Human Body Detection in Disaster Environments: A Review of Framework Design and Development Strategies

Abstract

The developments in intelligent systems and emerging technologies have greatly affected the disaster management processes by making the rescue operations quick, safe, and effective. Accuracy in detecting the human body in critical situations is crucial for minimizing response time and saving human lives. Various methods have been developed, including infrared and radar-based techniques, acoustic analysis, unmanned aerial vehicles, and robotics. These systems have been further enhanced with the incorporation of cloud computing, artificial intelligence (AI), and the Internet of Things (IoT), which enable real-time monitoring and decision-making, regardless of scale, as they can be easily deployed in changing, dynamic environments. In this study, deep learning (DL) frameworks and machine learning (ML) models have enhanced the accuracy of detection, particularly in complex or obstructed environments where conventional tools tend to fail. Combining dissimilar strategies for sensing creates a multimodal system, which is more reliable. The use of drones also expands to areas that are not accessible. A comprehensive review of existing approaches highlights the growing shift toward intelligent, adaptive, and cooperative frameworks in disaster response. This work emphasizes the importance of developing integrated detection technologies that not only improve efficiency and resilience but also contribute to sustainable and robust strategies for future disaster preparedness and management.