Skip to content
Innovaith Solutions

Data & annotation

Turn match footage into data you can use.

We turn broadcast and training footage into data that analysts, coaches and sports products can use. That means following the players and the ball, marking the moments that matter, and building the models that sit on top. We can hand you labelled footage for your own models or work with you on the whole analysis.
An analyst at a desk watching a volleyball match on a monitor.
Player and ball trackingEvent taggingPerformance metricsTactical and formation analysisHighlight detectionBroadcast footage annotation

What we offer

Sports Analytics services.

  • 01

    Player and ball tracking

    Frame-by-frame positions for players, officials and the ball, with consistent identities throughout a match.

  • 02

    Event tagging

    Passes, shots, tackles, fouls and set pieces logged with timestamps, players involved and pitch locations.

  • 03

    Performance metrics

    Physical and technical measures derived from tracking and event data, defined together with your analysts.

  • 04

    Tactical and formation analysis

    Team shape, pressing, defensive line height and formation changes identified across phases of play.

  • 05

    Highlight detection

    Models and labels that find key moments in long footage so editors spend less time scrubbing through video.

  • 06

    Broadcast footage annotation

    Camera angles, replays, scoreboards and on-screen graphics labelled so they can be handled correctly downstream.

How we work

From guidelines to delivered data.

AI takes the first pass, trained people review it, and quality is checked before delivery.
See How We Work
  1. 01

    Scope

    We agree label definitions, edge cases, formats and quality targets with you.

  2. 02

    Pilot

    A small batch tests the guidelines before any volume work starts.

  3. 03

    Annotate

    Trained annotators label to the agreed guidelines, with tooling to match.

  4. 04

    Review

    Multi-stage quality review against the specification, with feedback loops.

  5. 05

    Deliver

    Data in your format, with notes on what was checked, then we iterate.

Where it helps

Typical projects.

The kinds of work this service usually supports.
A video production desk with a monitor showing several camera feeds.
  • Club performance analysis

    Giving coaching and analysis staff consistent event and tracking data for post-match review and opposition scouting.

  • Recruitment and scouting

    Building player datasets that make it easier to compare candidates across leagues and competitions.

  • Media and highlights

    Helping broadcasters and content teams find and package key moments from full-match footage.

  • Sports technology products

    Training data and models for apps, wearables and platforms that analyse amateur or professional play.

Details

Output formats

  • Event data (JSON or CSV)
  • Frame-level tracking CSV
  • Pitch-coordinate data
  • COCO JSON
  • MOT Challenge format
  • YOLO TXT
  • Timestamped clip lists
  • Custom event schemas

Questions

Which sports can you work with?

The approach works for team and individual sports alike. For each project we agree event definitions and tagging rules with your analysts before production starts.

Can you use our own event definitions?

Yes. We can follow your existing event taxonomy or help you write one, and we keep a shared glossary so tags stay consistent across matches and annotators.

Do you work with broadcast or tactical camera footage?

Both. We annotate broadcast feeds, wide tactical angles and training-ground footage, and we mark camera cuts and replays so they do not distort tracking data.

All services

We mark up your images and video, saying what each thing is and where, so AI can learn to recognise it.

Explore service

Software that watches video for you and flags what matters, from recorded footage to live alerts.

Explore service

Idea → Architecture → Prototype → Production → Scale

Talk to us about Sports Analytics.

Tell us what you're trying to build, test, automate or improve. We'll tell you honestly where we can make a real difference, and where we can't.