<![CDATA[This study presents the development and implementation of a real-time human detection and counting system using the YOLOv11 deep learning algorithm. The system is designed to automatically monitor and analyze human flow within a campus environment as part of a Smart Campus initiative. A dataset of 1,000 human images obtained from Kaggle was used for model training, and data labeling was performed manually using the Roboflow platform. The YOLOv11 model was trained for 100 epochs with a batch size of 32 on a Google Colab T4 GPU. The proposed method integrates the YOLOv11 object detection framework with a centroid-based tracking algorithm and an in–out counting mechanism to determine directional human movement in real time. Experimental results show that the model achieved strong detection performance, with precision = 0.88, recall = 0.78, and mAP@0.5 = 0.87. The confusion matrix analysis demonstrated that 84% of actual human objects were correctly detected, while real-time video testing achieved stable tracking and reliable counting accuracy under different lighting and crowd conditions. Overall, the proposed YOLOv11-based system provides an effective, accurate, and robust solution for real-time human detection and flow monitoring, supporting the development of intelligent surveillance and Smart Campus applications.]]>
Copyrights © 2025
