Hyper-parameter determination method for critical convolutional layer of remote-sensing classification convolution neural network

Abstract

The present invention provides a hyper-parameter determination method for the critical convolutional layer of a remote-sensing classification convolution neural network. The method comprises the steps of constructing a convolutional neural network sample set; constructing a convolutional neural network structure; deterring the hyper-parameters of the critical layer of the convolutional neural network; selecting one convolutional layer as the critical layer, presetting the convolutional kernel size of the critical layer, and calculating the convolution scale; based on the convolutional kernel of the critical layer and the convolution scale, calculating the convolution step length according to a preset rule; presetting the convolutional kernels of other convolutional layers to be kernel size, and presetting the convolution step lengths of other convolutional layers to be 1; and conducting the mean-value down-sampling or the maximum-value down-sampling as the subsequent down-sampling. According to the technical scheme of the invention, based on the image input size and the convolution kernel size, the convolution scale concept is proposed and is adaptive to the remote-sensing spatial scale. On the above basis, an input size and convolution scale-based method for jointly determining the hyper-parameters of the critical layers is provided. In this way, the parameter adjustment time required for the algorithm is reduced, and the object-oriented remote-sensing classification precision is improved.

Description

technical field [0001] The invention relates to the field of remote sensing classification, in particular to a method for determining key convolutional layer hyperparameters of a remote sensing classification convolutional neural network. Background technique [0002] Geographic target recognition through remote sensing images is an important link in the application of remote sensing technology to practical problems. Whether it is thematic information extraction, dynamic change monitoring, thematic mapping, or remote sensing database construction, remote sensing image classification technology is inseparable. Object-oriented remote sensing technology gathers many adjacent pixels to form a spatial image object with certain semantics. It integrates the spatial, texture and spectral information contained in remote sensing data. Its core is image object construction and image object classification. Convolutional neural network is a deep learning algorithm. One of them, the algor...

AI Technical Summary

Problems solved by technology

However, when the convolutional neural network is applied to remote sensing image classification, there is still a problem of how to determine the hyperparameters (convolution kernel size and step size) of the convolutional neural network according to the input remote sensing images of different resolutions.

Images