Researchers at NYU’s Tandon School of Engineering and Grossman School of Medicine have created an app to help people with visual impairments navigate New York City’s subway system. Commute Booster uses a smartphone camera to recognize relevant signs along a transit route, guiding the user to their destination while ignoring nonessential signs and posters.
Commute Booster is designed for the “middle mile,” where passengers trawl through turnstiles, busy passageways and terminals to stay on the correct route. The app combines general transit feed specification (GTFS), a standardized and publicly available database about public transportation routes, with optical character recognition (OCR) to interpret signs and guide the user accordingly. “By integrating these two components, Commute Booster provides real-time feedback to users regarding the presence or absence of relevant navigation signs within the field of view of their phone camera during their journey,” an NYU press release published today reads.
A study that used the app on three NYC stations — Jay Street-Metrotech, Dekalb Avenue and Canal Street — had a 97 percent success rate in identifying the relevant signs needed to reach a mock destination. It managed to “read” the signs at a distance and from various angles expected from a typical commute.
“The ‘middle mile’ often involves negotiating a complex network of underground corridors, ticket booths and subway platforms. It can be treacherous for people who cannot rely on sight,” said John-Ross Rizzo, MD, an NYU professor (and co-author of the paper) known for his engineering work that helps people with disabilities. “Most GPS-enabled navigation apps address ‘first’ and ‘last’ miles only, so they fall short of meeting the needs of blind or low-vision commuters. Commute Booster is meant to fill that gap.”
Next is a planned human subject study to see how well the app holds up in real-world navigation scenarios. After that, the researchers hope to make it available for public use “in the near term.” Commute Booster is a simple smartphone app using a modern handset’s standard sensors, but that means users need to hold their phones’ cameras up as they navigate New York’s subway system — still well worth it, but less than an ideal setup. One can easily imagine this or a similar app running on AR smartglasses if or when they ever find broader consumer appeal. (Some companies have already tried.)