A Visual Servo Capture Control Strategy for UAVs Targeting in Emergency Rescue Scenarios

This paper proposes an image-based visual servoing control algorithm for air-to-ground UAV flight control, specifically tailored for emergency rescue scenarios. The controller is designed using a PD control strategy, while target detection is performed using the YOLOv5s object detector. A monocular camera is employed to identify the target and obtain its positional information in both the image coordinate system and the camera coordinate system. By regulating the relative position between the UAV and the target, the controller enables the UAV to precisely descend and hover above the target, facilitating further capture operation.