- This project is a Navigation Assistant that helps users navigate their surroundings.
- The system captures an image, sends it to an LLM like Gemini for processing, receives navigation instructions, and provides them as audio output using text-to-speech (TTS).
-
Image Capture
Utilizes the Raspberry Pi camera to capture real-time images. -
Vision Processing
Integrates with a vision model API to analyze captured images and extract useful navigation information. -
Voice Navigation
Converts navigation instructions into speech using Google Text-to-Speech (gTTS) for audible guidance. -
Audio Output
Plays voice instructions to assist the user in real-time. -
GPS Tracking
Continuously tracks the user's location using GPS. -
Emergency Alert
Includes an emergency button that, when pressed, sends the user's live location to their guardian via email.