Developing an Interactive Machine Learning-based Approach for Sidewalk Digitalization

Active transportation modes, such as walking and biking, are key elements of sustainable transportation systems. Active traveling is advocated as a way to keep physical fitness, mitigate local streets congestion, and foster community livability. To favor the active mobility, extensive work has been focused on planning, maintaining and enhancing the infrastructure, such as sidewalks. A significant amount of the efforts has to go for the setup and maintenance of the sidewalk inventory on a certain geographic scale (e.g., citywide, statewide). Conventionally, researchers rely on laborious field survey to conduct sidewalk inventory. However, the existing methods are not considering the comprehensive sidewalk system nor cost-effective. To address the stated problem, it is proposed herein to develop an interactive machine learning based approach that can do the following: (1) extract the features of sidewalks; (2) classify sidewalks into five major categories, i.e., paved sidewalk, landscape/lawn, crosswalk, parking lot/driveway, and missing sidewalks; and (3) construct a large-scale connected sidewalk network in a time-efficient and cost-effective manner. The proposed method will take full advantage of available data sources (e.g., aerial and satellite images), and build on top of existing roadway network, to digitize sidewalk.


  • English


  • Status: Active
  • Sponsor Organizations:

    California Department of Transportation

    1227 O Street
    Sacramento, CA  United States  95843

    Office of the Assistant Secretary for Research and Technology

    University Transportation Centers Program
    Department of Transportation
    Washington, DC  United States  20590
  • Principal Investigators:

    Luo, Ji

  • Start Date: 20160701
  • Expected Completion Date: 20161030
  • Actual Completion Date: 0

Subject/Index Terms

Filing Info

  • Accession Number: 01610332
  • Record Type: Research project
  • Source Agency: National Center for Sustainable Transportation
  • Files: UTC, RiP
  • Created Date: Sep 6 2016 5:17PM