Enabling a New Data Science for Urban Accessibility for All

PI: Jon Froehlich (UW), jonf@cs.washington.edu, ORCID: 0000-0001-8291-3353

Co PIs: Anat Caspi

AMOUNT & MATCH: $40,000 from PacTrans; $40,000 Match

PERFORMANCE PERIOD: 3/16/2021 – 3/15/2022

STATUS: Completed

CATEGORIES: Accessibility, Pedestrian Safety, Crowd Sourcing, Machine Learning

RESEARCH PROJECT HOT SHEET:

UTC PROJECT DOCUMENTATION:

FINAL PROJECT REPORT:

PROJECT DATA:

DESCRIPTION: In this proposal, we aim to leverage Project Sidewalk’s unique cross-regional sidewalk dataset to investigate the following research questions via new data analytics and visualization tools:

  • What are the geo-spatial patterns and key correlates of urban accessibility? How does accessible infrastructure correspond to racial and socioeconomic factors or other metrics such as house pricing, school ratings, park density, and transit access.? Who appears to be primarily impacted?
  • How do sidewalk patterns compare across cities? What are the main accessibility barriers and how can/should we categorize them? How do these barriers reflect the socio-cultural, economic, and political context of those regions?
  • How does urban accessibility change over time? We propose adapting our crowdsourcing + machine learning techniques to examine street scene imagery across time, which will enable new temporal analyses focused on how and where sidewalks and sidewalk accessibility change over time.
DELIVERABLE DUE DATE DATE RECEIVED
Research Project Progress Report #1 10/10/2021 10/14/2021
Research Project Progress Report #2 4/10/2022 N/A
Research Project Progress Report #3 10/10/2022 N/A
No Cost Extension Request 1/15/2022
Draft Report 1/15/2022 8/1/2022
Final Project Report 3/15/2022 12/1/2022