3D model reconstruction migration method and system based on graph model

Abstract

The present invention provides a three-dimensional model reconstruction and migration method and system based on a graph model to collect data, including aerial photography by means of unmanned aerial vehicles to obtain high-quality target building pictures; establishing a three-dimensional model library, including matching based on key point features The point cloud registration method, the 3D point cloud reconstruction of the collected data, the 3D models of multiple buildings are reconstructed, and finally the 3D model library is established; the semantic information processing includes the keyword extraction method based on the graph model, and the input Automatically extract the text information, and finally extract the key semantic information, the key semantic information includes the name, layer number, shape and orientation information of the 3D model; search for the corresponding 3D model, including searching and matching the target basic style in the 3D model library The 3D building model; 3D model migration, including the migration of the matched 3D model through key semantic information, to obtain the required target 3D model.

Description

technical field [0001] The invention belongs to the field of three-dimensional reconstruction, and in particular relates to a method and system for reconstructing and transferring a three-dimensional model based on a graph model. Background technique [0002] In recent years, with the development of 3D model acquisition technology, computer graphics and computer network technology, the rapid acquisition of 3D spatial information has played an increasingly important role in the fields of resource environment, land use, 3D reconstruction of buildings, and natural disasters. The traditional acquisition of 3D space information mainly relies on spaceborne, airborne and ground measurements, etc., and there are common problems such as high acquisition cost, long results cycle, and low time resolution. Because UAVs have the advantages of flying under the cloud, flexible data collection, low cost, strong timeliness, and reducing the danger of field operators, the 3D reconstruction me...

AI Technical Summary

Problems solved by technology

The algorithm based on statistical probability discretizes the space, uses the probability density function to estimate the distribution of point clouds, and obtains the transformation matrix between two point clouds through optimization techniques. Typical algorithms include multi-layer NDT (ML— NDT), Accelerated Coherent Point Drift Algorithm (ACPD), etc., but for large-scale point clouds, the computational complexity of probability-based algorithms is high

Images