SurfaceAI: Automated creation of cohesive road surface quality datasets based on open street-level imagery

TL;DR

SurfaceAI is a pipeline that automatically creates detailed, georeferenced datasets on road surface type and quality using open street-level imagery, aiding infrastructure analysis and safety improvements.

Contribution

It introduces a novel method for generating comprehensive road surface datasets from crowdsourced imagery, filling a critical data gap for infrastructure modeling.

Findings

Successfully predicts road surface type and quality from street-level images

Provides cohesive, georeferenced datasets for entire road segments

Enhances infrastructure safety and planning through detailed surface data

Abstract

This paper introduces SurfaceAI, a pipeline designed to generate comprehensive georeferenced datasets on road surface type and quality from openly available street-level imagery. The motivation stems from the significant impact of road unevenness on the safety and comfort of traffic participants, especially vulnerable road users, emphasizing the need for detailed road surface data in infrastructure modeling and analysis. SurfaceAI addresses this gap by leveraging crowdsourced Mapillary data to train models that predict the type and quality of road surfaces visible in street-level images, which are then aggregated to provide cohesive information on entire road segment conditions.