Ground object classification method and device

Abstract

The invention provides a ground object classification method and device, and the method comprises the steps of obtaining live-action three-dimensional data collected and processed by an unmanned plane, and analyzing the live-action three-dimensional data to obtain a surface three-dimensional vertex, a surface patch topological structure and a texture mapping relation; filtering the vertex data through a cloth simulation algorithm to obtain a patch formed by ground vertexes; performing surface patch color feature analysis, performing vegetation region growing based on a vegetation color threshold value, and processing candidate regions of vegetation surface patches through a graph cutting algorithm to obtain accurate vegetation category surface patches; projecting a facade patch approximately perpendicular to the ground to a two-dimensional plane, recording a projection area accumulated value, and determining a regional range of the building facade in the two-dimensional plane; and back-projecting the building facade area range to the three-dimensional surface patch, and obtaining the surface patch of the building category through height-based area growth. Through the scheme, the problem of inaccurate ground object classification is solved, accurate division of regions corresponding to different ground objects can be realized, and the data classification processing speed is improved.

Description

technical field [0001] The invention relates to the field of real-scene three-dimensional data processing, in particular to a ground object classification method and device. Background technique [0002] Using remote sensing technology to interpret the types of land cover features is a hot topic in remote sensing application research, and plays an important role in the fields of smart cities and land detection. Generally, the composition or distribution of land cover mainly includes buildings, vegetation and surface structures. In order to effectively interpret the distribution types of ground features, remote sensing satellite images and laser point clouds are often used to classify ground features. However, due to the loss of three-dimensional information or missing textures in ground feature data, the classification of ground features is inaccurate. Contents of the invention [0003] In view of this, the embodiments of the present invention provide a method and device f...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the embodiment of the present invention provides a method and device for object classification to solve the problem of inaccurate object classification caused by collecting object data based on remote sensing satellites or laser point clouds

Images