Local and global depth contrast feature learning network construction method for inter-image change detection

Abstract

The invention discloses a local and global depth contrast feature learning network construction method for inter-image change detection. The method comprises the following steps: encoding an input image to obtain a global high-dimensional representation feature; constructing positive sample data of which the feature domain is similar to the global feature and negative sample data of which the feature domain is not similar to the global feature; measuring the correlation degree between the global features and the constructed positive and negative sample data; establishing a constrained priori model of hierarchical input of the feature domain; obtaining an optimal coding representation feature; iteratively optimizing the probability model, and solving a difference probability graph matrix; and outputting a binary change result graph. According to the method, structural information of hierarchical input of a feature domain is fully utilized, a network loss function based on global features, local features and prior loss of positive and negative samples is constructed, and parameters of an encoder are updated by optimizing the loss function, so that the encoder can effectively learn local and global depth contrast features between images, and the accuracy of the local and global depth contrast features is improved. And the relevance between abstract semantic information and spatial information is embodied.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a method for constructing a local and global deep contrast feature learning network for change detection between images. Background technique [0002] The change detection of remote sensing images is a process of quantitatively analyzing and determining the characteristics of ground object changes for the multi-temporal remote sensing images acquired at different times in the same area. The purpose of change detection is to find the region of change and represent it with a binary image. Change detection tasks can detect the characteristics of the earth's surface in a timely and accurate manner, and provide a basis for a better understanding of the relationship and interaction between human and natural phenomena, so that resources can be better managed and used. It has urgent scientific application needs and extensive application prospects. Th...

AI Technical Summary

Problems solved by technology

Neither of the above two methods maximizes the correlation between global features and local features and similar features (positive samples) in the feature domain, and minimizes the correlation between features that are dissimilar to global features (negative samples). Effectively create spatial associations

Images