Automatic Batch Extraction Method of Horizontal Vector Outlines of Buildings in Satellite Images

Abstract

The invention provides an automatic batch extraction method for horizontal vector contours of buildings in satellite images. The method comprises the steps of firstly using a K-means algorithm to class the images to obtain the backbone parts of the buildings, and solving the problem of selection of initial seed points by taking mass centers of all building areas; after the areas of all the seed points are grown, separating the building areas from surrounding areas by virtue of image edge information and removing non-building areas according to characteristic parameters such as rectangularity and strip index to realize the automatic extraction of the horizontal pixel contours of the buildings; then using techniques such has Hough transformation and block processing to perform linear vector processing to the horizontal pixel contours, and finally obtaining the horizontal vector contours of all buildings in a batch. The automatic batch extraction method for the horizontal vector contours of the buildings in the satellite images is applicable to the batch and quick extraction of the horizontal vector contours of common polygonal buildings with top views which are of straight-line segment structures in the satellite images.

Description

technical field [0001] The invention relates to a method for automatically batch-extracting the horizontal vector outlines of buildings from a single satellite image of building groups, in particular to the automatic batch-extraction of the horizontal vector outlines of buildings whose top view is a straight-line structural polygon. Background technique [0002] Using a single satellite image to achieve virtual reconstruction of 3D scenes is a very active research topic. It is mainly used in urban construction planning, military scene simulation, resource management, earthquake relief simulation, etc. In the 3D virtual reconstruction of real scenes, most of them are ordinary buildings with simple structures and straight-line structural polygons in the top view. How to realize the rapid modeling of such a large number of ordinary buildings is the key to efficient reconstruction of 3D buildings. How to automatically extract the horizontal outlines of buildings from the images ...

AI Technical Summary

Problems solved by technology

The research objects of the above methods are all grayscale images, not suitable for color images, so the rich color information in color images cannot be used

In addition, the snake model method is sensitive to the initial position, and needs to rely on other mechanisms to place the initial contour near the image features of interest, otherwise the contour extraction will fail. At present, most of them use manual selection to set the initial boundary, which is not only very cumbersome , and it makes it difficult to automatically generate contour lines

However, there are two deficiencies in the more commonly used region growing method: first, the selection of the initial seed point

Most of the current methods for selecting seed points are manually selected, requiring a lot of manual intervention, time-consuming, laborious, and inefficient

The second is the selection of the growth threshold

The result of this method is greatly affected by the selection of the distance threshold. In order to obtain better results, each building in the image needs to correspond to a different distance threshold. In the past, the method of setting the distance threshold was often manually set based on experience. low efficiency

Images