An AI-Driven Risk-Aware Navigation Framework for Visually Impaired Individuals Beyond Conventional Object Detection
Authors
Assistant Professor, Department of Computer science, Shri Shankarlal Sundarbai Shasun Jain College for Women, Chennai, India (India)
Student, Department of Computer Science, Shri Shankarlal Sundarbai Shasun Jain College for Women,Chennai, India (India)
Student, Department of Computer Science, Shri Shankarlal Sundarbai Shasun Jain College for Women,Chennai, India (India)
Article Information
DOI: 10.51583/IJLTEMAS.2026.151000069
Subject Category: Artificial Intelligence
Volume/Issue: 15/10 | Page No: 834-839
Publication Timeline
Submitted: 2026-10-22
Accepted: 2026-10-27
Published: 2026-11-07
Abstract
Visually impaired people may face difficulties while navigating unfamiliar environments because they cannot directly observe surrounding obstacles and objects. This paper presents VisionMate, a smartphone-based accessibility assistant that provides environmental awareness through computer vision and voice interaction. The system combines real-time object detection, spatial analysis, motion tracking, and risk assessment to generate concise navigation instructions. A lightweight YOLOv8n model in ONNX format is executed on the device using ONNX Runtime. VisionMate also provides an interactive feature, Ask VisionMate, which allows users to ask questions about the current camera view through voice input. The captured image and question are processed using a FastAPI backend and Gemini multimodal AI, and the response is converted into speech. The proposed system combines continuous local obstacle awareness with interactive scene understanding in a single mobile application.
Keywords
Assistive Technology, Computer Vision, Object Detection, Visually Impaired, YOLOv8, Risk-Aware Navigation, Multimodal AI.
This article is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Downloads
References
1. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788. [Google Scholar] [Crossref]
2. G. Jocher, A. Chaurasia, and J. Qiu, “Ultralytics YOLO,” 2023. [Google Scholar] [Crossref]
3. “Enhancing Object Detection in Assistive Technology for the Visually Impaired: A DETR-Based Approach,” IEEE Access, vol. 13, pp. 71647–71661, 2025. [Google Scholar] [Crossref]
4. “Navigation Using Object Detection for Visually Impaired Individuals,” in Proc. 12th Int. Conf. Computing for Sustainable Global Development (INDIACom), 2025. [Google Scholar] [Crossref]
5. Flutter, “Camera Plugin Documentation,” Flutter Documentation. [Google Scholar] [Crossref]
6. Google, “Gemini API Documentation,” Google AI for Developers. [Google Scholar] [Crossref]
7. ONNX Runtime, “ONNX Runtime Mobile Documentation,” Microsoft. [Google Scholar] [Crossref]
Metrics
Views & Downloads
Similar Articles
- Impact of AI Tools on Student Learning
- Repogent: An Autonomous Multi-Agent System for End-To-End Repository Maintenance
- Trust-Centric Federated Learning Using Blockchain-Enabled Smart Contracts: An Analysis of Data Privacy, Model Integrity, and Decentralized AI Governance
- Can AI Care? Rethinking Ethics, Clinical Integrity, and Professional Responsibility in the Digital Age of Mental Healthcare
- AI-Based Smart Irrigation System Using IoT and Machine Learning for Precision Agriculture
This work is licensed under CC BY 4.0