Data Fusion of Cameras attached on Dual UAVs for Real-Time Human Detection and Localization

Abstract

Unmanned aerial vehicles (UAVs) are increasingly used in search and rescue operations due to their rapid deployment and wide-area coverage. However, many existing UAV-based systems focus mainly on victim detection and do not provide accurate geographic coordinates, which limits their usefulness in real rescue missions. In addition, detecting victims from aerial imagery remains challenging when targets appear as very small objects. This paper proposes a real-time dual UAV system for human detection and localization that integrates deep learning and geometric triangulation. Two UAVs equipped with cameras capture synchronized visual and telemetry data, which are transmitted to a ground processing server. A deep learning model based on YOLO is used to detect victims and guide semi-automatic camera alignment, while geometric triangulation and telemetry data from two independent UAVs are combined to estimate the victim’s GPS coordinates. The proposed system was evaluated through real-world field experiments. Experimental results show that the system achieves an average localization error of approximately 3.6 meters at an observation distance of about 150 meters, while maintaining real-time processing performance. These results demonstrate the feasibility of combining multi-UAV vision and geometric modeling to improve the effectiveness of UAV-assisted search and rescue operations.