Sports Data Science: are you ready to take the next (technical) hurdle?

Do you know what our projects called COURSE, STATS, STRADA and DAIQUIRI, VENTOUX and Wireless Cycling Network have in common? They all originated in Sports Data Science, the research group of Professor Steven Verstockt at UGent (IDLab).

The engineering focused research group has built a nice portfolio of sports related projects. The projects and their technologies contain an awful lot of potential to develop further, so that’s why we want to showcase each of them. Let us know which one resonates the most with your interests and ambitions! Here we go:

COURSE: A tool to predict unsafe situations in a cycling race

COURSE is a tool that collects unstructured incident tweets from cycling-related Twitter/X accounts and transforms it into structured data. This data is further enriched with input from cyclists, teams and race commissioners.

The data is used in the development of a course evaluation tool for identifying dangerous points on the race parcours. With the help of artificial intelligence, the tool analyzes race info provided by organizers (GoPro footage, gps course files descriptions, etc.). COURSE generates detailed stats/maps that UCI and organizers can use to determine how safe or unsafe certain segments of their races are.

→ More info on COURSE:

VENTOUX: Making cycling broadcasts more interactive

VENTOUX focuses on innovative formats for cycling broadcasting and investigates several video enrichment methods to optimize the user experience of these broadcasts.

Based on metadata generated by Artificial Intelligence (AI), VENTOUX optimizes the searchability of the video and exploits the content more widely. In addition, this project investigates how different video streams can be combined in an accurate 3D representation of the environment, on which additional virtual information can then be mapped (e.g. virtual banners and profiles).

→ More info on VENTOUX:

STRADA: A Sensor-Driven Tripod for Recording Athlete Data

STRADA is a tool that collects, analyses and learns from sports data. The aim is to capture available data streams, such as heart rate monitors, video streams, and lap times in real-time and use all these data streams to automatically detect highlights during training or competition, e.g., an attack of your favorite rider in track cycling, an overtake in short track speed skating, …

The framework generates short, personalized video clips that might attract the broader attention of sports fans (and broadcasting companies) and keeps them engaged. These filtered video clips also have value for athletes and coaches to improve technical and tactical skills.

→ More info on STRADA:

STATS: A Sensing & Testing Analytics Toolbox for Soldiers

This 2-year project aims to use sensor data and specific military test batteries for early detection of suboptimal performance and dysfunction at physical, mental or health issue levels. With a focus on non-commissioned officer training in Arlon (Belgium), the project seeks to explain high dropout rates and predict individual dropouts within the first eight weeks of training.

The DEFRA STATS project marks progress in improving military training through the integration of wearable technologydata analysis and expert insights. Initial findings underscore the potential of continuous monitoring to improve individual support, contributing to the overall success and well-being of military personnel during training.

→ More info on STATS:

Wireless Cycling Network (WCN): A dashboard to support coaches of track cyclists in analyzing and visualizing real-time sensor data

WCN is a user-friendly dashboard to support coaches in monitoring their athletes during indoor cycling, and is able to capture, analyze and visualize sensor data. The dashboard is extensible with different modules such as signal-strength (RSSI) based zone localization, PACE body battery and so on.

The main goals are:

  • To use all available ANT+ enabled sensors of the athletes (power, cadence, heart rate,…) and capture them in different zones on the track using off-the-shelf hardware.
  • To develop an innovative signal strength-based methodology to perform localization.
  • To build tools to automatically detect and evaluate specific events (e.g. madison change) and identify outliers.

→ More info on WCN:

Apart from the projects that originated within their research group, Sports Data Science offers support to other projects as well, regarding sports data analytics and data collection optimization.

PACE: A tool that quantifies the energetic reserve capacity of the body during exercise

PACE is an algorithm/tool that quantifies the energetic reserve capacity of the body during exercise. Individuals performing exercise obtain real-time feedback on their energetic balance. PACE integrates data registered during training (power output/speed or heart rate) and matches these data to the individual exercise capacity.

Many recreational cyclists participate in organized events and in doing so, they are often forced to perform close to their limits. They often do not know the physiological limits of their body and consequently don’t know how to pace their ride, resulting in exhaustion before reaching the finish line. This project is done in collaboration with the exercise physiology and training team of Prof. Jan Boone.

→ More info on PACE:

If you’re interested in one or more of these projects, want to have access to the IP or just want to plan a chat with the teams behind, let us know by leaving a message at our Contact page.

Related Posts

No results found.