System and method for merging asynchronous data sources
By merging broadcast video and live report data using computer vision, optical character recognition, and machine learning technologies, rich tracking data for sports competitions was generated, solving the problem of insufficient frame-level accuracy in existing technologies and achieving high-precision data merging and analysis.
CN116261748BActive Publication Date: 2026-06-16STAT LLC
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- STAT LLC
- Filing Date
- 2021-10-01
- Publication Date
- 2026-06-16
Smart Images
Figure CN116261748B_ABST
Abstract
A computing system identifies broadcast video data of a game. The computing system generates tracking data of the game from the broadcast video data using computer vision techniques. The tracking data includes coordinates of players during the game. The computing system generates optical character recognition data of the game from the broadcast video data by applying one or more optical character recognition techniques to each of a plurality of frames to extract score and time information from a scoreboard displayed in each frame. The computing system detects a plurality of events that occur in the game by applying one or more machine learning techniques to the tracking data. The computing system receives play-by-play data of the game. The computing system generates enriched tracking data. The generating includes merging the play-by-play data with one or more of the tracking data, the optical character recognition data, and the plurality of events.
Need to check novelty before this filing date? Find Prior Art