Professional Darts Pre-Throw Gaze Dataset (PDC World Championship 2026)

Read full text Summarise with VIRAT
Authors: Aiden Lyons, Morgan Daniel, Roan Murray
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

A manually curated dataset of 1,725 verified pre-throw intent frames extracted from three PDC World Championship matches played on 2–3 January 2026. Each row corresponds to a single dart throw and contains: 3D gaze vectors (left eye, right eye, and averaged) in head-normalised coordinates, head pose axes (x/y/z), face bounding box, eye agreement score, and linked game-state context (remaining score, segment label, checkout flags) matched to the Sportradar timeline feed. All frames were manually reviewed and verified. Gaze was extracted using MediaPipe Face Landmarker. Players: Gary Anderson, Gian van Veen, Luke Littler, Ryan Searle (4 players, 3 matches). All 1,725 samples passed face detection (detector confidence = 1.0) with mean eye agreement 0.993. Collected to support pre-throw intent prediction for automated darts broadcast spotting.

Fields of Study & Subjects

Gaze Tracking and Assistive Technology Face recognition and analysis Sports Dynamics and Biomechanics

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
27 March 2026
Language
EN
Document type
Dataset