Model Card for YOLOParkingDetection: Fine-Tuned YOLOv8 for Parking Spot Detection

YOLOParkingDetection is a deep learning model based on YOLOv8 (Ultralytics) and fine-tuned to detect parking spot availability in images.
It classifies each parking spot as either Empty or Occupied and outputs bounding boxes with labels for real-time monitoring.

This project showcases the power of transfer learning in adapting a general-purpose object detection model (trained on COCO) to a specialized use case for smart parking management systems.

⚠️ Disclaimer: This model is intended for research, educational, and demonstration purposes only. It should not be used in production environments without further testing and validation.

---

Model Details

Key Features:

• Object detection with bounding boxes for Empty and Occupied parking spots
• Fine-tuned from YOLOv8 pretrained weights (COCO dataset)
• Real-time performance (~10.7ms per image)
• High accuracy with robust metrics on test set

Skills & Technologies Used:

• Ultralytics YOLOv8 for object detection
• Transfer learning on custom parking dataset
• PyTorch backend with GPU acceleration
• Streamlit and Hugging Face Spaces for deployment

---

• Developed by: Rawan Alwadeya
• Model type: Object Detection (YOLOv8)
• Language(s): N/A (Image model)
• License: MIT

---

Uses

This model can be used for:

• Research on smart city solutions and AI-powered parking management
• Demonstrating transfer learning for object detection tasks
• Educational projects in computer vision and deep learning
• Real-time monitoring of parking availability in surveillance systems

---

Performance

The fine-tuned model achieved outstanding results on the test set:

• Precision: 99.39%
• Recall: 98.20%
• mAP@50: 98.73%
• mAP@50-95: 97.46%
• Speed: ~10.7ms per image

These results confirm the model’s strong ability to detect and classify parking spots in real-world scenarios.

---

👩‍💻 Author

Rawan Alwadeya
AI Engineer | Generative AI Engineer | Data Scientist

• 📧 Email: [email protected]
• 🌐 LinkedIn Profile

---

Example Usage

from ultralytics import YOLO
import cv2

# Load model from Hugging Face Hub
model = YOLO("RawanAlwadeya/YOLOParkingDetection")

# Run inference on an image
results = model("parking_lot_example.jpg")

# Visualize results
for r in results:
    im_array = r.plot()  # BGR image with predictions
    cv2.imshow("Parking Detection", im_array)
    cv2.waitKey(0)
    cv2.destroyAllWindows()