A tool to predict unsafe situations in a cycling race.
COURSE is a tool that collects unstructured incident tweets from cycling-related Twitter 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.
Following characteristics are taken into account in the course evaluation: stage hardness, bunch sprint & finish speed prediction, presence of descending lines, roundabouts & traffic furniture, changes in road type & road quality, and more.
Over the last years, the team of Prof. Steven Verstockt (UGent-imec, IDLab) has been involved in several sports-related projects/proposals to share their expertise on spatio-temporal datacollection, filtering, classification, enrichment, mapping, and visualization.
In response to several serious accidents in cycling, the International Cycling Union (UCI) wants to introduce a series of measures to make cycling safer. The UCI is counting on data-driven solutions from the research team at Ghent University through a new dashboard.
- Detection: Organizers can detect the potential safety risks of the race course
- Advise: UCI can advise organizers on what safety measures should be taken.
- Clean data: A structured dataset is built that indicates the most common causes and the time-space distribution of incidents.
- Implement: providing support in applying the tool during the preparation of particular race events.
- Finetune: learn and create smarter algorithms, making it possible to accurately estimate cycling accident risks.
- Prevent: accidents & injuries Keep riders healthy and safe throughout the full season.