Water-crossing bridge extraction method and device based on high-resolution remote sensing image

Abstract

The invention provides a water-crossing bridge extraction method based on a high-resolution remote sensing image, and the method comprises the steps: segmenting an original remote sensing image, and generating a segmented image; calculating the bridge width in the segmented image; communicating the water body regions in the segmented image through water body expansion to obtain a communicated water body region image; carrying out difference processing on the communicated water body region and segmented image, and marking a differential region; and performing bridge extraction from the differential region. In this way, water bodies in different remote sensing images can be automatically and accurately recognized, the bridge width is accurately obtained in combination with a statistical method, bridge expansion, corrosion and image difference are adopted for bridge extraction, the bridge position is accurately extracted, and automatic extraction of overwater bridges in the remote sensingimages is achieved. The method not only can be suitable for automatic accurate extraction of overwater bridges with different widths and different lengths, but also can be suitable for bridge extraction of high-resolution remote sensing images with meter-level and sub-meter-level spatial resolutions.

Description

technical field [0001] Embodiments of the present invention generally relate to the technical field of remote sensing image applications, and more specifically, relate to a method and device for extracting bridges across water based on high-resolution remote sensing images. Background technique [0002] As an important transportation infrastructure, bridges are one of the important tasks of the transportation department to manage and update information such as the spatial location, quantity, and technical level of bridges. With the development of high-resolution remote sensing technology, using high-resolution images to identify and extract bridges is an important research content in the field of remote sensing. In the water bridge extraction based on remote sensing images, the currently more commonly used methods mainly include object-oriented bridge extraction methods, road-based bridge extraction methods, and knowledge-based bridge extraction methods. [0003] In existin...

AI Technical Summary

Problems solved by technology

[0003] The existing object-oriented bridge extraction method is difficult to determine the segmentation scale to make it suitable for the extraction of all bridges. Most of the extraction work is semi-automatic extraction, and there are many manual interventions

The road-based bridge extraction method uses the premise that the road information in the image is known, which limits the range of target selection

Luo Jiancheng and others adopted a knowledge-based bridge extraction method, which is mainly based on the knowledge that bridges and rivers are connected, refines the image on the basis of extracted river information, detects the main line of the bridge by limiting the width, and vectorizes and expresses the features of the main line of the bridge. In order to obtain bridge information, it is difficult for this method to propose all bridges of all sizes with a single fixed bridge width limit parameter, and the extraction of some bridges will cause the main direction of the extracted bridge to deviate from the original image

Images