Lightweight semantic segmentation method for high-resolution remote sensing image

Abstract

A lightweight semantic segmentation method for a high-resolution remote sensing image comprises the steps of network construction, training and testing. Specifically, a deep semantic segmentation network of an encoder-decoder structure is constructed for a pytorch deep learning framework, after network training is carried out based on a remote sensing image data sample set, a to-be-tested remote sensing image serves as network input. A segmentation result of the remote sensing image is obtained. According to the method, on one hand, model parameters are reduced by decomposing depth separable convolution, the calculation complexity is reduced, the semantic segmentation time of the high-resolution remote sensing image is shortened, and the semantic segmentation efficiency of the high-resolution remote sensing image is improved; and on the other hand, semantic segmentation precision is improved through multi-scale feature aggregation, a spatial attention module and gating convolution, sothat the proposed lightweight deep semantic segmentation network can accurately and efficiently realize semantic segmentation of a high-resolution remote sensing image.

Description

technical field [0001] The invention relates to a technology in the field of remote sensing image processing, in particular to a lightweight semantic segmentation method for high-resolution remote sensing images. Background technique [0002] With the development of aerospace technology, high-resolution remote sensing images are becoming more and more easy to obtain in large quantities. Using image segmentation to extract the boundaries of ground objects in remote sensing images is the basis for further analysis and utilization of high-resolution remote sensing images. Traditional high-resolution remote sensing image segmentation algorithms usually rely on artificially designed features such as texture and color to extract the boundary of objects in the image, but they can only get the boundary of the object itself, and cannot obtain the semantics of the area defined by the boundary at the same time. Information, that is, the category of features. In recent years, semantic ...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a lightweight semantic segmentation method for high-resolution remote sensing images, which solves the problem of low operating efficiency of segmentation algorithms caused by the amount of parameters and calculations for large-scale high-resolution remote sensing images faced by existing semantic segmentation networks. On the one hand, through depth-separable convolution, decomposed convolution, etc. to reduce model parameters, reduce computational complexity, shorten the time for semantic segmentation of remote sensing images, and improve the efficiency of semantic segmentation of remote sensing images

Images