An assistive vision system for visually impaired users that provides real-time audio narration of the surrounding environment.
The system is designed to run on portable, low-power edge hardware, enabling real-time processing without relying on constant cloud connectivity. This makes it practical for everyday use—lightweight enough to carry, fast enough to respond in real-time, and private by keeping visual data on-device.
- Raspberry Pi 5 (edge processing unit)
- USB Webcam (0.3MP, 640×480 @ 30 FPS)
- Speaker/Headphones (audio output)
- Internet connection (for cloud services)
- Real-time object detection
- Human motion recognition
- Natural language scene descriptions
- Audio feedback
All rights reserved.
© 2025-2026