Broadcast analytics – an evaluation of video-based tracking systems with constrained player visibility
Bibliographic record
Abstract
Advancements in recent years have enabled the generation of tracking data from broadcast videos. However, regardless of the quality of these systems, off-screen actions cannot be monitored since the athletes are not visible. The present study investigates the influence of player visibility in soccer broadcast videos on typical data analysis routines in soccer. To this end, we emulate broadcast player tracking data from two video sources (scouting feed, SF; broadcast television, TV) and compare the quality of physical and tactical performance metrics to the official player tracking data (GT) in two experiments. Experiment 1 analyzes the impact of player visibility on total distance and high-speed distance covered, while experiment 2 investigates its effect on tactical formation detection through template matching. The results show that overall 97% but less than 50% of player activity is visible in SF and TV, respectively. Experiment 1 indicates that visibility in SF and TV significantly affects the assessment of physical match intensity. Experiment 2 shows that SF visibility has no meaningful effect on formation recognition accuracy, while limited visibility in TV results in minor accuracy reductions. The findings suggest that while some tactical analysis can be reliably conducted using broadcast tracking data, physical metrics may be more susceptible to inaccuracies caused by missing data. Although data quality may be improved through interpolation of missing player trajectories, researchers and practitioners rely on transparency from data providers regarding their methods to assess the sufficiency of their data to the task at hand.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".