Design and Development of Human Identification and Obstacle Detection System for Blind Using Machine Learning

According to the World Health Organization (WHO) estimates that the millions of people worldwide suffer from visual impairment, whether partial or complete, which makes it challenging for them to detect obstacles and identify people around them. However, recent advancements in information technology and spatial cognition theory have created an opportunity for researchers and developers to explore innovative solutions that can empower visually impaired individuals, enhance inclusivity, and improve accessibility. To this end, a novel framework has been proposed that utilizes artificial vision, specifically an intelligent system based on a convolutional neural network (CNN) algorithm. This system automatically recognizes human and scene objects or obstacles in real-time, even in difficult situation with large moving object. The system provides the user with a complete information, including the position of located targets, and alerts the user via a voice message about obstaclesor known or unknown individuals. The proposed work aims to create a user-friendly technology that fulfills the essential needs of physically disabled individuals, providing them with an easy-to-use interface, convenience, portability, and cost-effectiveness. Ultimately, this approach enables blind users to navigate and manage indoor and outdoor locations that they may not have been aware of otherwise, enhancing their autonomy and quality of life.