<![CDATA[Conventional car parking management systems still face challenges such as manual vehicle monitoring, limited real-time monitoring, and non-automatic parking access control. This study aims to develop an Internet of Things (IoT)-based smart parking system using ESP32-CAM and the YOLOv8n method to detect four-wheeled vehicles in real time. The developed system consists of ESP32CAM as an image acquisition device, a Python program as a processing center, YOLOv8n as an object detection model, EasyOCR for reading license plates, and MySQL as a storage medium for detection results. This system is also equipped with vehicle distance estimation features, LED flash control, and automatic gate control. Based on testing on 20 four-wheeled vehicle samples in a limited test environment, the system successfully detected all tested vehicles and no vehicle detection errors were found. The system was able to read vehicle license plates using EasyOCR and control automatic gates based on the detection results. However, the accuracy of driver detection and OCR decreased in night conditions, to 40% and 60%, respectively. In addition, the FPS dropped from 18 FPS in the morning to 11 FPS at night. These results indicate that the system is capable of supporting real-time vehicle monitoring and parking access control, although its performance is still affected by lighting conditions, image quality, and the limitations of the ESP32CAM camera.]]>
Copyrights © 2026
