Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Alexandra Kapp, Edith Hoffmann, Esther Weigmann, Helena Mihaljević

TL;DR

This paper introduces SurfaceAI, a pipeline designed to generate comprehensive georeferenced datasets on road surface type and quality from openly available street-level imagery by leveraging crowdsourced Mapillary data to train models that predict the type and quality of road surfaces visible in street-level images.

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.

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

TL;DR

This paper introduces SurfaceAI, a pipeline designed to generate comprehensive georeferenced datasets on road surface type and quality from openly available street-level imagery by leveraging crowdsourced Mapillary data to train models that predict the type and quality of road surfaces visible in street-level images.

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.
Paper Structure (7 sections, 2 figures)

This paper contains 7 sections, 2 figures.

Table of Contents

  1. Introduction
  2. Proposed approach
  3. Street-level imagery
  4. Image classification models
  5. Aggregation algorithm
  6. Evaluation in real-world scenarios
  7. Limitation and discussion

Figures (2)

  • Figure 1: Schematic of the proposed pipeline from user input (geographic boundary) to model output (classified road network). Note that, for clarity, the diagram displays the aggregation algorithm for quality only.
  • Figure 2: Examples of clear and ambiguous road types. Images from Mapillary; contributor names and image IDs are indicated for each image.