FMCW Radar for Human Detection in Collapsed Structures for Post-Disaster Search and Rescue

Disasters such as earthquakes, landslides, building collapses, and wars can leave people trapped in rubble, which makes rapid and accurate detection significant for successful rescue operations. Traditional search methods, such as visual inspection and thermal imaging, often struggle in complex environments where victims may be obscured. However, ensuring reliable detection remains a challenge, particularly due to visual obstruction and complex rubble scenarios. In this paper, a Frequency Modulated Continuous Wave (FMCW) radar is used to enhance victim detection. The 24 GHz FMCW radar used in this work, offers superior penetration through rubble, making it applicable for locating victims even when obstructed by collapsed structures. In our envisioned scenario, we integrate a down-looking radar with Unmanned Aerial Vehicles (UAVs) into the system. UAVs equipped with FMCW radar sensors can fly over or around collapsed structures, offering a bird's-eye view of the scene and the ability to cover a wider area more rapidly than ground-based teams. In addition, signal processing techniques are applied to filter out the noise and retain the necessary information from the signals. This preprocessing step is essential to improve the accuracy and reliability of Machine Learning (ML) models, enabling them to better identify and interpret signs of human presence in a complex environment.