Can a Parking System Be Smarter Than Humans? Designing a Secure IoTBased System with QR Code and YOLO

This dataset accompanies the study “Can a Parking System Be Smarter Than Humans? Designing a Secure IoT-Based System with QR Code and YOLO”, conducted by Tamaris Roulina Silitonga from Politeknik Negeri Batam, Indonesia. The research focuses on developing and testing a secure, intelligent parking system that integrates YOLOv8 for license plate recognition, Optical Character Recognition (OCR), QR code authentication, and IoT-based automated gate control into a unified architecture.

The system was designed to address limitations in traditional parking management—such as manual data entry, human error, and low operational efficiency—by combining deep learning and IoT technologies for automation, reliability, and security. The dataset and documentation include performance results, architecture diagrams, and implementation details of the developed modules:

License Plate Detection Module using YOLOv8 and PaddleOCR.

QR Code Authentication Module employing GM66 QR scanner as a fallback mechanism.

IoT-Based Gate Control using ESP32 microcontroller and RESTful API for automated barrier operation.

Laravel-Based Web Dashboard for real-time monitoring, data management, and reporting.

Experimental evaluations were conducted in a simulated parking environment, achieving:

100% success rate in automated barrier control.

9–10 seconds average response time for license plate recognition.

3–5 seconds response time for QR code validation.

These results demonstrate the system’s reliability and potential scalability for real-world deployment in smart city infrastructures. The dataset can be used as a foundation for further research in IoT automation, computer vision, and intelligent transportation systems, and may assist researchers or developers aiming to enhance smart parking, security automation, or urban mobility solutions.