Quick Info
Project Date
Jan. 1, 2013 - Oct. 8, 2014
Sponsors:
NSF
Keywords:
crowdsourcing accessibility,
computer vision,
google streetview,
urban accessibility
About

A workflow diagram depicting Tohme’s four main sub-systems.
Tohme uses machine learning to predict the quality of computer vision output and routes work accordingly.
Publications
Tohme: Detecting Curb Ramps in Google Street View Using Crowdsourcing, Computer Vision, and Machine Learning
Proceedings of UIST 2014
PDF | doi | Citation | Project Sidewalk • Tohme
An Initial Study of Automatic Curb Ramp Detection with Crowdsourced Verification using Google Street View Images
Poster Proceedings of HCOMP 2013
PDF | doi | Citation | Project Sidewalk • Tohme
Exploring Early Solutions for Automatically Identifying Inaccessible Sidewalks in the Physical World using Google Street View
HCIC2013 Workshop
PDF | Citation | Project Sidewalk • Tohme