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

Alexandra Kapp, Edith Hoffmann, Esther Weigmann, Helena Mihaljević
9/27/2024
cs.CV

No official code found. Best implementation: SurfaceAI/road_network_classification (9 stars, CC-BY-SA-4.0, last commit 2025-04-29).

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.

View on arXivView PDF

Code Implementations(1)

SurfaceAI/road_network_classificationCommunity100%
CC-BY-SA-4.0
93Python, PLpgSQLMar 4, 20241 years agoCC-BY-SA-4.0

Similar Papers

StreetSurfaceVis: a dataset of crowdsourced street-level imagery annotated by road surface type and quality

89% match1 repo52024

Paved or unpaved? A Deep Learning derived Road Surface Global Dataset from Mapillary Street-View Imagery

85% match2024

Shape Your Ground: Refining Road Surfaces Beyond Planar Representations

83% match2025

The changing surface of the world's roads

83% match2025

Multiple data sources and domain generalization learning method for road surface defect classification

82% match2024

Fuzzy-Logic and Deep Learning for Environmental Condition-Aware Road Surface Classification

82% match2025

Cite this paper

@article{kapp2024surfaceai,
  title  = {SurfaceAI: Automated creation of cohesive road surface quality datasets based on open street-level imagery},
  author = {Alexandra Kapp and Edith Hoffmann and Esther Weigmann and Helena Mihaljević},
  year   = {2024},
  eprint = {2409.18922},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.18922v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.18922.svg)](https://codeofpaper.com/paper/2409.18922)

Discussion