Simulating Tracking Data to Advance Sports Analytics Research

• URL: http://arxiv.org/abs/2503.19809v1
• Date: Tue, 25 Mar 2025 16:18:23 GMT
• Title: Simulating Tracking Data to Advance Sports Analytics Research
• Authors: David Radke, Kyle Tilbury,
• Abstract summary: We present a method to collect and utilize simulated soccer tracking data from the Google Research Football environment.<n>We provide processes that extract high-level features and events from the simulated data.<n>We address the scarcity of publicly available tracking data, providing support for research at the intersection of artificial intelligence and sports analytics.
• Score: 4.811183825795439
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Advanced analytics have transformed how sports teams operate, particularly in episodic sports like baseball. Their impact on continuous invasion sports, such as soccer and ice hockey, has been limited due to increased game complexity and restricted access to high-resolution game tracking data. In this demo, we present a method to collect and utilize simulated soccer tracking data from the Google Research Football environment to support the development of models designed for continuous tracking data. The data is stored in a schema that is representative of real tracking data and we provide processes that extract high-level features and events. We include examples of established tracking data models to showcase the efficacy of the simulated data. We address the scarcity of publicly available tracking data, providing support for research at the intersection of artificial intelligence and sports analytics.

Related papers

• Action Anticipation from SoccerNet Football Video Broadcasts [84.87912817065506]
  We introduce the task of action anticipation for football broadcast videos. We predict future actions in unobserved future frames within a five- or ten-second anticipation window. Our work will enable applications in automated broadcasting, tactical analysis, and player decision-making.
  arXiv  Detail & Related papers  (2025-04-16T12:24:33Z)
• SoccerSynth Field: enhancing field detection with synthetic data from virtual soccer simulator [0.8009842832476994]
  We propose the effectiveness of using a synthetic dataset (Soccer Synth-Field) for soccer field detection.<n>A synthetic soccer field dataset was created to pretrain models, and the performance of these models was compared with models trained on real-world datasets.
  arXiv  Detail & Related papers  (2025-03-18T07:05:24Z)
• OpenSTARLab: Open Approach for Spatio-Temporal Agent Data Analysis in Soccer [0.9207076627649226]
  Sports analytics has become more professional and sophisticated, driven by the growing availability of detailed performance data.<n>In soccer, the effective utilization of event and tracking data is fundamental for capturing and analyzing the dynamics of the game.<n>Here we propose OpenSTARLab, an open-source framework designed to democratizetemporal agent data analysis in sports.
  arXiv  Detail & Related papers  (2025-02-05T00:14:18Z)
• SoccerSynth-Detection: A Synthetic Dataset for Soccer Player Detection [0.7332146059733189]
  Soccer Synth-Detection is the first synthetic dataset designed for the detection of synthetic soccer players.<n>It includes a broad range of random lighting and textures, as well as simulated camera motion blur.<n>Our work demonstrates the potential of synthetic datasets to replace real datasets for algorithm training in the field of soccer video analysis.
  arXiv  Detail & Related papers  (2025-01-16T04:06:59Z)
• Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
  We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame. ATM outperforms strong video pre-training baselines by 80% on average. We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
  arXiv  Detail & Related papers  (2023-12-28T23:34:43Z)
• Hang-Time HAR: A Benchmark Dataset for Basketball Activity Recognition using Wrist-Worn Inertial Sensors [47.33629411771497]
  We present a benchmark dataset for evaluating physical human activity recognition methods from wrist-worn sensors. The dataset was recorded for two teams from separate countries (USA and Germany) with a total of 24 players who wore an inertial sensor on their wrist.
  arXiv  Detail & Related papers  (2023-05-22T15:25:29Z)
• Multi-Environment Pretraining Enables Transfer to Action Limited Datasets [129.24823721649028]
  In reinforcement learning, available data of decision making is often not annotated with actions. We propose combining large but sparsely-annotated datasets from a emphtarget environment of interest with fully-annotated datasets from various other emphsource environments. We show that utilizing even one additional environment dataset of sequential labelled data during IDM pretraining gives rise to substantial improvements in generating action labels for unannotated sequences.
  arXiv  Detail & Related papers  (2022-11-23T22:48:22Z)
• Large Scale Real-World Multi-Person Tracking [68.27438015329807]
  This paper presents a new large scale multi-person tracking dataset -- textttPersonPath22. It is over an order of magnitude larger than currently available high quality multi-object tracking datasets such as MOT17, HiEve, and MOT20.
  arXiv  Detail & Related papers  (2022-11-03T23:03:13Z)
• SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos [62.686484228479095]
  We propose a novel dataset for multiple object tracking composed of 200 sequences of 30s each. The dataset is fully annotated with bounding boxes and tracklet IDs. Our analysis shows that multiple player, referee and ball tracking in soccer videos is far from being solved.
  arXiv  Detail & Related papers  (2022-04-14T12:22:12Z)
• Optical tracking in team sports [0.0]
  We provide a basic understanding for quantitative data analysts about the process of creating the input data. We discuss the preprocessing steps of tracking, the most common challenges in this domain, and the application of tracking data to sports teams.
  arXiv  Detail & Related papers  (2022-04-08T15:51:35Z)
• Unified Transformer Tracker for Object Tracking [58.65901124158068]
  We present the Unified Transformer Tracker (UTT) to address tracking problems in different scenarios with one paradigm. A track transformer is developed in our UTT to track the target in both Single Object Tracking (SOT) and Multiple Object Tracking (MOT)
  arXiv  Detail & Related papers  (2022-03-29T01:38:49Z)
• Game Plan: What AI can do for Football, and What Football can do for AI [83.79507996785838]
  Predictive and prescriptive football analytics require new developments and progress at the intersection of statistical learning, game theory, and computer vision. We illustrate that football analytics is a game changer of tremendous value, in terms of not only changing the game of football itself, but also in terms of what this domain can mean for the field of AI.
  arXiv  Detail & Related papers  (2020-11-18T10:26:02Z)
• Group Activity Detection from Trajectory and Video Data in Soccer [16.134402513773463]
  Group activity detection in soccer can be done by using either video data or player and ball trajectory data. In current soccer datasets, activities are labelled as atomic events without a duration. Our results show that most events can be detected using either vision or trajectory-based approaches with a temporal resolution of less than 0.5 seconds.
  arXiv  Detail & Related papers  (2020-04-21T21:11:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.