<![CDATA[The rapid growth of urban populations has intensified the need for robust crowd monitoring systems to ensure public safety and efficient resource management. This study explores the integration of YOLOv11, an advanced real-time object detection model, for crowd counting and behavior analysis in dynamic environments. We propose a hybrid framework that leverages YOLOv11’s high-speed detection capabilities to identify individuals in densely packed scenes and extract behavioral cues such as motion patterns and group interactions. The model is fine-tuned on benchmark datasets to optimize accuracy in varying lighting and occlusion conditions. Experimental results demonstrate that our approach achieves a significant improvement in both counting precision and behavioral feature extraction compared to previous YOLO versions and other baseline models. This research highlights YOLOv11’s potential as a lightweight yet powerful solution for real-time crowd analytics, with applications ranging from smart surveillance to public event management.]]>
Copyrights © 2025
