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, specifically 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 increasingly easy to obtain in large quantities. The use of 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 boundaries of objects in the image. However, they can only obtain the boundaries of the objects themselves and cannot simultaneously obtain the semantics of the areas defined by the boundaries. Information, that is, the category of features. In recent years, s...

Images