Identifying safe intersection design through unsupervised feature extraction from satellite imagery

@article{Wijnands2020IdentifyingSI,
  title={Identifying safe intersection design through unsupervised feature extraction from satellite imagery},
  author={Jasper S. Wijnands and Haifeng Zhao and Kerry A. Nice and J. Thompson and Katherine Scully and Jingqiu Guo and Mark Stevenson},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.15343}
}
  • Jasper S. Wijnands, Haifeng Zhao, +4 authors Mark Stevenson
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • The World Health Organization has listed the design of safer intersections as a key intervention to reduce global road trauma. This article presents the first study to systematically analyze the design of all intersections in a large country, based on aerial imagery and deep learning. Approximately 900,000 satellite images were downloaded for all intersections in Australia and customized computer vision techniques emphasized the road infrastructure. A deep autoencoder extracted high-level… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 76 REFERENCES
    Combining Satellite Imagery and Open Data to Map Road Safety
    • 23
    Street smarts: measuring intercity road quality using deep learning on satellite imagery
    • 7
    • PDF
    Unsupervised Deep Learning to Explore Streetscape Factors Associated with Urban Cyclist Safety
    • 2
    Road Network Extraction and Intersection Detection From Aerial Images by Tracking Road Footprints
    • 279
    • PDF
    At the cross-roads: an on-road examination of driving errors at intersections.
    • 21
    Use of Satellite Imagery for Establishing Road Horizontal Alignments
    • 46
    • PDF
    Recent progress in road and lane detection: a survey
    • 531
    • PDF