Assisting blind people with AI and audio using smart glasses: System design with YOLOv8 variants comparisons
Assisting blind people with AI and audio using smart glasses: System design with YOLOv8 variants comparisons
This paper introduces a novel system design leveraging Vuzix Blade 2 smart glasses to enhance the mobility and independence of visually impaired individuals. The study critically examines existing assistive navigation and object detection technologies, identifying their limitations and gaps. The designed system integrates real-time object detection, distance estimation, and OCR, providing auditory feedback through a robust, efficient pipeline. The designed application enhances the independence and safety of visually impaired individuals, particularly in navigating university campuses. A dataset comprising 15,951 annotated images from the university campus was used for training and evaluation. A comparative analysis of three YOLOv8 models (YOLOv8-N, YOLOv8-S, and YOLOv8-M) was conducted, balancing accuracy and computational efficiency to optimise system performance. The pipeline offers a scalable framework for inclusive AR and AI-based assistive systems. Results show high object detection accuracy (precision: 0.90, recall: 0.83). Distance estimation performance was validated using a geometric size–based calculation that relates pixel width to calibrated focal length and known real-world object dimensions, achieving an average absolute error of 0.33 m. Results demonstrate the system’s capability to detect obstacles within 1 meter, provide precise distance estimation, and convert text into speech, validating its potential for real-world applications. This study emphasises the significant role of AI-driven solutions in advancing assistive technologies, paving the way for more accessible and inclusive navigation systems. Compared with recent assistive systems such as Smart Cane, OrCam MyEye, and IrisVision), the proposed system demonstrates superior integration of detection, text recognition, and real-time feedback within a lightweight wearable device.
AR application, Assisted technology, Augmented reality, OCR, Object detection
Kumari, Priyanka
c01aa85c-67d3-4d62-8179-e28407fd822c
Hammady, Ramy
9d5ff940-2d85-44e7-b001-222ae2feb935
20 January 2026
Kumari, Priyanka
c01aa85c-67d3-4d62-8179-e28407fd822c
Hammady, Ramy
9d5ff940-2d85-44e7-b001-222ae2feb935
Kumari, Priyanka and Hammady, Ramy
(2026)
Assisting blind people with AI and audio using smart glasses: System design with YOLOv8 variants comparisons.
Multimedia Systems, 73 (1), [73].
(doi:10.1007/s00530-025-02139-z).
Abstract
This paper introduces a novel system design leveraging Vuzix Blade 2 smart glasses to enhance the mobility and independence of visually impaired individuals. The study critically examines existing assistive navigation and object detection technologies, identifying their limitations and gaps. The designed system integrates real-time object detection, distance estimation, and OCR, providing auditory feedback through a robust, efficient pipeline. The designed application enhances the independence and safety of visually impaired individuals, particularly in navigating university campuses. A dataset comprising 15,951 annotated images from the university campus was used for training and evaluation. A comparative analysis of three YOLOv8 models (YOLOv8-N, YOLOv8-S, and YOLOv8-M) was conducted, balancing accuracy and computational efficiency to optimise system performance. The pipeline offers a scalable framework for inclusive AR and AI-based assistive systems. Results show high object detection accuracy (precision: 0.90, recall: 0.83). Distance estimation performance was validated using a geometric size–based calculation that relates pixel width to calibrated focal length and known real-world object dimensions, achieving an average absolute error of 0.33 m. Results demonstrate the system’s capability to detect obstacles within 1 meter, provide precise distance estimation, and convert text into speech, validating its potential for real-world applications. This study emphasises the significant role of AI-driven solutions in advancing assistive technologies, paving the way for more accessible and inclusive navigation systems. Compared with recent assistive systems such as Smart Cane, OrCam MyEye, and IrisVision), the proposed system demonstrates superior integration of detection, text recognition, and real-time feedback within a lightweight wearable device.
Text
Manuscript
- Accepted Manuscript
Text
s00530-025-02139-z
- Version of Record
More information
Accepted/In Press date: 5 December 2025
e-pub ahead of print date: 20 January 2026
Published date: 20 January 2026
Keywords:
AR application, Assisted technology, Augmented reality, OCR, Object detection
Identifiers
Local EPrints ID: 508253
URI: http://eprints.soton.ac.uk/id/eprint/508253
ISSN: 0942-4962
PURE UUID: a3bacfa9-54e4-4c63-a6f5-7e7db686f41d
Catalogue record
Date deposited: 15 Jan 2026 17:43
Last modified: 29 Jan 2026 05:23
Export record
Altmetrics
Contributors
Author:
Priyanka Kumari
Author:
Ramy Hammady
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics