Advanced AI-Powered Car Brand Detection System

A sophisticated web application that uses YOLOv11 deep learning model to detect and identify car brands from images with high accuracy. Features a modern cyberpunk-themed interface and real-time AI processing.

• 🤖 Advanced AI Model: YOLOv11 Medium architecture with 87.4% mAP50 accuracy
• 🎯 18 Car Brands: Supports major automotive brands including BMW, Mercedes, Toyota, Tesla, and more
• ⚡ Real-time Detection: Lightning-fast inference (~100ms processing time)
• 🎨 Modern Interface: Cyberpunk-themed responsive web design
• 📱 Cross-Platform: Works on desktop, tablet, and mobile devices
• 🖼️ Advanced Features: Drag & drop upload, bounding box visualization, full-screen viewer
• 🔧 RESTful API: Complete backend API for integration with other applications

• Python 3.8 or higher
• Modern web browser
• 4GB+ RAM recommended

1. Clone the repository

   git clone https://github.com/everyoneexe/CarBrandsAI.git
   cd CarBrandsAI

2. Install dependencies

   pip install -r requirements.txt

3. Run the application

   ./start.sh

4. Open in browser

   • Web Interface: http://localhost:8080
   • API Endpoint: http://localhost:5000

Total: 18 Brands with continuous expansion planned.

1. Upload Image: Drag & drop or click to select a car image
2. Analyze: Click "Markayı Bul" button to start AI detection
3. View Results: See detected brand, confidence score, and bounding box
4. Full Screen: Use "Tam Ekran Görüntüle" for detailed view
5. Save Results: Download annotated image or copy JSON data

POST /api/detect
Content-Type: multipart/form-data

{
  "image": <file>
}

Response:

{
  "brand": "BMW",
  "confidence": 0.92,
  "latency": "0.15s",
  "box": {
    "x": 120,
    "y": 80,
    "w": 160,
    "h": 160
  },
  "model_info": {
    "name": "CarBrandsAI YOLOv11m",
    "version": "V5",
    "accuracy": "87.4% mAP50"
  }
}

• GET / - Health check
• GET /api/brands - List supported brands
• GET /api/model-info - Model specifications

• Framework: Vanilla JavaScript (ES6+)
• Styling: Advanced CSS3 with animations
• Features: Canvas API for visualization, Fetch API for backend communication
• Theme: Cyberpunk-inspired design with particle effects

• Framework: Flask (Python)
• AI Model: YOLOv11 Medium (Ultralytics)
• Computer Vision: OpenCV for image processing
• APIs: RESTful design with CORS support

• Architecture: YOLOv11 Medium
• Training Dataset: 12,000+ labeled car images
• Accuracy: 87.4% mAP50
• Input Resolution: 640x640 pixels
• Training Epochs: 35 epochs with optimized hyperparameters
• Inference Time: ~100ms (CPU), ~50ms (GPU)

CarBrandsAI/
├── 🌐 Frontend
│   ├── index.html          # Main web interface
│   └── app.js              # JavaScript application logic
├── 🤖 Backend
│   ├── backend.py          # Flask API server
│   ├── requirements.txt    # Python dependencies
│   └── start.sh            # Quick start script
├── 🧠 AI Model
│   └── model/
│       └── best.pt         # Trained YOLOv11 model
└── 📚 Documentation
    ├── README.md           # This file
    └── START.md            # Quick start guide

• mAP50: 87.4% (Mean Average Precision at IoU 0.5)
• Precision: 89%
• Recall: 85%
• Model Size: ~45MB
• Memory Usage: ~2GB RAM during inference

• JPEG (.jpg, .jpeg)
• PNG (.png)
• WebP (.webp)
• Maximum file size: 16MB

• Chrome 80+
• Firefox 75+
• Safari 13+
• Edge 80+

1. Clone and enter directory

   git clone https://github.com/everyoneexe/CarBrandsAI.git
   cd CarBrandsAI

2. Install dependencies

   pip install -r requirements.txt

3. Run backend only

   python3 backend.py

4. Run frontend only

   python3 -m http.server 8080

# Test health endpoint
curl http://localhost:5000/

# Test brand detection
curl -X POST -F "image=@test_car.jpg" http://localhost:5000/api/detect

# Get supported brands
curl http://localhost:5000/api/brands

Backend fails to start

# Check if model file exists
ls -la model/best.pt

# Verify Python dependencies
pip install -r requirements.txt --force-reinstall

Port already in use

# Find and kill process using port 5000
lsof -i :5000
kill -9 <PID>

Model loading errors

• Ensure model/best.pt exists and is not corrupted
• Check available memory (requires 2GB+ RAM)
• Verify PyTorch installation

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

• Follow PEP 8 for Python code
• Use meaningful commit messages
• Add tests for new features
• Update documentation as needed

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

• Ultralytics for the YOLOv11 framework
• OpenCV for computer vision utilities
• Flask for the lightweight web framework
• Car manufacturers for inspiring this project

• Mobile App: React Native application
• Video Processing: Real-time video analysis
• More Brands: Expand to 50+ car brands
• Cloud Deployment: AWS/Azure integration
• API Authentication: Secure API access
• Batch Processing: Multiple image analysis

• GitHub Issues: Report bugs or request features
• Discussions: Community discussions

Made with ❤️ and AI by everyoneexe

"Advancing automotive AI, one detection at a time."