Spaces:
Running on Zero
Running on Zero
|
Download README.md from Robin7339/iris-visual-assistant: direct link, hf CLI and curl.
- Browser
- Download file 1.35 kB
-
https://huggingface.co/spaces/Robin7339/iris-visual-assistant/resolve/main/README.md
- Command line
-
hf download hf://spaces/Robin7339/iris-visual-assistant/README.md
-
curl -L -o README.md https://huggingface.co/spaces/Robin7339/iris-visual-assistant/resolve/main/README.md
1.35 kB
| title: IRIS Visual Navigation Assistant | |
| emoji: 👁️ | |
| colorFrom: indigo | |
| colorTo: purple | |
| sdk: gradio | |
| app_file: app.py | |
| pinned: false | |
| # IRIS — Intelligent Real-time Inference System for Visual Assistance | |
| IRIS is an AI-powered assistive navigation tool designed to help visually impaired individuals safely navigate indoor and outdoor spaces. | |
| ## ✨ Key Features | |
| - **Live Webcam Scanning**: Snap and analyze your real-time surroundings directly from your laptop or phone camera. | |
| - **Real-Time Object Detection**: Powered by Ultralytics YOLO11 (optimized for CPU/GPU inference). | |
| - **Directional Awareness**: Classifies obstacles into Left, Center (ahead), and Right navigation zones. | |
| - **Priority Engine**: Selects the single most crucial obstacle instruction, suppressing noise and information overload. | |
| - **Voice Guidance (TTS)**: Built-in natural audio warnings automatically spoken upon scene analysis. | |
| - **Video & Image Uploads**: Full-frame annotated previews and step-by-step navigational breakdown. | |
| ## 🛠️ Tech Stack | |
| - **Framework**: Gradio (Hugging Face Spaces Native) | |
| - **Vision Model**: Ultralytics YOLO11 | |
| - **Speech Engine**: gTTS (Google Text-to-Speech) | |
| - **Computer Vision**: OpenCV, NumPy | |
| ## 💻 Local Quickstart | |
| ```bash | |
| pip install -r requirements.txt | |
| python app.py | |
| ``` | |
| Open the local URL displayed in the terminal. | |