Smartphone Navigation Aid for Visually Impaired Users

Abstract

Navigation is a critical challenge faced by people with visual impairment, often limiting their independence and safety in unfamiliar environments. This paper presents Aurora, a novel deep learning-based smartphone navigation assistant designed specifically to aid visually impaired users in real-time navigation and obstacle avoidance. Aurora leverages convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to accurately interpret visual data captured through a smartphone camera, enabling robust scene understanding and path planning. The system integrates semantic segmentation to detect sidewalks, pedestrian crossings, obstacles, and signage, while simultaneously providing audio and haptic feedback to guide users safely and efficiently. In this study, we detail the architecture of Aurora, including the dataset preparation, model training, and optimization techniques applied to ensure real-time performance on mobile devices. The assistant also incorporates GPS data and inertial sensors to enhance localization accuracy and context awareness. Extensive experiments were conducted under various environmental conditions to validate the system’s effectiveness, achieving a high accuracy rate in obstacle detection and route guidance. Aurora’s user-centric design includes customizable feedback modes to cater to different user preferences and needs, ensuring accessibility and ease of use. This paper further discusses the usability evaluation involving visually impaired participants, highlighting improvements in navigation confidence and reduction in travel time. The results demonstrate that Aurora can significantly improve independent mobility for visually impaired individuals.