Enabling a New Data Science for Urban Accessibility for All
Previously, the research team received PacTrans funding for Project Sidewalk, which combines crowdsourcing, machine learning, and online imagery to transform how sidewalk accessibility data is collected. With Sidewalk, online crowdworkers label and assess sidewalk accessibility by virtually walking through city streets using Google Street View (GSV) [4]—similar to a first-person video game. Labels are used to create new urban accessibility visualizations, inform government policy and funding decisions, and to to train deep learning networks to assess sidewalks automatically—further scaling our approach [5]. Thus far, the users have contributed over 425,000 geo-located sidewalk accessibility labels across seven deployment cities, including two in the Pacific Northwest (Seattle, WA and Newberg, OR) and two international deployments . To the team's knowledge, this is the largest open sidewalk accessibility dataset ever collected and both [4] and [5] were recognized with Best Paper Awards, demonstrating research impact. Leveraging this data, the team now proposes new data science research for urban accessibility, focusing on: (1) What are the geo-spatial patterns and key correlates of urban accessibility? (2) How do sidewalk patterns compare across cities? (3) How does urban accessibility change over time?
Language
- English
Project
- Status: Completed
- Funding: $80000
-
Contract Numbers:
69A355174110
-
Sponsor Organizations:
Pacific Northwest Transportation Consortium
University of Washington
More Hall Room 112
Seattle, WA United States 98195-2700Office of the Assistant Secretary for Research and Technology
University Transportation Centers Program
Department of Transportation
Washington, DC United States 20590 -
Managing Organizations:
University of Washington, Seattle
Civil and Environmental Engineering Department
201 More Hall, Box 352700
Seattle, WA United States 98195-2700 -
Project Managers:
Froehlich, Jon
-
Performing Organizations:
University of Washington, Seattle
Civil and Environmental Engineering Department
201 More Hall, Box 352700
Seattle, WA United States 98195-2700 -
Principal Investigators:
Froehlich, Jon
Caspi, Anat
- Start Date: 20210316
- Expected Completion Date: 20220315
- Actual Completion Date: 0
- USDOT Program: University Transportation Centers Program
Subject/Index Terms
- TRT Terms: Accessibility; Data analysis; Sidewalks; Spatial analysis; Urban areas
- Subject Areas: Data and Information Technology; Safety and Human Factors; Society; Transportation (General);
Filing Info
- Accession Number: 01784887
- Record Type: Research project
- Source Agency: Pacific Northwest Transportation Consortium
- Contract Numbers: 69A355174110
- Files: UTC, RIP
- Created Date: Oct 17 2021 7:53AM