Multi-baseline SAR 3D reconstruction of vehicle from very sparse aspects: A generative adversarial network based approach

Research on target center elevation extraction method based on photogrammetric point cloud

“…Point cloud classification: according to K-Means clustering algorithm to distinguish between ground points and target point cloud; (4). Target center point calculation: take the average of the target point cloud coordinates as the center point coordinates and evaluate the accuracy; (5). Interval cyclic rejection threshold: repeat the above 2~4 process, based on the minimum root mean square error to determine the final center point elevation results.…”

“…In recent years, with the rapid development of photogrammetric technology, inclined photogrammetry has become one of the important means to obtain three-dimensional information on the ground surface [1,2]. Point cloud data generated by inclined photogrammetry is widely used in the fields of smart city [3], deformation monitoring [4], and natural resources investigation [5], etc., with the characteristics of rich information and high accuracy. As one of the main feature targets for point cloud identification, the accurate elevation information of the marking target is of great significance for surface change monitoring, engineering surveying [6].…”