Project Sidewalk: Mapping Accessibility through Google Street View

May 15, 2018 12:30pm to 1:00pm

project sidewalk logo12:30 - 1PM Eastern

Presented by TransCen, Inc. and the Mid-Atlantic ADA Center

This is a 30 minute session.

Google Maps, Waze, and Yelp have transformed the way people travel and access information about the physical world. While these systems contain terabytes of data about roads and points of interest (POIs), their information about physical accessibility is commensurately poor. New websites such as AXSmap, WheelMap, and AccessTogether aim to address this problem by collecting location-based accessibility information provided by volunteers (i.e., crowdsourcing). While these efforts are important and commendable, their value propositions are intrinsically tied to the amount and quality of provided data--and prior work has found that they suffer from serious data sparseness issues. In contrast, a team from the University of Maryland and the University of Washington is exploring a complementary approach called Project Sidewalk where volunteer users *virtually* walk through cities in Google Street View to label and assess sidewalk accessibility--a bit like a first-person video game. So, rather than pulling solely from a local population, the potential pool of users scales to anyone with an Internet connection and a web browser. Since Project Sidewalk's beta launch in Washington DC in Fall 2016, over 3,000 users have contributed 180,000 accessibility labels across 1,075 miles of DC streets, check out preliminary results. The collected data is shared with city governments and used to develop new accessibility-friendly mapping tools (e.g., route planners for people in wheelchairs, new types of map visualizations of access), to train machine learning algorithms to automatically assess accessibility, and to create better transparency about accessible infrastructure (imagine a WalkScore for sidewalk accessibility!).

Presenter: Jon Froehlich is an Associate Professor in the Paul G. Allen School of Computer Science and Engineering at the University of Washington.

  • This webinar will be presented via the Blackboard Collaborate Web Conferencing platform.
  • Real-time captioning will be availble through the webinar platform.
  • A telephone conference option will also available should you choose not to use the webinar platform.
  • Information on accessing the webinar platform and the telephone conference number will be provided prior to the session.

First time Blackboard Collaborate Web Conferencing System V12.6 users:
For more information on pre-configuring your computer for use with Blackboard Collaborate, please visit the First Time Users page.  We recommend you do this well in advance of the session to allow for any necessary troubleshooting.  Depending on your organizational policies you may need the assistance of your IT Staff if firewalls prevent you from downloading files. If you plan to log into the on-line webinar system to view the presentation, access captioning and/or submit questions it is important that you follow the instructions for checking your computer system to ensure that it is configured correctly and you have the necessary software to access the webinar platform.
Screen Reader Users: Individuals who are using Screen Reader Software should review the instructions and information available in the Accessibility Guide for Blackboard Collaborate Web Conferencing prior to the session.


Mapping Accessibility through Google Street View - One slide per page - Handout

Mapping Accessibility through Google Street View - Two slides per page - Handout

Mapping Accessibility through Google Street View - Three slides per page - Handout