This repository contains a Streamlit application designed for efficient evacuation planning in stadiums. It leverages advanced algorithms, image processing, and AI to provide personalized evacuation routes based on user location and specific requirements.
- Interactive Mapping: Utilizes Dijkstra's algorithm for optimal evacuation routes.
- Node and Edge Extraction: Processes stadium maps to extract key points and paths.
- Evacuation Time Estimation: Calculates times based on pedestrian types and walking speeds.
- Multilingual Voice Guidance: Offers text-to-speech conversion and supports multiple languages.
- AI-Generated Route Descriptions: Uses OpenAI's GPT-3.5-turbo for tailored evacuation instructions.
- Streamlit
- Pandas & NetworkX
- Pillow (PIL Fork)
- gTTS & googletrans
- OpenAI API
- Python-Dotenv
-
Clone the repository: git clone https://github.com/pozapas/EvacAIDi.git
-
Install dependencies: pip install -r requirements.txt
-
Run the application: streamlit run app.py
- Agent-based simulation for realistic wayfinding.
- More naturalistic voice synthesis.
- Expansion of the chatbot system.
- Advanced map navigation features.
- Incorporation of Building Information Modeling (BIM).
- Pedestrian behavior models in simulations.
Contributions, issues, and feature requests are welcome. Feel free to check issues page for open issues or open a new issue.
Distributed under the MIT License. See LICENSE for more information.