Neural network, building extracting method for remote sensing images, medium and computing device

Abstract

The invention discloses a neural network, a building extraction method for remote sensing images, a medium and a computing device. The neural network is used for building extraction of the remote sensing images and comprises: an input layer, first to fifth convolutional layers and first to fourth pooling layers in a VGG (Visual Geometry Group) network; a first single-scale fusion layer, wherein the input end of the first single-scale fusion layer is connected to the output end of the first convolution layer; second to fifth single-scale fusion layers, wherein the input ends of the second to fifth single-scale fusion layers are respectively connected to the output ends of the second to fifth convolutional layers; first to fourth up-sampling layers, wherein the input ends of the first to fourth up-sampling layers are respectively connected to the output ends of the second to fifth single-scale fusion layers; a multi-scale splicing fusion layer, wherein the input end of the multi-scale splicing fusion layer is connected to the output ends of the first single-scale fusion layer and the first to fourth up-sampling layers; and an outputting layer. Through the neural network disclosed bythe invention, densely-distributed buildings with various scales can be effectively processed and the automatic extraction precision of the buildings is improved.

Description

technical field [0001] The invention relates to the fields of neural network and image processing, in particular to a neural network, a method for extracting buildings from remote sensing images, a medium and a computing device. Background technique [0002] With the rapid development of sensor technology, the spatial resolution of remote sensing images has been continuously improved. Inspired by deep learning algorithms in the field of computer vision, scholars currently use convolutional neural networks to implement semantic segmentation tasks for remote sensing images. Although some cutting-edge methods have achieved good results in semantic segmentation tasks of remote sensing images, they have not considered some characteristics of remote sensing images themselves. First of all, in conventional computer vision semantic segmentation tasks, there are generally only a few to dozens of targets on the image to be detected, and the distribution of targets is relatively loose...

AI Technical Summary

Problems solved by technology

However, there is no effective method in the prior art that can make full use of convolutional neural networks to extract feature information of buildings of different scales in remote sensing images.

Images