Sidewalk extraction using aerial and street view images

Huan Ning, Xinyue Ye, Zhihui Chen, Tao Liu, Tianzhi Cao

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

A reliable, punctual, and spatially accurate dataset of sidewalks is vital for identifying where improvements can be made upon urban environment to enhance multi-modal accessibility, social cohesion, and residents' physical activity. This paper develops a synthetically new spatial procedure to extract the sidewalk by integrating the detected results from aerial and street view imagery. We first train neural networks to extract sidewalks from aerial images, and then use pre-trained models to restore occluded and missing sidewalks from street view images. By combining the results from both data sources, a complete network of sidewalks can be produced. Our case study includes four counties in the U.S., and both precision and recall reach about 0.9. The street view imagery helps restore the occluded sidewalks and largely enhances the sidewalk network's connectivity by linking 20% of dangles.

Original languageEnglish (US)
JournalEnvironment and Planning B: Urban Analytics and City Science
DOIs
StateAccepted/In press - 2021
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Architecture
  • Geography, Planning and Development
  • Urban Studies
  • Nature and Landscape Conservation
  • Management, Monitoring, Policy and Law

Keywords

  • Sidewalk
  • aerial imagery
  • deep learning
  • street view imagery

Fingerprint

Dive into the research topics of 'Sidewalk extraction using aerial and street view images'. Together they form a unique fingerprint.

Cite this