Remote sensing image classification and labeling method based on compound graph conditional random field

Abstract

Aiming at the problem of classification and labeling of remote sensing images, the present invention discloses a method for classification and labeling of remote sensing images based on conditional random fields of composite graphs. Figure; define the correlation potential function and interaction potential function of the conditional random field; optimize the conditional random field model through the quasi-Newton method; infer the test sample through the loop belief propagation algorithm, and obtain its classification and labeling results. In the present invention, a composite graph is constructed by combining a sparse graph capable of expressing global interaction information and a spatial graph capable of expressing local spatial interaction information, which enhances the ability of the graph structure to express data, and further enhances the classification and labeling performance of conditional random fields. It has high classification labeling accuracy.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and in particular relates to a method for classifying and marking remote sensing images based on conditional random fields of compound graphs. Background technique [0002] Remote sensing technology is the most intuitive, richest and most effective technical means to detect the comprehensive information of land cover. With the rapid development of sensor technology, remote sensing images are gradually showing the characteristics of multi-spectrum, high resolution and large amount of data. The effective acquisition of a large number of comprehensive and information-rich remote sensing images provides complete information resources for the development of related scientific research, but also puts forward higher requirements for remote sensing image processing technology. [0003] In the field of remote sensing, the classification and labeling of remote sensing imag...

AI Technical Summary

Problems solved by technology

However, the spatial graph can only fuse the local interaction information of the spatial neighborhood, and lacks the ability to fuse the global interaction information, which affects the classification performance of the conditional random field to a certain extent.

Images