer vision tracking tool with potential applications in performance analysis, training feedback, and injury prevention. © (2024), (UiTM Press). All rights reserved.
|
|---|