AI-powered luggage tracking and identification system using computer vision.

• Live Detection: Real-time luggage detection using webcam or video upload
• Smart Description: AI generates detailed descriptions of bags (color, brand, type, features)
• Semantic Search: Find your bag by describing it in natural language
• Status Tracking: Track bags from check-in to conveyor belt

• FastAPI - High-performance Python API
• Roboflow - Object detection (YOLO)
• BLIP - Image captioning and description
• CLIP - Semantic embeddings for similarity search
• Supabase - PostgreSQL database with pgvector

• Next.js 14 - React framework
• Tailwind CSS - Styling
• react-webcam - Live video capture

cd backend

# Create virtual environment
python -m venv venv

# Activate (Windows)
.\venv\Scripts\activate

# Activate (Mac/Linux)
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

# Copy env file and add your keys
copy .env.example .env
# Edit .env with your API keys

# Run server
uvicorn app.main:app --reload --port 8000

cd frontend

# Install dependencies
npm install

# Run development server
npm run dev

• Frontend: http://localhost:3000
• Backend API Docs: http://localhost:8000/docs

ROBOFLOW_API_KEY=your_key
SUPABASE_URL=your_url
SUPABASE_KEY=your_key
HF_TOKEN=your_token (optional)

NEXT_PUBLIC_API_URL=http://localhost:8000

Run this SQL in your Supabase SQL Editor:

CREATE EXTENSION IF NOT EXISTS vector;

CREATE TABLE bags (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    status TEXT CHECK (status IN ('CHECKIN', 'CONVEYOR')),
    description TEXT,
    color TEXT,
    brand TEXT,
    bag_type TEXT,
    size TEXT,
    features JSONB DEFAULT '[]',
    image_url TEXT,
    text_embedding vector(512),
    created_at TIMESTAMPTZ DEFAULT NOW()
);

CREATE INDEX ON bags USING ivfflat (text_embedding vector_cosine_ops) WITH (lists = 100);

CREATE OR REPLACE FUNCTION search_bags(query_embedding vector(512), match_count INT)
RETURNS SETOF bags AS $$
BEGIN
    RETURN QUERY
    SELECT *
    FROM bags
    ORDER BY text_embedding <=> query_embedding
    LIMIT match_count;
END;
$$ LANGUAGE plpgsql;

tamuhack26/
├── backend/
│   ├── app/
│   │   ├── main.py           # FastAPI app
│   │   ├── database.py       # Supabase client
│   │   ├── routers/          # API endpoints
│   │   ├── services/         # ML services
│   │   └── models/           # Pydantic models
│   └── requirements.txt
├── frontend/
│   ├── app/                  # Next.js pages
│   ├── components/           # React components
│   └── package.json
├── mockup.html               # Design mockup
└── README.md

MIT - Built for TAMUHack 2026