Relational network-based remote sensing image small sample target identification method in complex scene

Abstract

The invention discloses a relational network-based remote sensing image small sample target identification method in a complex scenex. The invention aims to solve the problem of insufficient remote sensing ship weather scene coverage under the condition of small samples. Remote sensing ship images in five typical weather scenes are generated through style migration, an original feature and measurement module is used for carrying out fine adjustment on the remote sensing ship images in different scenes, and a fine adjustment result serves as a training set and a support set and is used for optimizing network parameters and improving the identification precision of a network. Style migration is adopted to process the remote sensing images, the weather scene coverage range of training set data and support set data is increased, high-dimensional feature vector clustering center extraction is subsequently carried out on the support set data, the calculation amount of a relational network isreduced, the accuracy of a network identification result is improved, and meanwhile, the identification speed of the network is ensured.

Description

technical field [0001] The invention belongs to the field of deep learning and relates to a method for recognizing small-sample targets in remote sensing images by using relational networks and metric learning. Background technique [0002] When using deep learning for image recognition, a large amount of training set data is required to adjust network parameters and learn image features. Therefore, the accuracy of recognition results is often proportional to the number of data sets. For tasks such as remote sensing ship image recognition, it is difficult to obtain high-quality data sets, and other means need to be adopted to assist in improving the accuracy of recognition results. In the past two years, more and more scholars have begun to study the problem of target recognition based on small sample data, among which metric learning is a more effective method, which is modeled according to the distance distribution between samples, using the principle that similar samples ...

AI Technical Summary

Problems solved by technology

This type of network training is a kind of "meta-knowledge", which is more transferable in the case of small samples. However, there are few domestic studies on the use of metric learning methods to identify small-sample targets of remote sensing ships, and they have not yet combined remote sensing image targets. Targeted optimization of the characteristics

Images