Real-Time Casualty Detection System Using CCTV Surveillance: A Deep Learning Approach

The use of CCTV cameras for surveillance has become widespread in contemporary years, and there is a demand for efficient and accurate real-time casualty detection system to ensure the safety of the public. Our paper proposes a deep learning-based approach for real-time casualty detection using CCTV surveillance. Our approach uses a Densenet121 model that is trained on a huge dataset of casualty images to detect 13 different types of casualties. The model achieved an AUC score of 0.88, demonstrating its high accuracy in detecting casualties. We evaluated our proposed method on a real-time CCTV surveillance dataset and demonstrated its effectiveness in detecting casualties in real-time. Our system can provide timely alerts to emergency responders, enabling them to quickly and effectively respond to incidents and save lives. The results of our study demonstrate the potential of deep learning-based methods for real-time casualty detection using CCTV surveillance, and the importance of such systems in ensuring public safety.