Disentangled Non-Local Network for Hyperspectral and LiDAR Data Classification

TL;DR

This paper introduces a novel Disentangled Non-local network that effectively fuses hyperspectral and LiDAR data for improved joint classification, demonstrating superior performance on the Houston dataset.

Contribution

The paper presents a new attention fusion model based on DNL network that captures spectral and spatial features separately for hyperspectral and LiDAR data.

Findings

Outperforms several advanced baseline methods in joint classification tasks.

Effectively captures spectral and spatial features through multiscale and CNN modules.

Demonstrates superior accuracy on Houston dataset.

Abstract

As the ground objects become increasingly complex, the classification results obtained by single source remote sensing data can hardly meet the application requirements. In order to tackle this limitation, we propose a simple yet effective attention fusion model based on Disentangled Non-local (DNL) network for hyperspectral and LiDAR data joint classification task. In this model, according to the spectral and spatial characteristics of HSI and LiDAR, a multiscale module and a convolutional neural network (CNN) are used to capture the spectral and spatial characteristics respectively. In addition, the extracted HSI and LiDAR features are fused through some operations to obtain the feature information more in line with the real situation. Finally, the above three data are fed into different branches of the DNL module, respectively. Extensive experiments on Houston dataset show that the proposed network is superior and more effective compared to several of the most advanced baselines in HSI and LiDAR joint classification missions.