详情

Enabling a New Data Science for Urban Accessibility for All

项目名称：	Enabling a New Data Science for Urban Accessibility for All
摘要：	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?
状态：	Active
资金：	80000
资助组织：	Pacific Northwest Transportation Consortium<==>Office of the Assistant Secretary for Research and Technology
项目负责人：	Froehlich, Jon
执行机构：	University of Washington, Seattle
开始时间：	20210316
预计完成日期：	20220315
主题领域：	Data and Information Technology；Safety and Human Factors；Society；Transportation (General)