Integrating Machine Learning for Behavior Recognition in Intelligent Surveillance Systems
Pogiri Deepika, Aarthi Radha T S, Krishnakumar Mahendran · 2025
The advancements in artificial intelligence (AI) and machine learning (ML) have profoundly impacted the intelligent surveillance field. Human-dependent traditional surveillance systems tend to be susceptible to mistakes owing to fatigue and cognitive overload. This contrasts with ML-driven surveillance systems that offer automatic behavior identification, anomaly detection, and real-time response systems, hence improved security and operational efficiency. This manuscript gives a thorough review of the methodologies of ML used in intelligent surveillance that aims at deep learning models including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers. It also discusses the incorporation of Internet of Things (IoT) and multi-sensor fusion in surveillance systems and their effect on accuracy and robustness. This study seeks to gain insightful experience into the changing dynamics of ML-based surveillance and its implications for security and privacy in the future.