PhD Proposal: Scalable Methods to Collect and Visualize Sidewalk Accessibility Data for People with Mobility Impairment

Talk
Kotaro Hara
Time: 
02.26.2015 16:30 to 18:00
Location: 

AVW 4172

Poorly maintained sidewalks pose considerable accessibility challenges for people with mobility impairment. Despite comprehensive civil rights legislation for Americans with disabilities, many city streets and sidewalks in the U.S. remain inaccessible. The problem is not just that sidewalk accessibility fundamentally affects where and how people travel in cities, but also that there are few, if any, mechanisms to determine accessible areas of a city a priori.
To address this problem, my Ph.D. dissertation introduces new scalable methods for collecting data about street-level accessibility using a combination of crowdsourcing, automated methods, and Google Street View (GSV) as well as proof-of-concept map-based accessibility applications that leverage this data. My dissertation has four research threads: (i) a formative study with people with mobility impairments, (ii) development and evaluation of scalable crowdsourced accessibility data collection methods/tools, (iii) design of systems that combine crowdsourcing and automated methods to increase data collection efficiency, and (iv) implementation a proof-of-2 concept tool that visualize (in)accessible areas of a city to demonstrate the value of the collected data.
My work thus far has focused on the design and evaluation of data collection methods and tools-threads (ii) and (iii) above. My work has shown that paid crowd workers recruited from an online labor market can find and label accessibility attributes in GSV with accuracy of 81%. This accuracy improves to 93% with simple quality control mechanisms such as majority vote. I have further shown that by combining crowdsourcing and automated methods, I can increase data collection efficiency by 13% without sacrificing accuracy.
Building on the above, I propose the following research. First, I will conduct a formative study with 15-20 participants with mobility impairment. Second, I will extend the crowdsourced data collection methods with volunteer contributions to increase its efficiency, and study behaviors of volunteers. Finally, I will create and evaluate a proof-of-concept visualization tool for street-level accessibility.
My dissertation will contribute to the HCI community by: (i) extending the knowledge of how people with mobility impairments interact with technology to navigate through cities; (ii) introducing the first work that demonstrates that GSV is a viable source for learning about the accessibility of the physical world; (iii) introducing the first method that combines crowdsourcing and automated methods to remotely collect accessibility information; (iv) deploying interactive web tools that allow people to help establish the largest dataset about street-level accessibility of the world; and (v) presenting and evaluating accessibility-aware map-tools that empower people with mobility impairments.
Examining Committee:
Committee Chair: - Dr. Jon Froehlich
Dept's Representative - Dr. David Jacobs
Committee Member: - Dr. Ben Bederson