An effective model for bus door detection for the visually challenged

Visually impaired individuals are increasing worldwide, and as per the world statistics, around 39 million are blind, and 246 million are affected by low vision. This rate is also increasing in India, and as per the latest reviews, over 5 million visually challenged people are present. The authors performed a survey of some critical problems the visually challenged people faced in India from the Centre for Visually Challenged (CVC) School established by UVSM Hospitals. Among the major problems identified by the survey, most of these persons prefer to carry out their tasks independently, and they depend on public transport buses for navigation. However, the critical sub-problems being faced include; identification of bus door and accurately identifying the bus number to route them. This article aims to provide solutions in helping the visually challenged individuals to identify the exact bus that takes them to their destination, its door, bus number, and the path to board the bus. Here, a video sequence of the current scenario would be sent to the mobile, in which the actual processing of the image is carried out. After the video sequence processing, the generated output is a voice message that specifies the bus's location, door, and exact information of the bus number along the road path directly to the user using a wireless device. It aims to be one of the low-cost solutions.