Roof segmentation method, system and device based on multi-resolution three-dimensional statistical information

Abstract

The invention relates to the field of computer vision, in particular to a roof segmentation method, a system and a device based on multi-resolution three-dimensional statistical information, aiming atproviding a fast and robust roof segmentation method. The roof segmentation method of the invention comprises the following steps: acquiring high-precision depth and dense three-dimensional point cloud information from multi-view aerial photograph images; based on the statistical information of 3D point cloud features with different resolutions, the 3D point cloud scene is semantically classifiedby global energy optimization, and the point cloud of buildings is obtained. Taking the point cloud of the building as the initial a priori, the fine building segmentation is carried out on the multi-view aerial photograph image. Building transition region based on depth information is computed, and the fine roof segmentation result is obtained by removing the interference of building side to fine roof segmentation from fine building segmentation result. The invention realizes fast, robust and universal roof segmentation, effectively removes the influence of the lateral transition area of thebuilding, and improves the segmentation fineness.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a roof segmentation method, system and equipment based on multi-resolution three-dimensional statistical information. Background technique [0002] Buildings are an important part of aerial images. Building extraction based on aerial images has a wide range of applications in various fields such as urban planning, 3D reconstruction of urban scenes, and virtual flight simulation. However, although the extraction of buildings has made great progress, how to extract buildings quickly, robustly and universally is still a very challenging problem. This is because the appearance features of buildings often exhibit rich diversity with changing lighting conditions, inconsistent shading conditions, and differences in image resolution and quality. At the same time, buildings often have complex shapes and structures, and will be blocked by building sides around the building, other buildings ...

AI Technical Summary

Problems solved by technology

At the same time, buildings often have complex shapes and structures, and will be blocked by the sides of buildings around the building, other buildings or trees, resulting in errors in roof segmentation

Images