Towards Urban Public Safety: A Literature Review of Deep Learning Approaches for CCTV-based Violence Detection
Violence detection in video surveillance systems is a critical challenge for ensuring public safety in smart cities. This study presents a comprehensive analysis of deep learning architectures and transfer learning techniques for violence detection, evaluating their performance across benchmark datasets, including Hockey Fight, Movies, and UCF-Crime. ResNet50, MobileNetV2, ConvLSTM, DenseNet121, and Xception models are compared in terms of accuracy, computational efficiency, and real-world applicability. Results highlight ResNet50 as the most effective model, achievi