Geometric Primitive-Guided UAV Path Planning for High-Quality Image-Based Reconstruction

Image-based refined 3D reconstruction relies on high-resolution and multi-angle images of scenes. The assistance multi-rotor drones gimbal provides great convenience for image acquisition. However, capturing with manual control generally takes a long time. It could easily lead to redundant or insufficient local area coverage, resulting in poor quality the reconstructed model. We propose surface geometric primitive-guided UAV path planning method (SGP-G) that aims automatically quickly plan collision-free capture fewer images, based which high-quality models can be obtained. primitives are extracted by plane segmentation proxy, performs three main functions. First, more representative evaluation reconstructability whole scene is realized. Second, two optimization strategies different executed generate near-global optimized set viewpoints. Third, regularly arranged viewpoints generated improve efficiency Experiments virtual real scenes demonstrate remarkable performance our method. Compared state art, we accomplish photographic higher relatively simple way, achieving equivalent even model images.