A team of researchers from Mass Eye and Ear has developed a micro-navigation smartphone app that effectively aids blind and visually impaired individuals in finding bus stops. In a recent study published in Translational Vision Science & Technology, the app, known as All_Aboard, was found to have a significantly higher success rate than Google Maps.
While current GPS systems provide macro-navigation for planning routes that involve public transportation, micro-navigation remains a challenge for individuals who are blind or visually impaired. The precise location of bus stops and destinations can be difficult to determine accurately using GPS-based localization. To address this issue, the researchers developed All_Aboard, a mobile app that works in conjunction with mainstream GPS systems to enhance micro-navigation.
The app is designed to be opened when a user is nearing their destination, as indicated by the GPS. All_Aboard utilizes the smartphone’s camera to detect street signs from a distance of 30 to 50 feet. Auditory cues are then used to guide the user towards their destination, with the frequency of the sounds changing as they get closer to the endpoint.
Powered by artificial intelligence, the app utilizes a deep learning neural network trained on approximately 10,000 images of bus stops collected from various cities and regions. Currently, the app can recognize bus stops in 10 major cities/regions around the world.
In the study, 24 blind or visually impaired individuals used All_Aboard in conjunction with Google Maps to navigate a route that included 10 bus stops in both urban (Boston) and suburban (Newton, Mass.) areas. The success rate and localization error of the app were assessed and compared to those of Google Maps.
Localization error, or gap distance, refers to the distance between the desired destination and the marked endpoint on the maps. The success rate of localization indicates the likelihood of getting close enough to the bus stops. The researchers found that in both urban and suburban areas, All_Aboard had a success rate of 93%, while Google Maps only had a 52% success rate. The average gap distance with Google Maps was 6.62 meters, compared to 1.54 meters with All_Aboard.
Surprisingly, the low performance of Google Maps in Newton, Mass. was unexpected, as GPS accuracy is expected to be acceptable in suburban areas. Previous research by the team suggests that this problem may be attributed to errors in the mapping data for bus stop locations in Google Maps.
Dr. Gang Luo of the Schepens Eye Research Institute of Mass Eye and Ear highlighted the positive implications of the All_Aboard app. “Our findings suggest that the All_Aboard app could help travelers with visual impairments in navigation by accurately detecting the bus stop, and therefore greatly reducing their chance of missing buses due to standing too far from the bus stops,” said Dr. Luo. He also emphasized that computer vision-based object recognition capabilities can complement and enhance mapping-based macro-navigation services in real-world settings.
The development of the All_Aboard app demonstrates the potential of technology to improve accessibility and enhance the daily lives of individuals with visual impairments. By effectively aiding blind and visually impaired commuters in finding bus stops, the app empowers these individuals to navigate public transportation more independently and with greater confidence.
*Note:
1. Source: Coherent Market Insights, Public sources, Desk research
2. We have leveraged AI tools to mine information and compile it
