Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202558,
        author = {Muskan Jain and Muskan Jain and Mrunmayee Rahate},
        title = {Augmented Reality Navigation System for Visually Impaired Individuals},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {8659-8664},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202558},
        abstract = {In response to the global prevalence of visual im-pairment and the considerable disparity between the naviga-tion requirements of the visually impaired population and the functionalities offered by current assistive aids, we present an Augmented Reality Navigation System for Visually Impaired Individuals. This system combines the implementation of real-time obstacle recognition through the YOLOv8 deep learning architecture, zone-wise spatial evaluation, centroid object track-ing, predictive proximity estimation, and an audio navigation guidance module that offers instructions in both English and Hindi languages. The processing server is designed using the Python programming language with the Flask library to process frames sent by a Progressive Web Application (PWA) client installed on the mobile web browser. The system operates in two modes, namely Indoor and Outdoor. In outdoor mode, the system implements a hierarchical vehicle priority alert system based on estimated obstacle distance. State-wise announcements are used to reduce speech repetition of static objects with varying cooldown intervals between 0.8 and 3.0 seconds based on the criticality of the hazard. Evaluations through 18 test cases validated the correctness of the system implementation against all identified functional requirements.},
        keywords = {Augmented reality, assistive technology, YOLOv8, object detection, visually impaired, audio guidance, Progressive Web Application, centroid tracking, bilingual navigation.},
        month = {May},
        }