High-resolution remote sensing image supervised segmentation method based on variable Gaussian hybrid model

Abstract

The invention provides a high-resolution remote sensing image supervised segmentation method based on a variable Gaussian hybrid model, and the method comprises the steps: carrying out the supervised sampling of each ground feature class in a to-be-segmented high-resolution remote sensing image, and calculating the frequency of the gray value of each pixel in the corresponding ground feature class; building a variable Gaussian hybrid model for different ground feature classes in a gray measurement space of the high-resolution remote sensing image; enabling a spatial relation to be fused, and building a target function of the high-resolution remote sensing image; and carrying out the dividing of a target function matrix of the high-resolution remote sensing image according to the maximum probability measurement principle. The method can achieve the precise fitting of the complex distribution features of the high-resolution remote sensing image, is good in anti-noise performance, determines a Gaussian component number through the adaption to the same ground feature class, and achieves the precise fitting of the complex distribution features of the high-resolution remote sensing image. After the fusion of the spatial relation, the method well overcomes the impact on the segmentation result from geometric noise and pixel abnormality, and improves the segmentation precision.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a high-resolution remote sensing image supervision segmentation method based on a variable Gaussian mixture model. Background technique [0002] Image segmentation is the basic work and key link in image processing and pattern recognition. Since high-resolution remote sensing data can present surface coverage information more clearly and meticulously, it is increasingly widely used in accurate object segmentation. High-resolution remote sensing images have the following two typical new features: (1) the distribution curves of the same kind of ground objects present multi-peak distribution and asymmetric distribution characteristics, and (2) the overlapping of distribution curves of different ground objects increases. The above features increase the difficulty of image segmentation. [0003] Since the Gaussian mixture modeling (GMM) has the ability to fit any probabil...

AI Technical Summary

Problems solved by technology

To this end, Xiong Tao, Zeng Jia et al. (Xiong Tao, Jiang Wanshou and Li Lelin. Semi-supervised classification of remote sensing images based on Gaussian mixture model, Journal of Wuhan University Information Science Edition. 2011.36(1): 108-112; ZENGJ, XIEL.Type -2FuzzyGaussianMixtureModels.PatternRecognition, 2008,41(12):3636-3643.) proposes to establish a GMM model for each category area, which provides an effective way to model the complex distribution characteristics of high-resolution remote sensing images. However, the proposer sets all The number of components of the category GMM is the same, so there is a problem that the GMM with a fixed number of components cannot accurately model all categories, and because the spatial relationship between pixels is not considered, it cannot deal with the increased overlap of different surface object distribution curves in high-resolution remote sensing images. Difficult to segment and sensitive to noise

Images