Semantic segmentation network based on optical and PolSAR feature fusion

Abstract

The invention belongs to the technical field of intelligent application of remote sensing images, designs a semantic segmentation network based on optical and PolSAR feature fusion, and is used for realizing an end-to-end optical and PolSAR fusion ground feature segmentation task. The device is composed of a double-path twin convolution feature encoder, an attention mechanism module ASCAM and a symmetric jump connection decoder. Wherein the dual-path twin convolution feature encoder adopts ImageNet and a large number of labeled PolSAR and light images to carry out pre-training on each path of encoder. And then designing an ASCAM, obtaining a nonlinear influence relationship of light at a local position and each channel of the PolSAR on a classification task through an expansion space matrix, and combining the expansion space matrix with data of a double-channel twin convolution feature encoder to realize weighted guidance of attention on a feature fusion process. And finally, realizing fusion of weighted features through convolution, designing a symmetric jump connection decoder, performing jump connection on the fused features and coding process features in optical and PolSAR, and finally realizing end-to-end ground feature segmentation.

Description

technical field [0001] The invention belongs to the technical field of intelligent application of remote sensing images, and more specifically relates to the automatic semantic segmentation of ground object categories through the fusion of optical remote sensing images and PolSAR remote sensing images. Background technique [0002] Land cover segmentation and classification based on remote sensing imagery is a challenging problem due to its scale and material diversity. At present, many remote sensing image ground object segmentation tasks mainly use a single payload data. For example, many studies use visible light remote sensing images for ground object segmentation, but the effect is not good due to single spectral information and cloud cover. Some other studies use PolSAR images for ground object segmentation, but the poor image quality and high noise also lead to poor classification results. The complexity of many area types such as urban areas necessitates the use of ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the problem that the current multi-modal remote sensing image cannot be effectively fused and applied, and proposes a semantic segmentation network ASCAFNet based on the fusion of optical and PolSAR features, and realizes the useful information in PolSAR and optical images through the ASCAFNet neural network. Complementary to improve the accuracy and reliability of ground object segmentation

Images