United States Department of Transportation
i
Combining Crowdsourcing and Machine Learning to Collect Sidewalk Accessibility Data at Scale
-
2021-06-09
[PDF-2.65 MB]
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Final Report, May 2019 - 2021
-
Corporate Publisher:
-
Abstract:The authors are developing new data collection approaches that use a combination of remote crowdsourcing, machine learning, and online map imagery. Their newest effort, called Project Sidewalk, enables online crowdworkers to remotely label pedestrian-related accessibility problems by virtually walking through city streets in Google Street View. In 2019, the authors completed an 18-month deployment in Washington, D.C.: 1,150+ users provided over 200,000 geo-located sidewalk accessibility labels and audited 3,000 miles of D.C. streets. With simple quality control mechanisms, the authors found that minimally trained remote crowd workers could find and label 92 percent of accessibility problems in street view scenes, including missing curb ramps, obstacles in the path, surface problems, and missing sidewalks. For their PacTrans project, the authors proposed three threads of additional work. (1) First, the authors are deploying Project Sidewalk into three more cities, including two in the Pacific Northwest: Seattle, Washington, and Newberg, Oregon, to enable them to study and compare sidewalk accessibility factors across cities. (2) Second, to further scale their approach, the authors proposed new methods to automatically identify and classify sidewalk problems using deep learning techniques, which would be uniquely enabled by their large dataset. (3) Finally, the authors proposed new sidewalk accessibility models and interactive visualization tools to give stakeholders—from citizens to transit authorities—new understanding of their city’s accessibility.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
