ARTIFICIAL INTELLIGENCE ALGORITHMS FOR ANALYZING CROWD FLOWS AND DETECTING SUSPICIOUS ACTIVITIES IN PUBLIC SPACES

Abstract

The rapid growth of urban populations and increasing use of public spaces
have highlighted the need for efficient crowd monitoring and security management.
This study explores the application of artificial intelligence (AI) algorithms for
analyzing crowd flows and detecting suspicious activities in real-time. AI-based
methods, including computer vision, deep learning, and anomaly detection
techniques, are employed to process video data from surveillance systems. The
research focuses on identifying unusual movement patterns, abnormal behaviors,
and potential safety threats within densely populated areas. Experimental results
demonstrate that AI algorithms can accurately detect anomalies and provide timely
alerts, improving public safety and optimizing crowd management strategies. The
study also discusses challenges related to data privacy, computational efficiency,
and system scalability, offering practical recommendations for real-world
implementation.