Computer vision · Sports data · Product leadership

From pixels to table state

A snooker computer-vision proof point designed as a trustworthy data product: calibrate the table, resolve ball state, expose uncertainty and make the output legible to both technical reviewers and commercial stakeholders.

Computer vision Data products Evaluation Sports AI
Watch the demo See the evidence
CalibratedTable coordinate system
ReviewableBall-state evidence pack
56 secondsAnnotated demo

A vertical product slice from raw frame through QA and stakeholder-facing output.

Executive takeaway

Build the evidence chain, not the demo.

The useful product is not a bounding box. It is a reliable path from a changing broadcast view to a normalized table state that can support annotation, benchmark design, shot analysis and future probability features. I scoped the first proof point around that foundation and made every stage reviewable.

Start with the stable layer

Ball identity, position and state come before tactics or prediction. That kept the first contract narrow enough to evaluate and broad enough to unlock later products.

Normalize the world

A table homography converts image pixels into regulation-table coordinates. Downstream logic can then reason about the game rather than one camera angle.

Treat uncertainty as workflow

Hard cases, occlusions, inventory conflicts and unsafe refinements are routed into QA instead of being hidden behind an aggregate score.

System

From frame to decision signal.

The system separates perception from game logic. Frames are calibrated to the playing surface; candidate balls are detected and classified; coordinates are projected into normalized and millimetre space; and derived features can then be built on a consistent representation. Provenance and QA status stay attached throughout.

Pipeline diagram showing calibration, ball-state resolution, coordinate normalization and decision review, with provenance and QA controls across every stage.
The architecture is deliberately decomposable: each stage can be tested, replaced or reviewed without rewriting the product contract.

Calibrated coordinates

Map each table to a regulation playing surface so position means the same thing across crops, zooms and broadcast layouts.

Inventory-aware cleaning

Merge duplicates, reject off-table candidates and apply snooker inventory constraints before labels reach training or scoring.

Static-frame proof first

Establish a dependable table-state layer before adding temporal tracking, rules state and higher-order shot models.

Demonstration

Make the pipeline visible.

The annotated demo is a product communication object, not a claim that every overlay is production validated. It shows how calibrated ball state could feed shot geometry, event resolution and frame-level probability features in a form that stakeholders can challenge.

A silent 56-second visual demo. Three broadcast shots are frozen at decision points, balls are labelled, shot paths and outcomes are overlaid, and the illustrative frame-win signal updates after each resolved shot.
Read the visual sequence
  1. The first frame locks the table, pockets and visible balls.
  2. A banked-red path is drawn from cue contact through cushion contact to the finish point.
  3. The post-shot table state is resolved and the illustrative frame signal changes.
  4. Two later states repeat the freeze, label, resolve and update pattern.
Ten-frame spot-check contact sheet from the snooker demo showing the progression from raw table view to labelled objects, shot path, outcome and updated state.
A static spot-check sheet makes timing, label placement and state transitions reviewable without scrubbing through video.

Evaluation & QA

Show what the evidence can—and cannot—support.

The annotation loop uses calibrated perspective and highlight evidence to improve candidate centres, then automatically rolls back unsafe frame-level refinements. Triage separates clean passes, review candidates and high-severity conflicts so human effort lands where it adds the most value.

A held-out baseline proves the local end-to-end loop and creates a stable comparison point. Its purpose is engineering direction, not marketing theatre: challenge-grade claims wait for an independently reviewed and locked reference set.

Automated guards

Catch structural failure

Off-table centres, duplicate detections, impossible inventories, missing colours and risky cluster refinements create explicit review signals.

Visual review

Inspect the geometry

Overlays and before/after sheets expose whether a numerically small adjustment is visually correct in dense red clusters.

Promotion gate

Separate prefill from truth

Human centre review, red-count reconciliation, calibration checks and anti-leak review are required before a hidden scoring set is promoted.

Side-by-side V20 and V21 snooker table overlays illustrating calibrated glint and projected-scale centre refinement.
One V20/V21 comparison. Ball inventory remains stable while the revised centre logic uses glint evidence and perspective-scaled ball size.

Outcome & lessons

A proof point built to become a benchmark.

The work produced a stakeholder-ready demonstration, a calibrated annotation pipeline, a versioned prefill pack, inspectable QA artifacts and an evaluation baseline. More importantly, it made the next investment decisions concrete: where human review adds value, which classes need targeted data, and when temporal modelling becomes worthwhile.

  • Design the coordinate system before the clever feature. Stable table coordinates make future tracking and game-state logic far easier to reason about.
  • Hard cases are a product surface. A useful review queue often creates more value than another opaque point of aggregate accuracy.
  • Label the metric’s authority. A pseudo-label holdout is an engineering baseline; it is not the same evidence as locked, independently reviewed ground truth.
  • Demonstrations should expose the contract. Showing the chain from detection to decision lets commercial and technical teams discuss the same system.