Building contour automatic aggregation method and device, equipment and storage medium

Abstract

The invention discloses a building contour automatic aggregation method and device, equipment and a storage medium. The method comprises the following steps: acquiring a contour parameter set of buildings in a target area; classifying the buildings according to a spatial topological relation on the basis of the contour parameter set and screening conditions to obtain an isolated building set and a non-isolated building set; the screening conditions comprise a first screening condition based on a building external rectangular frame and a second screening condition based on a building contour; combining the buildings with the adjacency relation in the non-isolated building set to obtain a combined building cluster; and based on the isolated building set and all the combined building clusters, obtaining a contour aggregation result of the buildings in the target area. According to the method, the retrieval time of the isolated building can be shortened, the method is not limited by application scenes, and the building contour clustering efficiency is improved on the basis of ensuring that the clustering result is accurate and reliable.

Description

Technical field [0001] The present invention relates to the field of spatial clustering, and in particular, to a building contour automatic polymerization method, apparatus, device, and storage medium. Background technique [0002] Geography Information System (GIS) is an emerging marginal discipline integrating computer science, surveying and mapping remote sensing, geography, environmental science, spatial science, information science and management science. Spatial analysis is the core and soul of GIS, but also an important component of achieving spatial data value. Spatial analysis with the properties information of spatial data, can provide powerful, rich spatial data query features. Spatial cluster as an important part of spatial analysis, refers to the composition of the object in the space data set by a similar or related object, with a higher similarity or the same feature, and the difference between different classes. Clustering is a learning method of non-monitoring, w...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, each element is judged one by one based on the Delaunay triangulation or space directly according to the topological relationship, but the Delaunay triangulation method generally first needs to establish a triangulation for all nodes of the outline elements of the entire building, and build a network when the scale is large The time and space overhead is large, and it contains facets and complex face fusion operations, resulting in inefficiency

In the existing technology, clustering is also carried out based on the center point, spatial distance, area and other quantitative values, but the application scope is generally limited to large-scale spatial scenarios such as cartographic synthesis, and it is difficult to meet the needs of individual buildings in smaller scenarios. Apps that represent

In the prior art, feature points are also calculated by using additional data sources such as digital surface model (DSM, Digital Surface Model), digital elevation model (DEM, Digital Elevation Model) or digital orthophoto image (DOM, Digital OrthophotoMap), However, under real operating conditions, more data sources mean more cost and overhead, reducing the efficiency of contour aggregation

Images