Enhanced obstacle detection using bilateral vision-aided transformer neural network for visually impaired persons

Alarood, Ala Abdulsalam and Atoum, Mohammed Salem and Abdul Manaf, Azizah and Abubakar, Adamu and Alsmadi, Izzat (2025) Enhanced obstacle detection using bilateral vision-aided transformer neural network for visually impaired persons. Cluster Computing, 28 (997). pp. 1-23. ISSN 1386-7857 E-ISSN 1573-7543

Preview	PDF - Published Version Download (4MB) | Preview
Preview	PDF - Supplemental Material Download (154kB) | Preview
Preview	PDF - Supplemental Material Download (249kB) | Preview

Abstract

Obstacle detection remains vital in autonomous navigation and assistive technologies, especially for visually impaired individuals. This work introduces an enhanced obstacle detection framework based on a Bilateral Vision Transformer and Convolution Kernel Neural Network (BViT-CKNN). The system incorporates stereo vision data and applies a bilateral filter to reduce noise while preserving edge details. A Vision Transformer (ViT) model is then used for global feature extraction, and a Convolution Kernel Neural Network (CKNN) captures fine-grained local features. Evaluated using the COCO dataset, the proposed BViT-CKNN achieves superior performance in precision (0.93), recall (0.91), F1-score (0.92), and Mean Absolute Error (MAE) reduction (3.16%) compared to existing methods

Item Type:	Article (Journal)
Uncontrolled Keywords:	Visually impaired, Obstacle detection, Bilateral filter vision transformer, Convolution Kernel Neural Network
Subjects:	Q Science > Q Science (General) > Q300 Cybernetics > Q350 Information theory
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology > Department of Computer Science Kulliyyah of Information and Communication Technology > Department of Computer Science
Depositing User:	Dr Adamu Abubakar
Date Deposited:	27 Oct 2025 12:20
Last Modified:	27 Oct 2025 12:20
URI:	http://irep.iium.edu.my/id/eprint/123877

Actions (login required)

View Item