Multi-spectral image change detection method based on probability segmentation and Gaussian mixture clustering

Abstract

The invention belongs to the technical field of electronic equipment identification method or device, and discloses a multi-spectral image change detection method based on probability segmentation andGaussian mixture clustering. The method comprises the steps of firstly, inputting two original multi-spectral images of the same region and different time, and constructing the mixed difference imageHDS by CVA and SAM; secondly, segmenting the difference image into super-pixel space by using statistical region merging algorithm, and finally, using a K-Means algorithm to initialize Gaussian mixture model to overcome its shortcomings of convergence to local optimal solution, fitting the probability distribution of super-pixel feature space, and obtaining the change detection results by using Bayesian discriminant rule based on minimum error rate. The invention makes better use of the amplitude change information and the angle change information of the spectral vector, obtains the local structure characteristic of the image by using the super pixel segmentation, and effectively improves the detection accuracy of the change region in the SAR image.

Description

technical field [0001] The invention belongs to the technical field of identification methods or devices using electronic equipment, and in particular relates to a multispectral image change detection method based on probability segmentation and Gaussian mixture clustering. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: With the rapid development of remote sensing technology in recent years, the amount of remote sensing data is increasing day by day, and is widely used in fields such as environmental monitoring, atmospheric analysis and urban planning. Among them, the change detection of multispectral remote sensing images is applied to military and civilian fields, mainly involving the positioning of natural disaster areas such as floods, fires and earthquakes, the analysis of urban expansion, and the evaluation of strike effects in military applications. Therefore, research on multispectral remote sensing im...

AI Technical Summary

Problems solved by technology

However, this method is to segment the original dual-temporal remote sensing image separately, and then calculate the distance measure value between the superpixels. Due to the difference in the shape and structure of the target between the dual-temporal images, it is necessary to calculate the similar distance before the boundary configuration. accurate, which will destroy the geometric information of the target

Images