Highway route automatic extraction method based on remote-sensing digital image

Abstract

The invention discloses a highway route automatic extraction method based on a remote-sensing digital image. The highway route automatic extraction method comprises the following steps of converting a remote-sensing image of a road of a confirmed region into a vector polygon image of a binary image of a spectral region of the road; removing a small object and conducting noise reduction processing; confirming a main length and a main direction of a polygon region; confirming sectional widths of all sides, confirming a central line of the road, and according to the central line and the width of the road, using a polygon overlapping merge algorithm in a buffer region to conduct equal-width expanding to obtain a road region; and finally generating a specification road network. The highway route automatic extraction method based on the remote-sensing digital image can effectively distinguish a road outline, efficiently extract information, and effectively conduct line processing on the road.

Description

technical field [0001] The invention relates to a computer automatic interpretation of ground elements based on remote sensing digital images, which belongs to the technical field of computer vision, and in particular to a computer algorithm for automatic extraction of continuous vector information of ground motor vehicle roads based on remote sensing images, so as to automatically form images Vector illustration of the motor vehicle road network within the frame. Background technique [0002] With the development of digital photography technology, remote sensing application technology based on optical images has been gradually replaced by digital remote sensing images in recent years. The improvement of computer performance has made the digital image processing technology develop greatly, and the computer automatic recognition technology (computer vision) of objects based on digital image information has become an emerging technical field. As an obvious linear feature, the...

AI Technical Summary

Problems solved by technology

[0003] 1. The extraction of linear images based on image features cannot separate roads and other features such as the contours of buildings, which can easily lead to misreading, misjudgment, missed judgment and decision-making errors

[0004] 2. The judgment and interpretation conditions of the recognition are relatively simple, and there is a big gap, which makes the user's sorting time, analysis and decision-making time increase, so that the efficiency of information extraction is very low

[0005] 3. There are big deficiencies in the accuracy of road extraction and the amount of information. The center line of the road is intermittent, without linear processing, and there is a lack of information on the width of the road and the type of road surface

Images