Design and Implementation of an Embedded Real-Time System for Guiding Visually Impaired Individuals

Computer vision aims to provide computers with vision capabilities similar to humans. Humans use their eyes and their brains to see and understand the world and objects around them. For visually impaired individuals, these capabilities are lost or damaged in different degrees. Their eyes cannot discharge vision responsibilities. This paper aims to design and implement a portable system to help visually impaired individuals in perceiving objects and people around them and estimating their distance precisely. The proposed system uses a CNN-based real-time object detection technique called YOLO (You Look Only Once) with a single camera mounted on Raspberry Pi board. The system also estimates the distance of the detected objects and deliver these data to visually impaired person in audible form. The results show that the system can detect a person and predict his/her distance with 98.8% accuracy.