A team of researchers from Mass Eye and Ear has developed a smartphone app called "All_Aboard" to assist individuals who are blind or visually impaired (BVI) in finding their bus stops. The app focuses on improving micro-navigation, which involves finding the exact locations of bus stops and destinations. It aims to complement mainstream GPS systems, which provide macro-navigation for planning routes using public transportation .
The All_Aboard app utilises the phone's camera to detect street signs from a distance of 30 to 50 feet. It then provides auditory cues to guide the user towards their destination, with the frequency of the sounds changing as they approach the bus stop. The app is powered by artificial intelligence, using a deep learning neural network trained on approximately 10,000 images of bus stops collected in various cities and regions around the world .
A recent study evaluated the effectiveness of the All_Aboard app compared to Google Maps in helping BVI individuals navigate a set route with 10 bus stops in both urban (Boston) and suburban (Newton, Mass.) locations. The study measured the localization error (gap distance) and the rate of successful localisation. The researchers found that the All_Aboard app had a success rate of 93 percent, while Google Maps had a success rate of 52 percent. Additionally, the average gap distance with Google Maps was 6.62 meters, compared to 1.54 meters with All_Aboard .
“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 Gang Luo, of the Schepens Eye Research Institute of Mass Eye and Ear. “This study indicates that computer vision-based object recognition capabilities can be used in a complementary way and provide added benefit to purely mapping-based, macro-navigation services in real-world settings.
The study's findings suggest that the All_Aboard app could greatly assist travellers with visual impairments in accurately detecting bus stops, reducing the chance of missing buses due to standing too far away from the stops. The app's computer vision-based object recognition capabilities provide added benefits to mapping-based macro-navigation services in real-world settings.