Method for multi-dimension segmentation of remote sensing image and representation of segmentation result hierarchical structure

Abstract

The invention provides a multi-scale image segmentation method for a remote sensing image, in particular for the remote sensing image with high spatial resolution, and constructs a relation among hierarchical structures of the segmentation results of different scales with consistent segmentation boundary. The method comprises the following steps: obtaining an initial segmentation result by a basic image segmentation method, scanning the segmented regions to establish an adjacency relation among segmented blocks, generating an initial bottom small-scale region structure, and subsequently adding features such as gray scale, texture, shape and the like on the basis to merge, adjust, and form a second-layer larger-scale segmented region structure and a third-layer large-scale segmented region structure. The course can be performed by iteration until the required-scale segmentation hierarchy and structure are formed. The generated hierarchical structures of the multi-scale segmentation regions can realize quick switching and access among the segmentation regions of different scales, and the structures are not only suitable for a watershed image segmentation algorithm, but also suitable for other segmentation methods to construct the hierarchical structures of the multi-scale segmented regions.

Description

technical field [0001] The invention relates to remote sensing image processing technology, in particular to a multi-scale segmentation method of remote sensing images and a data structure for multi-scale representation of segmentation results, the data structure is applicable to multiple segmentation methods. Background technique [0002] High-spatial-resolution images, especially high-spatial-resolution remote sensing images, provide a wealth of information about the geometric structure, texture details, and spectrum of surface objects, making it possible to observe changes in surface details and perform Large-scale remote sensing mapping and monitoring the impact of human activities on the environment become possible and have broad application prospects. [0003] Remote sensing image segmentation is the premise of ground object recognition. Therefore, using image segmentation technology to first segment remote sensing images into homogeneous regions and then use the spect...

AI Technical Summary

Problems solved by technology

These segmentation methods will give a single-scale segmentation result, and there is no technical solution to realize multi-scale segmentation at the same time, let alone establish the hierarchical structure relationship and expression of different scale segmentation results at the same time

Images