FALCON 🦅

Fall Alert Landslide Condition Observation Network

A full-stack application for rockfall prediction, risk analysis, and route optimization using drone imagery and machine learning. This was my Smart India Hackathon (SIH) project where I contributed in developing the backend infrastructure and the crack segmentation model using computer vision techniques.

View Architecture Features

⚡ Quick Start

# Install dependencies
npm run install:all

# Start development servers
npm run dev

# Access Points:
Frontend: http://localhost:5173
Backend: http://localhost:8000
API Docs: http://localhost:8000/docs

🏗️ Architecture

Project Structure

FALCON/
├── frontend/ # React + TypeScript Frontend
│ ├── src/
│ │ ├── components/
│ │ │ ├── PredictionWorkflow/
│ │ │ │ ├── DataInjection.tsx # File upload & data input
│ │ │ │ ├── ModelPredicting.tsx # ML model execution
│ │ │ │ └── RockfallForecast.tsx # Results visualization
│ │ │ ├── AuthModal.tsx # Authentication system
│ │ │ ├── Dashboard.tsx # Main control center
│ │ │ ├── InteractiveMapNew.tsx # Map visualization
│ │ │ ├── Navigation.tsx # Top navigation bar
│ │ │ ├── OptimizedRoute.tsx # Route planning
│ │ │ ├── RiskAnalysisPanel.tsx # Risk assessment display
│ │ │ ├── LeftSidebar.js # Dashboard sidebar
│ │ │ ├── RightSidebar.js # Dashboard controls
│ │ │ └── SimpleMap.tsx # Basic map component
│ │ ├── services/
│ │ │ └── api.ts # API service layer
│ │ ├── lib/
│ │ │ ├── completeAuth.ts # Authentication logic
│ │ │ └── firebaseConfig.ts # Firebase configuration
│ │ ├── App.tsx # Main application component
│ │ ├── main.tsx # Application entry point
│ │ └── index.css # Global styles
│ ├── public/
│ │ ├── falcon-logo.png # Application logo
│ │ └── index.html # HTML template
│ ├── vite.config.ts # Vite build configuration
│ ├── tailwind.config.js # Tailwind CSS configuration
│ ├── tsconfig.json # TypeScript configuration
│ └── package.json # Frontend dependencies
├── backend/ # FastAPI Python Backend
│ ├── main.py # FastAPI application & endpoints
│ ├── models/ # ML Model files
│ │ ├── weather_pipeline.pkl # Weather prediction model
│ │ ├── crack_segmentation.h5 # Crack detection model
│ │ └── DEM.pkl # Digital Elevation Model
│ ├── weather_processor.py # Weather analysis module
│ ├── crack_segmentation.py # Crack detection module
│ ├── dem_processor.py # DEM analysis module
│ ├── requirements.txt # Python dependencies
│ └── .env # Environment variables
├── package.json # Root development scripts
└── README.md # Project documentation

System Architecture

Frontend Layer (React + TypeScript)

  • Component-Based Architecture: Modular React components with TypeScript
  • State Management: React hooks and context for global state
  • Styling: Tailwind CSS with glassmorphism design patterns
  • Routing: Client-side routing for SPA experience
  • API Integration: Axios-based service layer for backend communication

Backend Layer (FastAPI + Python)

  • RESTful API: FastAPI framework with automatic OpenAPI documentation
  • ML Pipeline: Multi-model prediction system with three specialized models
  • Data Processing: File upload handling for drone images and elevation data
  • Authentication: JWT-based user authentication system
  • CORS Configuration: Cross-origin resource sharing for frontend integration

Machine Learning Pipeline

  • Weather Model: Meteorological risk assessment
  • Crack Segmentation: Computer vision for structural analysis
  • DEM Analysis: Topographical and geological risk evaluation
Data Input → Preprocessing → Multi-Model Analysis → Risk Averaging → Results

🚀 Features

Frontend

  • Interactive dashboard with real-time monitoring
  • Risk analysis panel with severity mapping
  • Route optimization with interactive maps
  • Prediction workflow (Data Injection → Model Prediction → Results)
  • Authentication system with glassmorphism design

Backend

  • RESTful API with auto-documentation
  • ML model integration (Weather, Crack Segmentation, DEM)
  • Multi-model risk assessment with averaging
  • File upload for drone images and DEM data
  • Real-time data processing

🛠️ Tech Stack

React 18 TypeScript Vite Tailwind CSS FastAPI Python 3.8+ Machine Learning Computer Vision OpenCV Firebase

🔧 Commands

npm run dev
Start both servers
npm run dev:frontend
Frontend only
npm run dev:backend
Backend only
npm run build
Build for production
npm run install:all
Install all dependencies

📚 Key API Endpoints

POST /api/comprehensive-analysis # Multi-model risk analysis
POST /api/auth/login # User authentication
GET /api/monitoring/live-data # Real-time monitoring

🚀 Deployment

Frontend:

cd frontend
npm run dev

Backend:

cd backend
pip install -r requirements.txt
uvicorn main:app --host 0.0.0.0 --port 8000 --reload

FALCON Command Center - Advanced geospatial analysis for safer navigation 🦅

Made with ❤️ by Lakshya Tripathi