<![CDATA[Currently, technological advancements have led to the creation of various products that impact company performance. One of the products used in shopping malls is a monitoring application. A temporary closure occurred at one of the stores in a shopping mall due to a surge in visitors caused by a large discount offer. The manual methods currently in use are highly prone to errors. Knowing the number of people in a room is crucial for maintaining service quality. Information about the number of visitors is essential for companies to optimize resource utilization and conduct operational evaluations. This study aims to develop an application for counting the number of people in a room using the YOLOv8 (You Only Look Once) method. Model testing shows that an image size of 640x640 yields a higher mAP compared to the 416x416 size, achieving a precision of 79.6%, a recall of 61.7%, a mAP of 72.3%, and a f1-score of 69.52%. Accuracy testing for counting the number of people shows an accuracy rate of 82.67%.]]>
Copyrights © 2025
