Vision Walk: AI-Driven Real-Time Visual Assistance System for Visually Impaired Navigation

Jitesh Sandesh Kadam, Vaibhav Vasant Joyashi and Waman R. Parulekar

International Journal of Scientific Research in Science and Technology, 2026, vol. 13, issue 3, 415-424

Abstract: Visually impaired individuals face significant chal-lenges in perceiving their surroundings, detecting obstacles, read-ing text, and navigating safely. Traditional aids like white canes offer limited tactile feedback and lack contextual information. This paper presents Vision Walk, an AI-driven real-time visual assistance system that combines YOLOv8 for object detection, Tesseract OCR for text recognition, and spatial reasoning within a Flask-based web framework. The system operates entirely through a mobile browser, requiring no installation, and de-livers natural-language audio descriptions with directional cues (left, center, right). Experiments demonstrate that Vision Walk achieves object detection inference times of 40–80 ms, OCR processing of 70–140 ms, and end-to-end latency of 120–250 ms, making it suitable for real-time navigation. A user study with 12 visually impaired participants shows significant improvement in environmental awareness and navigation confidence. The system’s browser-based architecture ensures platform independence and cost-effectiveness, presenting a scalable solution for assistive technology.

Keywords: Assistive Technology; Computer Vision; YOLOv8; Optical Character Recognition; Visually Impaired; Real-Time Systems; Web-Based Deployment; Flask (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrst.com/home/article/view/IJSRST26133160 Abstract page (text/html)
https://ijsrst.com/home/article/download/IJSRST26133160/IJSRST26133160 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:etm:ijsrst:v13:y2026:i3:id:1617

DOI: 10.32628/IJSRST26133160

Access Statistics for this article

More articles in International Journal of Scientific Research in Science and Technology from Technoscience Academy
Bibliographic data for series maintained by Pankaj Sharma ().