Remote sensing aircraft target classification method and device based on double triple pseudo-twin architecture

Abstract

The present application relates to a remote sensing aircraft target classification method and device based on double triplet pseudo-twin architecture. The method includes: acquiring a sample set of remote sensing aircraft targets, the sample set includes: anchor samples, positive samples and negative samples, and constructing a remote sensing aircraft target classification network based on a double triplet pseudo-twin architecture, the network includes: three based on pseudo-twins. The classification subnet of the Siamese architecture; the classification subnet includes two classification branches consisting of a feature extraction network, a fully connected layer and a classification layer; a loss function is constructed; according to the anchor samples, positive samples, negative samples and loss functions, the network is analyzed. The remote sensing aircraft target classification model is obtained by training, and the samples to be tested are input into the model to obtain the remote sensing aircraft target classification results. In this method, the contrast loss is used to improve the ability of the model to distinguish non-homologous features; the triple loss is used to shorten the distance of similar objects in the feature space, while increasing the distance of non-similar objects in the feature space to improve the classification accuracy.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular, to a method and device for classifying remote sensing aircraft targets based on a double triplet pseudo-twin architecture. Background technique [0002] With the rapid development of remote sensing technology, the resolution of remote sensing images has gradually increased, and the spatial and texture information of images has become more and more abundant. The precise identification of remote sensing aircraft targets is a hot research topic in the field of remote sensing in recent years. Its main process is to classify according to the target features extracted by the network. How to effectively extract target feature information and be able to distinguish different types of targets with small differences is the key to remote sensing aircraft target recognition. Because the targets of different types of aircraft are similar in size and shape, the differenc...

AI Technical Summary

Problems solved by technology

[0004] The existing classification model based on the twin architecture has achieved relatively advanced performance, but the recognition accuracy for fine-grained is not high

Images