Building a Provenance-First Computer Vision Corpus

Every bounding box, track, label, and homography stores:

• Source master file ID
• Exact frame number
• Model/version that produced it
• Confidence score
• Schema version

Future models can be run retroactively over the entire historical corpus because raw evidence (tracks, homography, audio features) is stored at ingest.

Only first-party film (your own team's Hudl exports, self-filmed 4K sideline) or properly licensed commercial film is ingested. No NFHS streams, no scraped content. The pipeline is deliberately source-agnostic but the business rule is strict.

• Helmet detection agreement: 97.9% over 240 frames
• ~9,900 frames labeled with 193,736 boxes

The dataset grows with every game ingested, whether or not the film receives restoration or clipping. This ensures that when advanced route/coverage models arrive, they have the full historical base to train on.