Intelligent Assistance System for Visually Impaired/Blind People (ISVB)

Visual impairments pose a parsing need to develop new automated systems to assist persons presenting visual impairments. The visual impairments have trouble interacting and sensing their surroundings. Their movement is limited and has to rely on a guided stick for them to move safely from one place to another. However, traditional canes have the disadvantage of failing to detect far-away obstacles and small objects. Therefore, this project is proposed to design and develop an Intelligent Assistance System for Visually Impaired People (ISVB). Our proposed system is composed of three interconnected parts, a smart cap, a 3D-printed intelligent cane and a mobile application that connects the system through an online server. The smart cap uses the Raspberry Pi and camera module, along with a deep learning object detection module for obstacle detection. The intelligent cane will provide the feasibility for the visually impaired person to walk without encountering problems by analyzing the surrounding environment through a microcontroller with multiple sensors and a bluetooth module. The mobile application interacts with the cap and the cane. Additionally, it will provide virtual navigation to help visually impaired people in their movement. To evaluate the performance of the system, different experiments for object detection, sensors and mobile applications have been conducted. The overall performance of the model showed an efficiency of 94.6 %.