Search for: All records

The advancement of 3D modeling applications in various domains has been significantly propelled by innovations in 3D computer vision models. However, the efficacy of these models, particularly in large-scale 3D reconstruction, depends on the quality and coverage of the viewpoints. This paper addresses optimizing the trajectory of an unmanned aerial vehicle (UAV) to collect optimal Next-Best View (NBV) for 3D reconstruction models. Unlike traditional methods that rely on predefined criteria or continuous tracking of the 3D model’s development, our approach leverages reinforcement learning to select the NBV based solely on single camera images and the relative positions of the UAV with the reference points to a target. The UAV is positioned with respect to four reference waypoints at the structure’s corners, maintaining its orientation (field of view) towards the structure. Our approach removes the need for constant monitoring of 3D reconstruction accuracy during policy learning, ultimately boosting both the efficiency and autonomy of the data collection process. The implications of this research extend to applications in inspection, surveillance, and mapping, where optimal viewpoint selection is crucial for information gain and operational efficiency.