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

TL;DR

This study provides global data insights derived from maps and statistics about spatial distribution of Mapillary coverage and road pavedness on a continent and countries scale, with rural and urban distinction.

Abstract

We have released an open dataset with global coverage on road surface characteristics (paved or unpaved) derived utilising 105 million images from the world's largest crowdsourcing-based street view platform, Mapillary, leveraging state-of-the-art geospatial AI methods. We propose a hybrid deep learning approach which combines SWIN-Transformer based road surface prediction and CLIP-and-DL segmentation based thresholding for filtering of bad quality images. The road surface prediction results have been matched and integrated with OpenStreetMap (OSM) road geometries. This study provides global data insights derived from maps and statistics about spatial distribution of Mapillary coverage and road pavedness on a continent and countries scale, with rural and urban distinction. This dataset expands the availability of global road surface information by over 3 million kilometers, now representing approximately 36% of the total length of the global road network. Most regions showed moderate to high paved road coverage (60-80%), but significant gaps were noted in specific areas of Africa and Asia. Urban areas tend to have near-complete paved coverage, while rural regions display more variability. Model validation against OSM surface data achieved strong performance, with F1 scores for paved roads between 91-97% across continents. Taking forward the work of Mapillary and their contributors and enrichment of OSM road attributes, our work provides valuable insights for applications in urban planning, disaster routing, logistics optimisation and addresses various Sustainable Development Goals (SDGS): especially SDGs 1 (No poverty), 3 (Good health and well-being), 8 (Decent work and economic growth), 9 (Industry, Innovation and Infrastructure), 11 (Sustainable cities and communities), 12 (Responsible consumption and production), and 13 (Climate action).

Figures (16)

• Figure 1: Flow chart of the presented approach.
• Figure 2: Map visualizations of road sequence data from various global urban areas. Each panel displays sequences that have been color-coded where possible, although the high volume of sequences in areas such as Tokyo and Moscow prevents distinct color coding. The different colors observed in sequences from San Francisco and Paris indicate various sequences; however, due to the limited color palette, a single color may represent multiple sequences.
• Figure 3: Comparison of Mapillary-OSM assignments from Sendai, Japan. Red lines correspond to the shortest lines to all OSM segments within 30 meters. The left sub-figure (a) shows examples were some image points are assigned to multiple OSM segments, particularly near intersections. The right sub-figure (b) shows examples for misallignments in non urban settings. OpenStreetMap is used as basemap for both sub-figures.
• Figure 4: Examples of filtered images that did not contain any road using the CLIP model.
• Figure 5: Visualization of road surface classification. Warmer colors (red, orange, and yellow) denote higher intensity activation levels, whereas cooler colors (e.g., blue and green) denote lower activation levels.