Field evaluation of a mobile app for assisting blind and visually impaired travelers to find bus stops
Shrinivas Pundlik, Prerana Shivshanker, Tim Traut-Savino, Gang Luo

TL;DR
This study evaluates the All_Aboard mobile app, which uses neural networks and audio feedback to help blind and visually impaired travelers locate bus stops more accurately than standard GPS-based apps.
Contribution
The paper introduces a real-time bus stop detection app for BVI users, demonstrating improved localization accuracy over Google Maps in real-world settings.
Findings
All_Aboard achieved a 91% success rate in locating bus stops.
All_Aboard's gap distance was significantly lower at 1.8 meters.
Google Maps had a success rate of 52% with a 7-meter gap.
Abstract
Purpose: It is reported that there can be considerable gaps due to GPS inaccuracy and mapping errors if blind and visually impaired (BVI) travelers rely on digital maps to go to their desired bus stops. We evaluated the ability of a mobile app, All_Aboard, to guide BVI travelers precisely to the bus-stops. Methods: The All_Aboard app detected bus-stop signs in real-time via smartphone camera using a neural network model, and provided distance coded audio feedback to help localize the detected sign. BVI individuals used the All_Aboard and Google Maps app to localize 10 bus-stop locations in Boston downtown and another 10 in a sub-urban area. For each bus stop, the subjects used the apps to navigate as close as possible to the physical bus-stop sign, starting from 30 to 50 meters away. The outcome measures were success rate and gap distance between the app-indicated location and the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTactile and Sensory Interactions · Traffic and Road Safety · Safety Warnings and Signage
