Three-dimensional point cloud orientation correction method based on SFM

Abstract

The invention discloses a three-dimensional point cloud orientation correction method based on SFM, and the method comprises the steps: firstly judging whether a scene is single-flight-strip linear flight according to GPS coordinates, then judging whether the orientation of a three-dimensional point cloud is correct through an SFM result, and finally correcting the orientation of the three-dimensional point cloud according to the posture information of a camera. According to the three-dimensional point cloud orientation correction method based on the SFM, image attitude information is considered, the three-dimensional point cloud orientation is corrected, and the problem of errors of subsequently generated orthoimages due to the fact that the three-dimensional point cloud orientation is not considered is solved. Verification shows that the SFM result is corrected through the method, and the finally generated three-dimensional reconstruction result can meet the set requirements.

Description

technical field [0001] The invention belongs to the application field of unmanned aerial vehicle data, and in particular relates to an SFM-based three-dimensional point cloud orientation correction method. Background technique [0002] In recent years, UAVs have been widely used in the field of aerial survey and remote sensing. and monitoring have played an important role. However, the general UAV aerial image is a two-dimensional image, which lacks spatial information and cannot completely restore the three-dimensional scene information of the scene being photographed. Dimensional to 3D. [0003] The Structure From Motion (SFM) technology determines the spatial and geometric relationship of the target through the movement of the camera, which can be used to restore the 3D scene information of the aerial image of the UAV. Compared with other 3D reconstruction methods, the SFM method has lower cost, more automatic processing, and stronger scene applicability. Therefore, it...

AI Technical Summary

Problems solved by technology

[0004] In the application of large-scale scenes of UAVs, especially the scenes of straight-line flight with a single flight belt, due to the lack of constraints of 3D plane space, the reconstructed 3D scenes are often not facing the ground orthographically, which will lead to errors in the generation of orthophotos. The problem

I-shaped flight can avoid the above problems, but the workload of the flight will be greatly increased, and the flight cost will be greatly increased

Images