Remote sensing image change detection method based on multi-feature fusion

Abstract

The invention discloses a remote sensing image change detection method based on multi-feature fusion. By using current change detection method, an omission ratio is high and whole change detection precision is not high. By using the method of the invention, the above problems can be solved. The method comprises the following steps: firstly, inputting difference of two time phase remote sensing images, acquiring a gray scale difference graph, calculating a variance of the gray scale difference graph and setting a threshold so as to determine whether to carry out morphology pretreatment on the two time phase images; then, calculating a neighborhood difference graph and a Gabor texture feature difference graph, using a Treelet algorithm to fuse three groups of difference graphs, and carrying out maximum entropy segmentation on the fused difference graphs so as to obtain an initial detection result; finally, using an area threshold method to remove parts of isolated pseudo change information so as to obtain a final detection result graph. Experiment shows that by using the method of the invention, an edge feature of a region of variation can be maintained, noise interference can be effectively restrained and the omission ratio can be reduced simultaneously. The method of the invention can be used in environment protection, city program construction and natural disaster detection fields.

Description

technical field [0001] The invention belongs to the technical field of image processing, and specifically relates to a remote sensing image change detection method based on multi-feature fusion, which can be used for remote sensing image analysis in many fields such as environmental protection, agriculture, water conservancy and military affairs. Background technique [0002] Remote sensing image change detection is a hot issue in remote sensing image processing. It compares and analyzes two remote sensing images taken at the same location at different times, so as to detect the change information of the area. This technology is widely used in many fields of national economy and national defense construction, such as environmental protection, urban planning and construction, geographic data update, and dynamic monitoring of strategic targets such as roads and bridges in the military. [0003] Changes in ground features are reflected in remote sensing images as changes in ima...

AI Technical Summary

Problems solved by technology

This method is prone to accumulating classification errors, and majority voting does not guarantee optimal detection results

In the article "An object-based change detection approach by integrating intensity and texture differences", Lingcao Huang and other scholars proposed a change detection method that combines grayscale features and texture features, in which the texture features are described by gradient vectors. The detection obtained by this method As a result, the edges are well maintained, but there are more false alarms

Images