Remote sensing image water area segmentation and extraction method for super-pixel classification and recognition

Abstract

The invention aims to solve the problems that the remote sensing image water area segmentation extraction method in the prior art is poor in self-adaptation due to the fact that a segmentation critical value is manually set, a large number of non-water-area land types exist in a result, and a large number of impulse noise exists in the result. The invention provides a remote sensing image water area segmentation and extraction method for super-pixel classification and identification. In combination with an improved linear clustering super-pixel segmentation method, a remote sensing image is divided into a plurality of super-pixels which are good in homogeneity, compact in layout and capable of well keeping edge information; superpixels are used as a feature extraction unit, water area features in a remote sensing image are extracted from three perspectives of spectrum, texture and terrain, the features of a water area and non-water areas are described more accurately, a typical learning sample library is constructed, and a nonlinear support vector machine is used for supervised classification. Experimental results show that the method can overcome the defects of the prior art and remarkably improve the water area segmentation and extraction precision and speed of the remote sensing image.

Description

technical field [0001] The invention relates to a method for segmenting and extracting water areas of remote sensing images, in particular to a method for segmenting and extracting water areas of remote sensing images based on superpixel classification and recognition, and belongs to the technical field of remote sensing image segmentation. Background technique [0002] Water is an important part of the natural ecosystem and a necessary substance for the survival of humans and other organisms on the earth. Water is closely related to the survival and development of humans. It is used in agricultural irrigation, industrial development, aquaculture, shipping and transportation, and maintaining ecological balance play an irreplaceable role. However, with the rapid development of global industry, rapid population growth, and accelerated urbanization, excessive and irrational use of water resources, coupled with the unbalanced distribution of water resources in time and space and...

AI Technical Summary

Problems solved by technology

[0012] In view of the deficiencies of the prior art, the remote sensing image water area segmentation and extraction method for superpixel classification and recognition provided by the present invention, for the prior art remote sensing image water area segmentation and extraction method, artificially setting the segmentation threshold leads to poor self-adaptation, and there are a large number of errors in the result. There are a lot of impulsive noises in non-water areas and the results. A water segmentation and extraction method for remote sensing images based on superpixel classification and recognition is proposed. Combined with an improved linear clustering superpixel segmentation method, the remote sensing images are divided into several homogeneous regions. Superpixels with good quality, compact layout and better ability to maintain edge information, using superpixels as feature extraction units, extract water features in remote sensing images from three angles of spectrum, texture and terrain, and more accurately describe water and non-water features, construct a typical learning sample library, and use nonlinear support vector machines for supervised classification

Images