Adaptive Remote Sensing Scene Classification Method Fused with Meteorological Environment Parameters and Image Information

Abstract

The invention relates to an adaptive remote sensing scene classification method based on the fusion of meteorological environment parameters and image information, which can be used in geographical surveys, environmental monitoring, etc.; it solves the problem that existing methods based on image brightness values ​​are easily disturbed by the environment, thus causing features based on visible light The differences are large, and it is impossible to effectively identify and understand remote sensing scene problems. The method steps include: 1) After the weather data is standardized, the weather data feature F is obtained by using a fully connected network wea ; 2) utilize the weather data feature F that step 1) obtains wea Construct an adaptive convolutional neural network; 3) extract remote sensing image features F using the adaptive convolutional neural network constructed in step 2) rgb , and use the SoftMax classifier to classify it; 4) train and test the adaptive convolutional neural network, and use the trained adaptive convolutional neural network to classify remote sensing images.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to an adaptive remote sensing scene classification method for the fusion of meteorological environment parameters and image information, which can be used in geographical and national surveys, environmental monitoring, and the like. Background technique [0002] With the development of aerospace technology, more and more high-resolution satellites are launched into space to obtain data on the earth's surface for the purpose of disaster monitoring and agricultural production estimation. Usually, the data transmitted from satellites to the ground has a huge frame. In order to make full use of these Scene classification is a very important preprocessing method for large and high-resolution remote sensing data. It is of great help to subsequent tasks such as target recognition, change detection, and image retrieval. Currently, scene classification methods for remote sensin...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the problem that the existing method based on image brightness values ​​is easily disturbed by the environment, which causes large differences in characteristics based on visible light, and cannot effectively recognize and understand remote sensing scenes, and proposes a fusion of meteorological environment parameters and image information Adaptive remote sensing scene classification method to make the scene expression more refined and sufficient, thereby improving the accuracy of scene classification

Images