Integrating global spatial features in CNN based Hyperspectral/SAR imagery classification

TL;DR

This paper introduces a dual-branch CNN that integrates geographic location data with pixel features for improved land cover classification in hyperspectral and SAR remote sensing images.

Contribution

It proposes a novel dual-branch CNN architecture that fuses global geographic information with pixel features for enhanced remote sensing image classification.

Findings

Outperforms traditional single-channel CNN methods.

Effective on both hyperspectral and PolSAR imagery.

Improves classification accuracy and universality.

Abstract

The land cover classification has played an important role in remote sensing because it can intelligently identify things in one huge remote sensing image to reduce the work of humans. However, a lot of classification methods are designed based on the pixel feature or limited spatial feature of the remote sensing image, which limits the classification accuracy and universality of their methods. This paper proposed a novel method to take into the information of remote sensing image, i.e., geographic latitude-longitude information. In addition, a dual-branch convolutional neural network (CNN) classification method is designed in combination with the global information to mine the pixel features of the image. Then, the features of the two neural networks are fused with another fully neural network to realize the classification of remote sensing images. Finally, two remote sensing images are used to verify the effectiveness of our method, including hyperspectral imaging (HSI) and polarimetric synthetic aperture radar (PolSAR) imagery. The result of the proposed method is superior to the traditional single-channel convolutional neural network.