Regular house roof automatic extraction method based on remote sensing image spectral information

Abstract

The invention discloses a regular house roof automatic extraction method based on remote sensing image spectral information. Firstly, spectral value information of pixel points in a collection area is classified, edge points are searched, then under the limitation of the fitting degree, edge lines fit a plurality of straight lines, the edge lines intersect to generate corner points, if the corner points are edge points, the corner points are reserved and are connected pairwise to generate pseudo edge lines, the pseudo edge lines are divided into three types according to the attributes of the points on the pseudo edge lines, and the pseudo edge lines are divided into three types. The method comprises the following steps: for pseudo side line points of which the spectral values are within a roof prior spectral range and which are edge points, reserving the pseudo side lines, and dividing the pseudo side lines into two types according to the relation between the lengths and included angles of the pseudo side lines and limit thresholds, and for the pseudo side lines of which the lengths and the included angles are within the limit thresholds, the pseudo side lines are true side lines. And finally, generating a roof surface by the true sidelines. According to the method, the house roof surface can be rapidly extracted, meanwhile, errors caused by subjectivity of a user are reduced, the method is less affected by the environment, and high-efficiency automatic house roof extraction can be realized.

Description

technical field [0001] The invention belongs to the technical field of computer vision target recognition, and relates to a method for automatically extracting regular house roofs based on spectral information of remote sensing images and a cross-border application. Background technique [0002] With the continuous development and integration of computer technology and spatial information technology, users hope to obtain high-quality and efficient data products through the availability of computer vision models and big data of remote sensing images. The early method of using surveying and mapping technology to collect large-scale topographic maps in the field is not only greatly affected by the environment, but also has low efficiency. Contents of the invention [0003] In order to overcome the problems existing in the prior art, the object of the present invention is to provide a method for automatically extracting regular house roofs based on remote sensing image spectra...

AI Technical Summary

Problems solved by technology

The early method of using surveying and mapping technology to collect large-scale topographic maps in the field is not only greatly affected by the environment, but also has low efficiency

Images