Urban scene reconstruction method and device based on mass data

Abstract

The invention discloses an urban scene reconstruction method and device based on mass data. The method comprises the following steps: acquiring urban outdoor scene point cloud data; according to the point cloud data, dividing outdoor scenes into two categories of buildings and non-buildings, and dividing the buildings into two subcategories of building main bodies and building accessory structures; for a building main body structure, using a reconstruction technology based on low-rank matrix recovery and curved surface fitting to realize reconstruction of a building main body under missing data; for the building accessory structures, using a reconstruction technology based on symmetric pattern recognition to obtain three-dimensional models of all the accessory structures; for a non-building, finding a model template most similar to an object in a pre-constructed non-building model library based on a deep learning method, and using a template component deformation method for modeling; and finally, combining the obtained three types of models to obtain a city outdoor scene model. According to the invention, rapid reconstruction of the urban three-dimensional model can be realized.

Description

technical field [0001] The present invention relates to a three-dimensional reconstruction technology of urban outdoor scenes, and more particularly relates to a method and device for urban scene reconstruction based on massive data. Background technique [0002] In the information age, cities are not only the center of national politics, economy, military, transportation, energy, and commerce, but also the center of science, technology, culture, and information. Accurate 3D models of cities can be used in many fields such as urban planning, disaster monitoring, and smart cities. [0003] In recent years, with the advancement of data acquisition technology and the improvement of data production capacity, large-scale tilt data, 3D terrain, laser point cloud and other real-scene 3D data have been more and more widely used in the construction of smart cities and the protection of digital historical and cultural heritage. In areas such as restoration and restoration, building i...

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: The purpose of the present invention is to provide a method for urban scene reconstruction based on massive data, to solve the problem of low processing efficiency due to the large amount of urban three-dimensional real scene data, to repair the missing three-dimensional real scene data, and to realize the fast reconstruction of urban outdoor scenes with massive data. Construct

Images