Target level remote sensing image change detection method based on RBM model

Abstract

The present invention discloses a target level remote sensing image change detection method based on a RBM model, mainly aims at the defects of an existing change detection method, combines a Restricted Boltzmann Machine (RBM) with target level remote sensing image change detection and is applied to remote sensing image change detection. The target level remote sensing image change detection method comprises the implementing steps of: (1) inputting gray matrices of two remote sensing images; (2) carrying out fuzzy clustering to obtain the segmented gray matrices of two remote sensing images; (3) constructing a logarithm ratio difference gray matrix to be detected; (4) carrying out pre-classification on the logarithm ratio difference gray matrix; (5) selecting a training sample; (6) training the RBM; and (7) outputting a change detection result. According to the present invention, the dependency on remote sensing image registration accuracy is reduced; the target level remote sensing image change detection method has the excellent noise immunity; and accuracy and classification accuracy of remote sensing image change detection are improved.

Description

technical field [0001] The invention belongs to the technical field of computers, and further relates to a method for detecting changes in target-level remote sensing images based on an RBM model in the technical field of image processing. Through remote sensing image change detection, it can be used in the fields of ground object coverage and utilization, natural disaster monitoring and evaluation, urban planning, map update, etc. Background technique [0002] The remote sensing image change detection method is an important technology for analyzing and understanding multi-temporal remote sensing images. It is a method for analyzing multi-temporal remote sensing images acquired at different times in the same area. Difference images are divided into two categories: changed and unchanged, focusing on identifying changes in ground objects in two remote sensing images. [0003] From the perspective of the abstract level of image processing objects, the remote sensing image chan...

AI Technical Summary

Problems solved by technology

This detection method uses the spatial information and texture information of the image to avoid the occurrence of false detection, but still has the disadvantage that it needs to select the appropriate classification threshold according to the specific remote sensing image and processing problems, which cannot be universally applied.

However, the disadvantage of this method is that it directly processes the gray value of the pixels in the difference map, does not use the spatial information of the image, and has a high dependence on the registration accuracy.

Images