Remote sensing image semantic segmentation method and device

Abstract

The invention relates to a remote sensing image semantic segmentation method and device. The method comprises the steps of obtaining a to-be-segmented remote sensing image; inputting the to-be-segmented remote sensing image into a pre-established self-attention multi-scale feature aggregation network, and obtaining an initial prediction result of the to-be-segmented remote sensing image output bythe pre-established self-attention multi-scale feature aggregation network; up-sampling the initial prediction result of the remote sensing image to be segmented to the image size of the remote sensing image to be segmented, and obtaining the final prediction result of the remote sensing image to be segmented; according to the method provided by the invention, the association between modal features and spatial information can be effectively enhanced, the multi-scale target downward text information perception capability is improved, and a finer semantic annotation result is obtained.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a remote sensing image semantic segmentation method and device. Background technique [0002] In recent years, with the gradual and in-depth research of deep learning technology in the field of image processing, image processing methods based on deep learning, especially fully convolutional neural networks, have developed rapidly in the field of remote sensing. In image processing in remote sensing scenarios, semantic segmentation can obtain category labeling information at the target pixel level, and has broad application prospects in land planning, wartime investigation, and environmental monitoring. However, the semantic segmentation method based on deep learning is a data-driven method that requires a large amount of accurately labeled data. The traditional manual labeling method is costly and inefficient, so it is particularly important to improve th...

AI Technical Summary

Problems solved by technology

However, existing methods usually directly merge or add multi-modal images or features directly, and its feature learning is completely dependent on the performance of convolutional neural networks, ignoring the differences in the inherent data structure and feature complexity of different modalities, which are easy to introduce Redundant features, resulting in reduced labeling performance, network scale and parameter redundancy

Images