Small-sample high-resolution remote sensing image scene classification method

Abstract

The invention discloses a small-sample high-resolution remote sensing image scene classification method. The method mainly comprises the following three parts: firstly, preparing source domain and target domain training sample sets, respectively selecting a proper amount of images from different remote sensing scene data sets to respectively construct a source training sample set with a large number of samples and a target domain training sample set with a small number of samples, and simulating the condition of small sample classification; secondly, AlexNet is selected as a DCNN main network, and deep convolution feature extraction is carried out on the sample image in combination with an FPN network layer fusion strategy; and finally, realizing feature distribution migration from a source domain to a target domain by using an improved distribution adaptation algorithm WS-BDA based on single sample weighting, and training a target classifier by using migrated feature data to finish classification of remote sensing scene images.

Description

technical field [0001] The invention relates to a small sample high spatial resolution remote sensing image scene classification method, which belongs to the technical field of image processing and pattern recognition. Background technique [0002] Scene classification is an important subject in the field of remote sensing image processing, and it has been widely used in spatial modeling, land planning, agricultural surveys, and disaster monitoring. Compared with ordinary images, high spatial resolution remote sensing images contain more abundant space, shape, texture and spectral information, and the imaging results are easily affected by factors such as shooting angle, shooting time and weather interference. features are more difficult. In addition, when completing the actual remote sensing image classification task, it can be found that there are very few labeled samples available for training in some ground object categories, resulting in insufficient classification acc...

AI Technical Summary

Problems solved by technology

Even if these conditions can be met, when the distribution of sample data changes or the output scene of the model changes, the original model cannot be applied to the new scene, and it needs to be retrained and learned, which is less flexible.

Images