Remote sensing image semantic segmentation method, storage medium and computing device

Abstract

The invention discloses a remote sensing image semantic segmentation method, a storage medium and computing equipment, and the method comprises the steps: carrying out equal-proportion cutting of a large-scale remote sensing image and a corresponding label image, and obtaining a small remote sensing image for training; randomly processing the small remote sensing images and the corresponding labelimages, and numbering all the generated training images and the corresponding label images in sequence to obtain an expanded remote sensing image data set for training; constructing a loss function and sequentially putting the training pictures into a semantic segmentation network to obtain a trained remote sensing image semantic segmentation network; traversing all pixels of the whole feature map and carrying out optimization operation, then carrying out merging operation on the randomly cut small remote sensing images, carrying out majority voting on overlapped parts to obtain a segmentation result of the large-scale remote sensing images, and completing feature map merging operation. The method is high in processing speed and good in effect.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and specifically relates to a large-scale remote sensing image semantic segmentation method based on spatial information and multi-scale fusion, a storage medium and a computing device, which are used to identify the land cover type of each pixel on a remote sensing image, and to use Issues such as urban planning and road monitoring. Background technique [0002] Large-scale remote sensing images have been widely used in research in various fields such as traditional geography, environmental science, and earth science due to their advantages of globalization, low cost, and high accuracy. Compared with ordinary images, remote sensing images have the characteristics of large monitoring range, fast data acquisition and short cycle. Secondly, for areas with harsh natural conditions and difficult ground work, it is easier to obtain data. Finally, different remote sensing information can be o...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a large-scale remote sensing image semantic segmentation method, storage medium and computing equipment based on spatial information and multi-scale fusion to improve the accuracy of remote sensing image semantic segmentation. Meet the needs of practical engineering, and solve the problems of low segmentation accuracy of high-resolution large-scale remote sensing images and difficult recognition of targets of different scales in existing technologies

Images