<![CDATA[The YOLOv8 algorithm for the license plate detection system of vehicles entering the integrated parking lot of Universitas Negeri Yogyakarta (UNY) needs to be evaluated because license plate detection is crucial in integrated parking management to improve the security and efficiency of parking lot usage. YOLOv8, as a deep learning-based object detection algorithm, was chosen to improve the accuracy and speed of detection. This research combines the YOLOv8 approach with a dataset specifically designed for the context of UNY parking lots. The testing process was conducted using the required hardware and software to ensure the algorithm's ability to adapt to the real environment. In addition, the performance of YOLOv8 in detecting vehicle license plates under different vehicle license plate conditions, such as black plates or white plates, was also evaluated. The results show that YOLOv8 is able to provide adequate vehicle license plate detection results. This research contributes to give development result of a vehicle license plate detection system for parking management by utilizing the latest object detection technology, as well as providing an overview of the challenges and solutions for implementation of this algorithm in the specific context of UNY parking lots.]]>
Copyrights © 2024
