Building watchable digital twins of 64 World Cup games

A lot of us saw the cool World Cup data visualizations going around social media, like this one from Alexander Bogachev:

Source: Bogachev's tweet here

I wanted to make my own but go a lot deeper, so I went looking to see where the data comes from.It turns out a bunch of companies sell data to sports teams and gamblers that they build using computer vision on live broadcasts. It works something like this:Source: SoccerNetObject detection and OCR for players / ball trackingField geometry identification for coordinate transform (using the penalty box corners, center circle, goal lines)Mix of inference and human tagging to log events (like passes, interceptions, shots, penalties)There's a lot more complexity around event tagging and player tracking, which requires visual embeddings for the players to maintain a best guess of their position when their jersey number isn't visible, but this is the high level.The completeness of this tracking data varies by provider. It generally falls into the following categories:

Each row May include

Matches one match competition, date, home & away teams, stadium, score / outcome, # periods

Roster one player player name, team, position, jersey number, started?

Events one event event type, timestamp, duration, actor, detail (varies by type)

Tracking one frame each player's XY position, ball XYZ position

I found 5 providers that offer free data samples for developers. Here's a quick comparison of their level of completeness:

Source # Games What Frames/game Link

PFF 64 Videos + events + tracking ~160k Data

StatsBomb 426 Events + tracking ~3-4k Data

Metrica 3 Events + tracking ~160k Data

SoccerNet 550 Videos + raw CV data ~160k Data

WhoScored Many Avg team X position (what Bogachev used?) ~100 Example game

Since I'm building high-resolution digital twins of the games, I need a minimum of ~2 data frames per second (~11k frames total). PFF data is the most complete and polished with XY coordinates for all players at 30Hz.

This resolution allows us to do any kind of game analysis, or visualization, we want. The data also happens to be from the 2022 World Cup! Other sources had regional league games.💡Side note: SoccerNet seems to have the best scientific community around game data extraction with multiple publications and helpful public reposNow let's dig into PFF's data. Here's what it looks like, per game:Match: 1KBRoster: 8KBEvents: ~16-20MBTracking: ~0.8-1.2GBThe event data is highly detailed. Below is an example event object from a Messi header initialBodyType:HE at 13:36 in the Argentina v France final:{ "frameNum": 29098, "period": 1, "periodGameClockTime": 816.417238, "game_id": 10517, "game_event_id": 6739132, "game_event": { "game_event_type": "OTB", "formatted_game_clock": "13:36", "player_id": "1531", "player_name": "Lionel Messi", "shirt_number": "10", "position_group_type": "RW", "team_id": "364", "team_name": "Argentina", "start_time": 970.904, "end_time": 970.904, "duration": 0, "home_team": 1, "sequence": 48, "home_ball": true }, "possession_event": { "possession_event_type": "PA" }, "event_data": { "sequence": 48, "initialTouch": { "initialBodyType": "HE",

"initialHeightType": "A", "facingType": "G", "initialTouchType": "S", "initialPressureType": "N" }, "possessionEvents": { "possessionEventType": "PA", "nonEvent": false, "ballHeightType": "A", "highPointType": "A", "passType": "S", "passOutcomeType": "C", "targetPlayerId": 10715, "targetPlayerName": "Julian Alvarez", "targetFacingType": "B", "receiverPlayerId": 10715, "receiverPlayerName": "Julian Alvarez", "receiverFacingType": "B", "accuracyType": "S", "pressureType": "N", "createsSpace": false } } } So here's what we want to build: a "video player" for World Cup games, rendering, as faithfully as possible, a 3D stadium, field, fans, and players.The architecture will be pretty simple:API server providing a list of available games, player info, and video keyframesStreaming endpoint to deliver XY coordinates for players as the user watches the gameWeb viewer with a game selector and video playerWe'll start with a 2D visualization. Claude did a great job parsing the PFF data spec and building a compressed / streamable data format with a simple player to watch the data in 2D. Each game came out to ~100MB split into ~600 10-second files that are requested by the client in sequence as you watch the game. I'm sure this could be optimized further — JSON is not an efficient format. 0:00 /0:12 Very cool! Now let's make it 3D, which of course will require no additional position data. We could just build a 3D stadium and 3D players and have them run around at the same XY coordinates, but this breaks down in cases where the players aren't running, e.g. corner kicks, headers, and injuries.Also, our player position data is scraped from live broadcasts.

On average, for 27% of broadcast airtime the ball is not in play or the camera is running a replay, player closeup, etc, so we don't have player tracking data for those frames. To create a pleasant viewing experience we need to show something else, like a cutscene.This is where our event data comes in handy. I had Claude build the following player motions and cutscenes which are played when they are triggered by certain events:

Type Name Avg # / game Avg time / event

Player motion Run / walk N/A N/A

Player motion Header 93 0.9s

Player motion Goalie dive 8.8 3s

Player motion Goal celebration 2.7 20s

Player motion Injury 30 10s

Camera angle Corner kick 9.0 12s

Camera angle Throw-in 40.9 6s

Camera angle Free kick 28.5 8s

Camera angle Penalty kick 0.4 12s

Camera angle Kick off 4.8 10s

Referee actions Yellow/red card 3.6 3s

Referee actions Offside flag 4.1 3.5s

Referee actions VAR review 0.3 5s

Referee actions Substitution 9.2 10s

We can also create a simulated crowd composed of fans wearing jerseys for the home or away team, who audibly and visibly cheer when their team is advancing or making shots on goal.Now, putting this all together, we get a decently faithful reproduction of a soccer game in our video player: 0:00 /0:14 Of course we could go arbitrarily higher fidelity but that's not the point. Since we already have the data, we can visualize it any way we want. Here are some aliens playing the 2022 World Cup final on Mars: 0:00 /0:15 I've open sourced the data builder and viewer here.

Please fork it and build whatever you want! Hmu on GitHub with any questions ⚽References:https://skillcorner.com/products/football/xy-tracking-datahttps://www.gradientsports.com/trackinghttps://www.hudl.com/products/statsbomb