Road cycling safety scoring based on geospatial analysis, computer vision and machine learning

Abstract

Road cycling is a cycling discipline in which riders ride on public roads. Traffic calming measures are made to make public roads safer for everyday usage for all its users. However, these measures are not always yielding a safer cycling racecourse. In this paper we present a methodology that inspects the safety of roads tailored to road bicycle racing. The automated approach uses computer vision and geospatial analysis to give an indicative racecourse safety score based on collected, calculated and processed multimodal data. The current version of our workflow uses OpenStreetMap (OSM), turn detection and stage type / bunch sprint classification for the geospatial analysis and uses road segmentation and an extensible object detector that is currently trained to detect road cracks and imperfections for visual analysis. These features are used to create a mechanism that penalizes dangerous elements on the route based on the remaining distance and the generated penalties with its relative importance factors. This results in a comprehensive safety score along with a detailed breakdown of the most concerning passages on the course which can be used by race organizers and officials to help them in the iterative process to create an engaging, yet safe course for the riders.