Lunar meteorite crater identification method and device based on depth residual U-Net and storage medium

Abstract

The invention provides a lunar meteorite crater recognition method and device based on a deep residual U-Net and a storage medium, and the method comprises the steps: constructing a U-Net network model based on a residual unit, carrying out the mapping combination of first historical data and second historical data, constructing a training set, inputting the training set into the U-Net network model, carrying out the training, obtaining a first prediction value, screening and de-weighting the first predicted value to obtain a second predicted value, calculating error loss between the second predicted value and the true value of the input data, updating weight parameters of the U-Net network model, and identifying the lunar meteorite crater image by using the trained U-Net network model of which the error loss meets a preset threshold value. Different features of a network model are combined by designing a U-shaped network based on a residual unit, so that the identification effect and accuracy of the lunar meteorite crater are improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a moon crater recognition method, device and storage medium based on depth residual U-Net. Background technique [0002] At present, with the continuous development and progress of deep learning technology, Convolutional Neural Networks (CNN) has been widely used in the field of image processing, playing an important role in target detection, classification and recognition, and in the field of remote sensing images. , its appearance also provides a new method for efficiently identifying craters. [0003] At present, the recognition of craters is divided into visual recognition and automatic recognition algorithms. There are crater detection through template matching, crater recognition based on Canny method and edge matching, etc. These traditional methods based on image processing and image registration Although the crater identification method can effectively identif...

Images