Land classification method based on high-resolution remote sensing image

Abstract

The invention relates to a land classification method based on a high-resolution remote sensing image, and the application of the high-resolution remote sensing image can effectively achieve the dynamic monitoring of land utilization, and improves the scientificity of land management. By using the ERFNet in combination with the conditional random field (CRF), the semantic segmentation precision can be further improved on the basis of reducing computing resources, and the land use classification work can be better completed; and an efficient land use classification method plays an important role in promoting the development of land utilization, urban planning, environmental monitoring and military fields.

Description

technical field [0001] The invention belongs to the field of deep learning, relates to an image segmentation technology and a land use classification algorithm, uses a convolutional neural network as a basic tool, and particularly relates to a land classification method based on high-resolution remote sensing images. Background technique [0002] The full convolutional network replaces the fully connected layer in the convolutional neural network with a convolutional layer. Compared with the traditional convolutional neural network, the input image size of the full convolutional network does not need to be fixed, which facilitates the convolutional neural network in Applications in semantic segmentation, in addition to using deconvolutional layers for upsampling, generalized the use of convolutional networks for end-to-end semantic segmentation. At the same time, in order to improve the accuracy of semantic segmentation, the full convolutional network introduces skip connect...

AI Technical Summary

Problems solved by technology

ResNet can effectively solve the problems of slower network convergence and lower accuracy caused by increasing the number of neural network layers after the deep neural network grows to a certain depth.

Images