Real-Time Deep Learning-Driven Surveillance with Spatiotemporal Feature Extraction for Detection of Anomalous Human Behavior Across Dynamic Environments
Madhuri Pangavhane, Rahul Patil, Rajesh D. Bharati, Deepak Kumar Gupta, Prashant Ahire, Pramod Patil, Wasudeo Rahane, Deepak Sudhakar Dharrao · International Journal of Safety and Security Engineering · 2025
Nowadays continuous monitoring of public and private environments through Closed-Circuit Television (CCTV) is at peak attention.The identification and reporting of suspected human activity is crucial for the safety and security of the individuals and their belongings.Many researchers have provided numerous solutions for automated activity monitoring with CCTV and machine learning applications.But these models are struggling to provide high accuracy with real-time detection and triggering alert systems in a dynamic environment.The proposed model addresses these issues with a combined approach of convolutional and recurrent neural networks (Inception V3 and Bidirectional Long Short-Term Memory (BiLSTM)) with an attention mechanism to classify videos.This proposed model uses the strength of the Inception V3 network to extract spatial features from video frames, and the BiLSTM network processes these features in a timedependent manner to the identification of suspicious human activities.Also, the attention mechanism added to proposed system to focuses on the most significant spatiotemporal variables for violence detection.This deep learning model is designed to extract spatiotemporal features and thus can extract complex patterns in human motion robustly.This model is trained with publicly available dataset to analyze the performance with accuracy in a dynamic environment.The proposed deep-learning model effectively identifies and categorizes numerous suspicious behaviors in real-time by scrutinizing video sequences.The performance analysis proves that the proposed model efficiently detects activities like loitering, aggressive behavior, and unauthorized access.This automated surveillance system strengthens security in homes as well as other public and private environments.