Disaster Response Survivor Detection System

A real-time aerial image analysis system that generates priority heatmaps for likely survivor zones in disaster scenarios. The system processes satellite and drone imagery to identify areas with high probability of human presence, considering building damage, accessibility, and temporal factors.

Features

• Multi-Sensor Integration: Processes both satellite and drone imagery
• Real-time Mapping: Supports both batch and streaming image processing
• Priority Heatmap Generation: Outputs likelihood scores for survivor zones
• Explainable AI Layers:
  • Building damage assessment
  • Accessibility analysis
  • Human-presence proxies
  • Time since last coverage analysis
• Dynamic Resource Allocation: Supports path planning and resource optimization

System Architecture

Input Images → Preprocessing → Feature Extraction → Multi-Layer Analysis → Heatmap Generation → Output
     ↓              ↓              ↓                    ↓                    ↓
Satellite/Drone → Normalization → CNN/Transformer → Damage/Access/Human → Priority Map

Quick Start

1. Install dependencies:

pip install -r requirements.txt

2. Run the system:

python main.py --input_path /path/to/images --output_path /path/to/output

3. For streaming mode:

python main.py --stream --input_source /path/to/stream --real_time

Project Structure

prober/
├── src/                    # Source code
│   ├── preprocessing/      # Image preprocessing modules
│   ├── models/            # ML models for analysis
│   ├── analysis/          # Core analysis modules
│   ├── visualization/     # Heatmap and visualization
│   └── utils/             # Utility functions
├── data/                  # Sample data and models
├── tests/                 # Unit and integration tests
├── config/                # Configuration files
├── docs/                  # Documentation
└── examples/              # Example scripts and notebooks

Contributing

Please read our Contributing Guidelines before submitting pull requests.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citation

If you use this system in your research, please cite:

@software{disaster_survivor_detection,
  title={Disaster Response Survivor Detection System},
  author={Team Probe},
  year={2025},
  url={https://github.com/mashcodes10/teamprober}
}